diff --git "a/git.diff" "b/git.diff" new file mode 100644--- /dev/null +++ "b/git.diff" @@ -0,0 +1,8890 @@ +diff --git a/unit8/ppo_gae.ipynb b/unit8/ppo_gae.ipynb +index cb2af65..5dcce4b 100644 +--- a/unit8/ppo_gae.ipynb ++++ b/unit8/ppo_gae.ipynb +@@ -59,60 +59,33 @@ + "metadata": {}, + "outputs": [], + "source": [ +- "# class TransformerMLP(nn.Module):\n", +- "\n", +- "# def __init__(self, input_dim, intermediate_dim, hidden_dim):\n", +- "# super().__init__()\n", +- "# self.up_proj = nn.Linear(input_dim, intermediate_dim, bias=True)\n", +- "# self.down_proj = nn.Linear(intermediate_dim, hidden_dim, bias=True)\n", +- "# self.gate_proj = nn.Linear(input_dim, intermediate_dim, bias=True)\n", +- "# self.act_fn = nn.SiLU()\n", +- "\n", +- "# def forward(self, x):\n", +- "# return self.down_proj(self.act_fn(self.gate_proj(x)) * self.up_proj(x))\n", +- "\n", +- "# class Agent(nn.Module):\n", +- "\n", +- "# def __init__(self, observation_dim, action_dim):\n", +- "# super().__init__()\n", +- "# self.critic = nn.Sequential(\n", +- "# TransformerMLP(observation_dim, 2 * 768, 768),\n", +- "# nn.SiLU(),\n", +- "# TransformerMLP(768, 2 * 768, 1)\n", +- "# )\n", +- "# self.actor = nn.Sequential(\n", +- "# TransformerMLP(observation_dim, 2 * 768, 768),\n", +- "# nn.SiLU(),\n", +- "# TransformerMLP(768, 4 * 768, action_dim),\n", +- "# nn.SiLU(),\n", +- "# TransformerMLP(action_dim, 4 * action_dim, action_dim)\n", +- "# )\n", +- "\n", +- "# def get_statue_value(self, observation):\n", +- "# return self.critic(observation)\n", +- " \n", +- "# def get_action_logits(self, observation):\n", +- "# action_logits = self.actor(observation)\n", +- "# return action_logits\n", +- " \n", ++ "class TransformerMLP(nn.Module):\n", ++ "\n", ++ " def __init__(self, input_dim, intermediate_dim, hidden_dim):\n", ++ " super().__init__()\n", ++ " self.up_proj = nn.Linear(input_dim, intermediate_dim, bias=True)\n", ++ " self.down_proj = nn.Linear(intermediate_dim, hidden_dim, bias=True)\n", ++ " self.gate_proj = nn.Linear(input_dim, intermediate_dim, bias=True)\n", ++ " self.act_fn = nn.SiLU()\n", ++ "\n", ++ " def forward(self, x):\n", ++ " return self.down_proj(self.act_fn(self.gate_proj(x)) * self.up_proj(x))\n", + "\n", + "class Agent(nn.Module):\n", + "\n", + " def __init__(self, observation_dim, action_dim):\n", + " super().__init__()\n", + " self.critic = nn.Sequential(\n", +- " nn.Linear(observation_dim, 64, bias=True),\n", +- " nn.Tanh(),\n", +- " nn.Linear(64, 64, bias=True),\n", +- " nn.Tanh(),\n", +- " nn.Linear(64, 1, bias=True),\n", ++ " TransformerMLP(observation_dim, 2 * 768, 768),\n", ++ " nn.SiLU(),\n", ++ " TransformerMLP(768, 2 * 768, 1)\n", + " )\n", + " self.actor = nn.Sequential(\n", +- " nn.Linear(observation_dim, 64, bias=True),\n", +- " nn.Tanh(),\n", +- " nn.Linear(64, 64, bias=True),\n", +- " nn.Tanh(),\n", +- " nn.Linear(64, action_dim, bias=True),\n", ++ " TransformerMLP(observation_dim, 2 * 768, 768),\n", ++ " nn.SiLU(),\n", ++ " TransformerMLP(768, 4 * 768, action_dim),\n", ++ " nn.SiLU(),\n", ++ " TransformerMLP(action_dim, 4 * action_dim, action_dim)\n", + " )\n", + "\n", + " def get_state_value(self, observation):\n", +@@ -125,13 +98,13 @@ + }, + { + "cell_type": "code", +- "execution_count": null, ++ "execution_count": 7, + "metadata": {}, + "outputs": [ + { + "data": { + "application/vnd.jupyter.widget-view+json": { +- "model_id": "985972a63cde44c1bf92802a35e40866", ++ "model_id": "21253ded4e014db58269632eed54e64c", + "version_major": 2, + "version_minor": 0 + }, +@@ -146,21 +119,8293 @@ + "name": "stdout", + "output_type": "stream", + "text": [ +- "Rollout 0/9766, Reward: -418.871±50.839, Episode_length: 70.400±9.211\n", +- "Rollout 1/9766, Reward: -66.662±67.258, Episode_length: 116.400±31.639\n", +- "Rollout 2/9766, Reward: -2299.141±1797.852, Episode_length: 492.100±264.612\n" ++ "Rollout 0/9766, Reward: -493.992±140.992, Episode_length: 60.900±10.173\n", ++ "Rollout 1/9766, Reward: -633.824±145.424, Episode_length: 70.800±6.765\n", ++ "Rollout 2/9766, Reward: -610.880±174.397, Episode_length: 71.900±12.445\n", ++ "Rollout 3/9766, Reward: -581.710±151.312, Episode_length: 68.300±10.228\n", ++ "Rollout 4/9766, Reward: -463.408±51.392, Episode_length: 68.100±12.437\n", ++ "Rollout 5/9766, Reward: -306.047±84.166, Episode_length: 88.200±9.325\n", ++ "Rollout 6/9766, Reward: -298.074±167.366, Episode_length: 114.800±31.849\n", ++ "Rollout 7/9766, Reward: -677.080±124.149, Episode_length: 163.700±35.956\n", ++ "Rollout 8/9766, Reward: -190.272±102.590, Episode_length: 306.200±93.474\n", ++ "Rollout 9/9766, Reward: -262.222±23.351, Episode_length: 181.500±48.527\n", ++ "Rollout 10/9766, Reward: -261.418±28.319, Episode_length: 203.500±45.998\n", ++ "Rollout 11/9766, Reward: -260.215±27.618, Episode_length: 306.000±76.948\n", ++ "Rollout 12/9766, Reward: -250.285±58.446, Episode_length: 366.400±173.519\n", ++ "Rollout 13/9766, Reward: -226.067±62.880, Episode_length: 459.700±287.198\n", ++ "Rollout 14/9766, Reward: -198.394±35.611, Episode_length: 342.400±170.478\n", ++ "Rollout 15/9766, Reward: -167.612±36.222, Episode_length: 286.500±118.389\n", ++ "Rollout 16/9766, Reward: -176.591±38.937, Episode_length: 537.000±162.144\n", ++ "Rollout 17/9766, Reward: -213.853±130.571, Episode_length: 675.100±285.956\n", ++ "Rollout 18/9766, Reward: -221.737±132.351, Episode_length: 632.200±274.432\n", ++ "Rollout 19/9766, Reward: -160.593±28.990, Episode_length: 370.600±85.766\n", ++ "Rollout 20/9766, Reward: -180.115±59.665, Episode_length: 912.800±109.501\n", ++ "Rollout 21/9766, Reward: -80.691±12.588, Episode_length: 1000.000±0.000\n", ++ "Rollout 22/9766, Reward: -84.105±15.948, Episode_length: 1000.000±0.000\n", ++ "Rollout 23/9766, Reward: -42.638±15.381, Episode_length: 1000.000±0.000\n", ++ "Rollout 24/9766, Reward: -19.083±34.681, Episode_length: 998.600±4.200\n", ++ "Rollout 25/9766, Reward: -28.783±24.810, Episode_length: 1000.000±0.000\n", ++ "Rollout 26/9766, Reward: -27.691±10.012, Episode_length: 1000.000±0.000\n", ++ "Rollout 27/9766, Reward: -11.999±23.779, Episode_length: 1000.000±0.000\n", ++ "Rollout 28/9766, Reward: 184.821±29.654, Episode_length: 760.700±90.490\n", ++ "Rollout 29/9766, Reward: 71.323±67.698, Episode_length: 975.900±59.820\n", ++ "Rollout 30/9766, Reward: -4.781±22.034, Episode_length: 1000.000±0.000\n", ++ "Rollout 31/9766, Reward: -4.897±21.969, Episode_length: 1000.000±0.000\n", ++ "Rollout 32/9766, Reward: -17.288±13.460, Episode_length: 1000.000±0.000\n", ++ "Rollout 33/9766, Reward: 49.582±51.211, Episode_length: 994.400±12.508\n", ++ "Rollout 34/9766, Reward: 168.397±61.980, Episode_length: 751.600±176.340\n", ++ "Rollout 35/9766, Reward: 129.725±53.891, Episode_length: 856.200±220.093\n", ++ "Rollout 36/9766, Reward: 79.566±226.239, Episode_length: 739.200±287.386\n", ++ "Rollout 37/9766, Reward: 147.060±133.528, Episode_length: 614.800±96.528\n", ++ "Rollout 38/9766, Reward: 224.284±31.966, Episode_length: 496.100±170.416\n", ++ "Rollout 39/9766, Reward: 159.044±146.833, Episode_length: 380.200±149.460\n", ++ "Rollout 40/9766, Reward: 102.620±179.429, Episode_length: 340.300±148.520\n", ++ "Rollout 41/9766, Reward: 133.558±145.959, Episode_length: 397.500±165.333\n", ++ "Rollout 42/9766, Reward: 142.215±85.857, Episode_length: 593.500±205.595\n", ++ "Rollout 43/9766, Reward: 95.569±112.783, Episode_length: 465.400±166.264\n", ++ "Rollout 44/9766, Reward: 105.757±142.261, Episode_length: 511.500±234.630\n", ++ "Rollout 45/9766, Reward: 30.706±213.348, Episode_length: 647.300±290.661\n", ++ "Rollout 46/9766, Reward: 36.599±164.192, Episode_length: 348.200±245.424\n", ++ "Rollout 47/9766, Reward: 171.131±11.414, Episode_length: 770.500±105.173\n", ++ "Rollout 48/9766, Reward: 187.277±49.951, Episode_length: 582.900±141.986\n", ++ "Rollout 49/9766, Reward: 213.642±40.350, Episode_length: 549.400±154.142\n", ++ "Rollout 50/9766, Reward: 175.108±52.018, Episode_length: 686.300±209.202\n", ++ "Rollout 51/9766, Reward: 229.578±18.755, Episode_length: 448.200±25.003\n", ++ "Rollout 52/9766, Reward: 253.267±18.791, Episode_length: 407.800±61.998\n", ++ "Rollout 53/9766, Reward: -108.782±524.036, Episode_length: 303.300±143.483\n", ++ "Rollout 54/9766, Reward: 213.276±30.814, Episode_length: 551.100±139.958\n", ++ "Rollout 55/9766, Reward: 172.436±69.402, Episode_length: 707.200±297.225\n", ++ "Rollout 56/9766, Reward: 202.398±50.161, Episode_length: 544.300±175.502\n", ++ "Rollout 57/9766, Reward: 137.296±49.290, Episode_length: 892.100±224.268\n", ++ "Rollout 58/9766, Reward: 176.721±64.506, Episode_length: 836.700±244.966\n", ++ "Rollout 59/9766, Reward: 157.896±59.934, Episode_length: 910.700±209.757\n", ++ "Rollout 60/9766, Reward: 186.248±55.908, Episode_length: 757.100±309.653\n", ++ "Rollout 61/9766, Reward: 131.740±42.079, Episode_length: 956.400±130.800\n", ++ "Rollout 62/9766, Reward: 192.244±45.705, Episode_length: 670.000±232.283\n", ++ "Rollout 63/9766, Reward: 213.722±44.095, Episode_length: 591.800±197.177\n", ++ "Rollout 64/9766, Reward: 183.782±48.090, Episode_length: 767.200±240.157\n", ++ "Rollout 65/9766, Reward: 209.597±34.871, Episode_length: 591.000±171.664\n", ++ "Rollout 66/9766, Reward: 197.315±53.116, Episode_length: 666.300±247.174\n", ++ "Rollout 67/9766, Reward: 155.791±56.893, Episode_length: 775.500±275.915\n", ++ "Rollout 68/9766, Reward: 158.479±47.961, Episode_length: 898.700±204.581\n", ++ "Rollout 69/9766, Reward: 137.620±17.680, Episode_length: 1000.000±0.000\n", ++ "Rollout 70/9766, Reward: 243.625±21.089, Episode_length: 422.100±49.095\n", ++ "Rollout 71/9766, Reward: 125.412±23.599, Episode_length: 1000.000±0.000\n", ++ "Rollout 72/9766, Reward: 254.578±23.234, Episode_length: 331.500±35.446\n", ++ "Rollout 73/9766, Reward: 237.952±13.514, Episode_length: 400.900±22.034\n", ++ "Rollout 74/9766, Reward: 235.613±18.662, Episode_length: 427.800±96.870\n", ++ "Rollout 75/9766, Reward: 172.309±122.708, Episode_length: 415.800±214.316\n", ++ "Rollout 76/9766, Reward: 251.843±19.978, Episode_length: 306.600±29.544\n", ++ "Rollout 77/9766, Reward: 202.349±48.500, Episode_length: 747.800±297.929\n", ++ "Rollout 78/9766, Reward: 273.145±17.480, Episode_length: 305.200±26.951\n", ++ "Rollout 79/9766, Reward: 242.586±30.190, Episode_length: 452.200±234.471\n", ++ "Rollout 80/9766, Reward: 251.133±19.550, Episode_length: 322.200±45.731\n", ++ "Rollout 81/9766, Reward: 239.044±59.791, Episode_length: 472.700±298.246\n", ++ "Rollout 82/9766, Reward: 186.048±67.203, Episode_length: 586.100±339.363\n", ++ "Rollout 83/9766, Reward: 218.153±56.195, Episode_length: 471.500±269.494\n", ++ "Rollout 84/9766, Reward: 191.906±65.522, Episode_length: 383.100±209.679\n", ++ "Rollout 85/9766, Reward: 220.234±24.252, Episode_length: 387.500±134.140\n", ++ "Rollout 86/9766, Reward: 182.807±80.074, Episode_length: 420.800±211.772\n", ++ "Rollout 87/9766, Reward: 184.535±74.468, Episode_length: 500.300±235.725\n", ++ "Rollout 88/9766, Reward: 227.977±22.447, Episode_length: 325.800±66.516\n", ++ "Rollout 89/9766, Reward: 269.567±20.128, Episode_length: 270.100±23.488\n", ++ "Rollout 90/9766, Reward: 255.571±27.551, Episode_length: 314.100±40.476\n", ++ "Rollout 91/9766, Reward: 264.814±22.711, Episode_length: 288.400±53.226\n", ++ "Rollout 92/9766, Reward: 255.521±24.588, Episode_length: 269.900±27.548\n", ++ "Rollout 93/9766, Reward: 210.451±60.543, Episode_length: 417.900±240.383\n", ++ "Rollout 94/9766, Reward: 273.081±16.891, Episode_length: 249.600±18.763\n", ++ "Rollout 95/9766, Reward: 234.647±42.624, Episode_length: 357.800±165.231\n", ++ "Rollout 96/9766, Reward: 220.620±54.113, Episode_length: 440.400±250.439\n", ++ "Rollout 97/9766, Reward: 276.940±14.501, Episode_length: 301.500±27.303\n", ++ "Rollout 98/9766, Reward: 268.763±18.873, Episode_length: 286.400±23.049\n", ++ "Rollout 99/9766, Reward: 263.166±28.741, Episode_length: 292.900±35.495\n", ++ "Rollout 100/9766, Reward: 270.357±17.591, Episode_length: 277.000±28.983\n", ++ "Rollout 101/9766, Reward: 257.672±15.231, Episode_length: 337.000±45.460\n", ++ "Rollout 102/9766, Reward: 199.398±107.622, Episode_length: 337.900±96.369\n", ++ "Rollout 103/9766, Reward: 247.959±35.338, Episode_length: 347.500±75.764\n", ++ "Rollout 104/9766, Reward: 267.046±22.413, Episode_length: 313.000±14.248\n", ++ "Rollout 105/9766, Reward: 255.967±16.308, Episode_length: 339.100±33.180\n", ++ "Rollout 106/9766, Reward: 246.023±13.709, Episode_length: 357.500±38.609\n", ++ "Rollout 107/9766, Reward: 234.470±15.841, Episode_length: 460.100±44.137\n", ++ "Rollout 108/9766, Reward: 214.030±77.157, Episode_length: 424.500±101.773\n", ++ "Rollout 109/9766, Reward: 220.325±29.748, Episode_length: 475.800±107.060\n", ++ "Rollout 110/9766, Reward: 59.191±99.448, Episode_length: 871.300±178.544\n", ++ "Rollout 111/9766, Reward: 174.102±80.884, Episode_length: 591.500±200.423\n", ++ "Rollout 112/9766, Reward: 195.668±57.874, Episode_length: 568.800±229.263\n", ++ "Rollout 113/9766, Reward: 247.125±9.130, Episode_length: 377.100±55.423\n", ++ "Rollout 114/9766, Reward: 248.151±19.243, Episode_length: 305.400±27.840\n", ++ "Rollout 115/9766, Reward: 247.336±41.382, Episode_length: 362.100±218.142\n", ++ "Rollout 116/9766, Reward: 257.766±14.833, Episode_length: 352.800±184.990\n", ++ "Rollout 117/9766, Reward: 262.475±23.289, Episode_length: 234.100±12.637\n", ++ "Rollout 118/9766, Reward: 166.148±49.652, Episode_length: 854.400±291.277\n", ++ "Rollout 119/9766, Reward: 259.931±39.619, Episode_length: 343.900±219.819\n", ++ "Rollout 120/9766, Reward: 240.136±12.668, Episode_length: 493.700±237.352\n", ++ "Rollout 121/9766, Reward: 266.570±18.885, Episode_length: 286.700±26.511\n", ++ "Rollout 122/9766, Reward: 238.731±48.767, Episode_length: 352.800±217.965\n", ++ "Rollout 123/9766, Reward: 209.328±52.986, Episode_length: 702.900±347.811\n", ++ "Rollout 124/9766, Reward: 262.613±25.024, Episode_length: 263.400±20.323\n", ++ "Rollout 125/9766, Reward: 264.680±22.544, Episode_length: 242.000±15.453\n", ++ "Rollout 126/9766, Reward: 270.910±20.037, Episode_length: 245.600±20.328\n", ++ "Rollout 127/9766, Reward: 218.081±54.932, Episode_length: 889.000±226.366\n", ++ "Rollout 128/9766, Reward: 163.548±37.400, Episode_length: 974.600±76.200\n", ++ "Rollout 129/9766, Reward: 259.766±29.513, Episode_length: 379.800±256.431\n", ++ "Rollout 130/9766, Reward: 259.570±18.277, Episode_length: 257.500±13.603\n", ++ "Rollout 131/9766, Reward: 188.133±83.569, Episode_length: 759.400±309.896\n", ++ "Rollout 132/9766, Reward: 267.765±24.347, Episode_length: 273.100±14.131\n", ++ "Rollout 133/9766, Reward: 238.669±17.359, Episode_length: 343.700±12.149\n", ++ "Rollout 134/9766, Reward: 252.716±17.759, Episode_length: 364.500±21.565\n", ++ "Rollout 135/9766, Reward: 242.668±16.018, Episode_length: 547.300±28.796\n", ++ "Rollout 136/9766, Reward: 250.696±11.712, Episode_length: 773.500±167.250\n", ++ "Rollout 137/9766, Reward: 238.311±20.209, Episode_length: 405.900±118.001\n", ++ "Rollout 138/9766, Reward: 244.650±17.987, Episode_length: 523.400±199.214\n", ++ "Rollout 139/9766, Reward: 92.711±246.809, Episode_length: 252.000±122.911\n", ++ "Rollout 140/9766, Reward: 263.606±12.596, Episode_length: 318.000±17.164\n", ++ "Rollout 141/9766, Reward: 206.088±171.369, Episode_length: 283.300±61.041\n", ++ "Rollout 142/9766, Reward: 240.241±34.519, Episode_length: 376.400±209.831\n", ++ "Rollout 143/9766, Reward: 218.947±72.410, Episode_length: 294.200±40.538\n", ++ "Rollout 144/9766, Reward: 78.079±197.567, Episode_length: 453.800±215.777\n", ++ "Rollout 145/9766, Reward: 99.196±172.651, Episode_length: 522.500±100.462\n", ++ "Rollout 146/9766, Reward: 182.631±65.782, Episode_length: 575.100±282.177\n", ++ "Rollout 147/9766, Reward: 216.943±44.788, Episode_length: 570.700±270.919\n", ++ "Rollout 148/9766, Reward: 198.986±51.307, Episode_length: 564.300±238.919\n", ++ "Rollout 149/9766, Reward: 188.895±46.361, Episode_length: 515.000±247.627\n", ++ "Rollout 150/9766, Reward: 214.531±36.592, Episode_length: 427.900±193.117\n", ++ "Rollout 151/9766, Reward: 229.318±33.685, Episode_length: 368.300±29.947\n", ++ "Rollout 152/9766, Reward: 229.905±55.245, Episode_length: 411.300±197.123\n", ++ "Rollout 153/9766, Reward: 246.186±19.696, Episode_length: 373.800±17.503\n", ++ "Rollout 154/9766, Reward: 249.414±16.212, Episode_length: 362.300±34.377\n", ++ "Rollout 155/9766, Reward: 229.184±28.727, Episode_length: 478.100±149.942\n", ++ "Rollout 156/9766, Reward: 236.576±16.763, Episode_length: 458.600±43.642\n", ++ "Rollout 157/9766, Reward: 223.012±23.217, Episode_length: 459.800±96.972\n", ++ "Rollout 158/9766, Reward: 229.423±35.003, Episode_length: 396.100±62.638\n", ++ "Rollout 159/9766, Reward: 221.384±27.177, Episode_length: 349.700±62.629\n", ++ "Rollout 160/9766, Reward: 220.824±28.056, Episode_length: 356.000±58.686\n", ++ "Rollout 161/9766, Reward: 248.919±23.501, Episode_length: 405.200±98.304\n", ++ "Rollout 162/9766, Reward: 212.929±67.831, Episode_length: 368.600±60.004\n", ++ "Rollout 163/9766, Reward: 254.446±26.474, Episode_length: 338.600±27.281\n", ++ "Rollout 164/9766, Reward: 230.214±32.541, Episode_length: 428.400±88.373\n", ++ "Rollout 165/9766, Reward: 241.541±15.517, Episode_length: 463.900±152.096\n", ++ "Rollout 166/9766, Reward: 230.099±34.573, Episode_length: 463.800±89.738\n", ++ "Rollout 167/9766, Reward: 251.456±23.494, Episode_length: 304.400±13.328\n", ++ "Rollout 168/9766, Reward: 254.346±16.554, Episode_length: 301.100±14.639\n", ++ "Rollout 169/9766, Reward: 248.517±46.130, Episode_length: 357.000±98.625\n", ++ "Rollout 170/9766, Reward: 220.596±27.186, Episode_length: 449.000±108.792\n", ++ "Rollout 171/9766, Reward: 215.465±37.656, Episode_length: 463.800±109.722\n", ++ "Rollout 172/9766, Reward: 200.292±47.880, Episode_length: 525.400±117.662\n", ++ "Rollout 173/9766, Reward: 5.383±22.292, Episode_length: 1000.000±0.000\n", ++ "Rollout 174/9766, Reward: 3.429±16.044, Episode_length: 1000.000±0.000\n", ++ "Rollout 175/9766, Reward: 17.280±81.209, Episode_length: 899.000±202.179\n", ++ "Rollout 176/9766, Reward: -3.393±14.562, Episode_length: 1000.000±0.000\n", ++ "Rollout 177/9766, Reward: 237.501±27.637, Episode_length: 401.000±49.782\n", ++ "Rollout 178/9766, Reward: 234.607±20.676, Episode_length: 421.800±35.913\n", ++ "Rollout 179/9766, Reward: -11.207±21.438, Episode_length: 1000.000±0.000\n", ++ "Rollout 180/9766, Reward: -61.321±201.881, Episode_length: 912.400±262.800\n", ++ "Rollout 181/9766, Reward: 63.600±318.910, Episode_length: 414.200±173.076\n", ++ "Rollout 182/9766, Reward: -157.779±360.821, Episode_length: 442.900±367.193\n", ++ "Rollout 183/9766, Reward: -90.413±419.234, Episode_length: 254.200±159.599\n", ++ "Rollout 184/9766, Reward: 13.553±350.352, Episode_length: 239.000±113.425\n", ++ "Rollout 185/9766, Reward: -112.566±453.408, Episode_length: 216.700±119.604\n", ++ "Rollout 186/9766, Reward: -110.347±460.703, Episode_length: 218.700±121.380\n", ++ "Rollout 187/9766, Reward: -309.662±605.944, Episode_length: 213.500±111.498\n", ++ "Rollout 188/9766, Reward: 184.387±232.350, Episode_length: 283.900±74.855\n", ++ "Rollout 189/9766, Reward: 15.161±457.801, Episode_length: 276.500±98.196\n", ++ "Rollout 190/9766, Reward: -498.825±289.432, Episode_length: 91.100±69.424\n", ++ "Rollout 191/9766, Reward: -175.121±410.244, Episode_length: 232.700±183.693\n", ++ "Rollout 192/9766, Reward: -19.749±392.033, Episode_length: 263.400±123.768\n", ++ "Rollout 193/9766, Reward: -197.367±438.270, Episode_length: 270.600±276.574\n", ++ "Rollout 194/9766, Reward: -166.710±426.312, Episode_length: 219.000±153.892\n", ++ "Rollout 195/9766, Reward: -47.637±428.668, Episode_length: 353.300±259.801\n", ++ "Rollout 196/9766, Reward: -115.317±396.455, Episode_length: 499.000±424.393\n", ++ "Rollout 197/9766, Reward: -69.219±461.248, Episode_length: 271.400±131.993\n", ++ "Rollout 198/9766, Reward: -18.506±400.153, Episode_length: 312.100±204.085\n", ++ "Rollout 199/9766, Reward: -28.729±369.908, Episode_length: 726.900±378.985\n", ++ "Rollout 200/9766, Reward: 100.658±261.332, Episode_length: 550.300±319.912\n", ++ "Rollout 201/9766, Reward: -160.269±417.778, Episode_length: 723.000±423.127\n", ++ "Rollout 202/9766, Reward: 159.167±31.245, Episode_length: 849.400±165.558\n", ++ "Rollout 203/9766, Reward: 138.880±140.821, Episode_length: 755.300±184.442\n", ++ "Rollout 204/9766, Reward: 146.859±145.755, Episode_length: 675.300±254.603\n", ++ "Rollout 205/9766, Reward: 195.159±45.538, Episode_length: 479.100±215.719\n", ++ "Rollout 206/9766, Reward: 189.551±49.130, Episode_length: 561.500±245.493\n", ++ "Rollout 207/9766, Reward: 167.665±70.684, Episode_length: 683.800±318.946\n", ++ "Rollout 208/9766, Reward: 195.880±35.718, Episode_length: 573.500±186.681\n", ++ "Rollout 209/9766, Reward: 164.223±134.293, Episode_length: 556.400±98.664\n", ++ "Rollout 210/9766, Reward: 144.532±138.667, Episode_length: 631.200±215.252\n", ++ "Rollout 211/9766, Reward: 115.630±166.806, Episode_length: 424.500±162.492\n", ++ "Rollout 212/9766, Reward: 165.413±57.075, Episode_length: 648.900±280.614\n", ++ "Rollout 213/9766, Reward: 213.797±26.693, Episode_length: 445.900±102.001\n", ++ "Rollout 214/9766, Reward: 228.277±13.575, Episode_length: 397.300±74.736\n", ++ "Rollout 215/9766, Reward: 221.561±27.762, Episode_length: 442.600±194.236\n", ++ "Rollout 216/9766, Reward: 166.156±116.720, Episode_length: 519.900±212.703\n", ++ "Rollout 217/9766, Reward: 254.005±17.817, Episode_length: 327.200±42.581\n", ++ "Rollout 218/9766, Reward: 267.112±20.263, Episode_length: 288.100±17.660\n", ++ "Rollout 219/9766, Reward: 258.230±14.616, Episode_length: 279.600±14.101\n", ++ "Rollout 220/9766, Reward: 263.475±22.488, Episode_length: 266.000±16.817\n", ++ "Rollout 221/9766, Reward: 272.733±19.149, Episode_length: 303.600±17.631\n", ++ "Rollout 222/9766, Reward: 252.939±13.495, Episode_length: 284.000±23.711\n", ++ "Rollout 223/9766, Reward: 138.014±19.959, Episode_length: 1000.000±0.000\n", ++ "Rollout 224/9766, Reward: 272.953±16.443, Episode_length: 283.100±27.646\n", ++ "Rollout 225/9766, Reward: 268.480±19.970, Episode_length: 260.000±23.414\n", ++ "Rollout 226/9766, Reward: 274.262±16.979, Episode_length: 278.000±51.092\n", ++ "Rollout 227/9766, Reward: 270.265±17.939, Episode_length: 240.100±18.300\n", ++ "Rollout 228/9766, Reward: 265.826±17.373, Episode_length: 263.000±29.526\n", ++ "Rollout 229/9766, Reward: 258.151±22.057, Episode_length: 247.800±12.820\n", ++ "Rollout 230/9766, Reward: 277.965±18.788, Episode_length: 253.100±30.645\n", ++ "Rollout 231/9766, Reward: 266.805±19.567, Episode_length: 249.600±13.177\n", ++ "Rollout 232/9766, Reward: 140.643±365.033, Episode_length: 234.300±54.807\n", ++ "Rollout 233/9766, Reward: 287.821±12.733, Episode_length: 239.100±22.407\n", ++ "Rollout 234/9766, Reward: 273.156±10.524, Episode_length: 239.700±30.113\n", ++ "Rollout 235/9766, Reward: 267.947±17.707, Episode_length: 236.400±24.311\n", ++ "Rollout 236/9766, Reward: 265.501±23.382, Episode_length: 226.400±12.249\n", ++ "Rollout 237/9766, Reward: 134.250±385.702, Episode_length: 298.500±238.211\n", ++ "Rollout 238/9766, Reward: 278.296±14.352, Episode_length: 254.700±33.868\n", ++ "Rollout 239/9766, Reward: 272.213±18.889, Episode_length: 244.100±25.610\n", ++ "Rollout 240/9766, Reward: 281.300±11.211, Episode_length: 243.700±21.624\n", ++ "Rollout 241/9766, Reward: 276.689±22.431, Episode_length: 236.800±14.621\n", ++ "Rollout 242/9766, Reward: 267.059±21.664, Episode_length: 225.900±18.014\n", ++ "Rollout 243/9766, Reward: 136.899±433.527, Episode_length: 207.700±43.729\n", ++ "Rollout 244/9766, Reward: 194.596±224.937, Episode_length: 203.700±44.692\n", ++ "Rollout 245/9766, Reward: 199.623±231.068, Episode_length: 200.400±42.356\n", ++ "Rollout 246/9766, Reward: 283.694±23.277, Episode_length: 219.300±13.402\n", ++ "Rollout 247/9766, Reward: 271.750±18.600, Episode_length: 214.500±17.107\n", ++ "Rollout 248/9766, Reward: 280.730±21.350, Episode_length: 224.300±21.480\n", ++ "Rollout 249/9766, Reward: 277.377±18.944, Episode_length: 232.300±19.617\n", ++ "Rollout 250/9766, Reward: 271.297±21.945, Episode_length: 246.000±21.863\n", ++ "Rollout 251/9766, Reward: 268.259±13.686, Episode_length: 238.100±30.310\n", ++ "Rollout 252/9766, Reward: 279.662±19.022, Episode_length: 224.300±19.627\n", ++ "Rollout 253/9766, Reward: 197.631±209.573, Episode_length: 263.400±112.223\n", ++ "Rollout 254/9766, Reward: 282.206±13.167, Episode_length: 223.700±17.692\n", ++ "Rollout 255/9766, Reward: 272.448±22.517, Episode_length: 245.500±51.325\n", ++ "Rollout 256/9766, Reward: 272.307±18.466, Episode_length: 214.700±20.910\n", ++ "Rollout 257/9766, Reward: 277.221±10.613, Episode_length: 228.200±33.867\n", ++ "Rollout 258/9766, Reward: 272.523±16.495, Episode_length: 221.600±17.454\n", ++ "Rollout 259/9766, Reward: 282.112±16.329, Episode_length: 230.800±25.534\n", ++ "Rollout 260/9766, Reward: 285.457±11.749, Episode_length: 225.400±13.433\n", ++ "Rollout 261/9766, Reward: 248.991±40.585, Episode_length: 330.500±228.191\n", ++ "Rollout 262/9766, Reward: 252.341±14.396, Episode_length: 297.200±44.043\n", ++ "Rollout 263/9766, Reward: 257.213±25.741, Episode_length: 309.100±48.350\n", ++ "Rollout 264/9766, Reward: 263.330±15.131, Episode_length: 279.000±30.305\n", ++ "Rollout 265/9766, Reward: 271.459±14.341, Episode_length: 250.200±25.035\n", ++ "Rollout 266/9766, Reward: 273.461±18.217, Episode_length: 257.900±19.233\n", ++ "Rollout 267/9766, Reward: 269.277±24.366, Episode_length: 324.200±113.544\n", ++ "Rollout 268/9766, Reward: 260.013±24.006, Episode_length: 255.800±15.753\n", ++ "Rollout 269/9766, Reward: 224.677±68.321, Episode_length: 308.400±102.054\n", ++ "Rollout 270/9766, Reward: 267.718±21.054, Episode_length: 270.200±26.992\n", ++ "Rollout 271/9766, Reward: 196.602±140.090, Episode_length: 416.700±250.493\n", ++ "Rollout 272/9766, Reward: 255.713±34.383, Episode_length: 283.600±62.500\n", ++ "Rollout 273/9766, Reward: 250.232±26.956, Episode_length: 304.300±88.991\n", ++ "Rollout 274/9766, Reward: 221.245±117.402, Episode_length: 294.700±64.369\n", ++ "Rollout 275/9766, Reward: 262.331±11.774, Episode_length: 261.400±22.064\n", ++ "Rollout 276/9766, Reward: 264.855±12.542, Episode_length: 254.900±19.736\n", ++ "Rollout 277/9766, Reward: 272.710±21.028, Episode_length: 275.400±34.162\n", ++ "Rollout 278/9766, Reward: 264.170±27.331, Episode_length: 274.800±91.548\n", ++ "Rollout 279/9766, Reward: 268.329±19.427, Episode_length: 255.600±12.282\n", ++ "Rollout 280/9766, Reward: 276.250±12.336, Episode_length: 262.300±24.170\n", ++ "Rollout 281/9766, Reward: 276.428±14.643, Episode_length: 243.900±31.121\n", ++ "Rollout 282/9766, Reward: 258.402±49.079, Episode_length: 330.600±223.959\n", ++ "Rollout 283/9766, Reward: 191.582±230.758, Episode_length: 262.300±40.487\n", ++ "Rollout 284/9766, Reward: 268.555±18.861, Episode_length: 276.900±25.399\n", ++ "Rollout 285/9766, Reward: 34.762±342.859, Episode_length: 211.500±79.663\n", ++ "Rollout 286/9766, Reward: 270.702±19.548, Episode_length: 286.700±28.274\n", ++ "Rollout 287/9766, Reward: 263.748±21.453, Episode_length: 291.700±18.773\n", ++ "Rollout 288/9766, Reward: 262.249±27.848, Episode_length: 269.900±20.710\n", ++ "Rollout 289/9766, Reward: 270.771±21.921, Episode_length: 269.600±33.106\n", ++ "Rollout 290/9766, Reward: 266.317±18.410, Episode_length: 271.700±27.691\n", ++ "Rollout 291/9766, Reward: 268.577±16.173, Episode_length: 259.000±18.336\n", ++ "Rollout 292/9766, Reward: 283.139±15.544, Episode_length: 249.100±15.339\n", ++ "Rollout 293/9766, Reward: 272.719±23.744, Episode_length: 268.100±15.604\n", ++ "Rollout 294/9766, Reward: 268.909±23.673, Episode_length: 251.500±18.635\n", ++ "Rollout 295/9766, Reward: 272.410±19.763, Episode_length: 292.000±46.282\n", ++ "Rollout 296/9766, Reward: 270.550±20.022, Episode_length: 264.900±19.501\n", ++ "Rollout 297/9766, Reward: 263.218±19.708, Episode_length: 279.300±17.141\n", ++ "Rollout 298/9766, Reward: 261.563±15.902, Episode_length: 289.300±32.644\n", ++ "Rollout 299/9766, Reward: 251.952±25.502, Episode_length: 317.200±60.582\n", ++ "Rollout 300/9766, Reward: 120.581±298.428, Episode_length: 273.900±97.467\n", ++ "Rollout 301/9766, Reward: 228.934±78.451, Episode_length: 333.600±39.462\n", ++ "Rollout 302/9766, Reward: 257.555±15.358, Episode_length: 299.400±44.657\n", ++ "Rollout 303/9766, Reward: 261.728±14.430, Episode_length: 308.100±17.259\n", ++ "Rollout 304/9766, Reward: 263.814±19.861, Episode_length: 296.300±20.794\n", ++ "Rollout 305/9766, Reward: 265.868±20.966, Episode_length: 294.800±16.339\n", ++ "Rollout 306/9766, Reward: 272.346±13.887, Episode_length: 287.700±22.055\n", ++ "Rollout 307/9766, Reward: 262.603±20.831, Episode_length: 268.800±19.441\n", ++ "Rollout 308/9766, Reward: 280.273±13.756, Episode_length: 281.000±26.963\n", ++ "Rollout 309/9766, Reward: 254.589±15.590, Episode_length: 314.700±21.996\n", ++ "Rollout 310/9766, Reward: 260.975±19.993, Episode_length: 276.300±22.900\n", ++ "Rollout 311/9766, Reward: 261.723±15.858, Episode_length: 254.200±14.176\n", ++ "Rollout 312/9766, Reward: 246.985±13.732, Episode_length: 279.300±101.645\n", ++ "Rollout 313/9766, Reward: 278.745±20.294, Episode_length: 246.900±11.760\n", ++ "Rollout 314/9766, Reward: 271.685±21.840, Episode_length: 252.900±16.392\n", ++ "Rollout 315/9766, Reward: 279.084±15.723, Episode_length: 245.900±20.935\n", ++ "Rollout 316/9766, Reward: 276.933±24.872, Episode_length: 221.200±17.342\n", ++ "Rollout 317/9766, Reward: 282.243±10.545, Episode_length: 255.900±16.202\n", ++ "Rollout 318/9766, Reward: 268.298±23.113, Episode_length: 244.800±18.126\n", ++ "Rollout 319/9766, Reward: 266.040±17.948, Episode_length: 241.800±19.909\n", ++ "Rollout 320/9766, Reward: 271.773±12.275, Episode_length: 254.300±13.357\n", ++ "Rollout 321/9766, Reward: 269.753±17.667, Episode_length: 262.500±19.663\n", ++ "Rollout 322/9766, Reward: 271.140±21.695, Episode_length: 292.400±24.287\n", ++ "Rollout 323/9766, Reward: 262.845±15.337, Episode_length: 271.400±17.783\n", ++ "Rollout 324/9766, Reward: 263.841±17.422, Episode_length: 275.500±21.001\n", ++ "Rollout 325/9766, Reward: 274.892±21.317, Episode_length: 268.900±18.727\n", ++ "Rollout 326/9766, Reward: 214.405±150.428, Episode_length: 267.300±58.298\n", ++ "Rollout 327/9766, Reward: 271.545±11.094, Episode_length: 281.900±16.784\n", ++ "Rollout 328/9766, Reward: 261.606±20.525, Episode_length: 255.500±13.858\n", ++ "Rollout 329/9766, Reward: 263.653±20.438, Episode_length: 281.100±22.309\n", ++ "Rollout 330/9766, Reward: 259.971±16.534, Episode_length: 261.300±12.861\n", ++ "Rollout 331/9766, Reward: 274.227±13.395, Episode_length: 253.100±19.450\n", ++ "Rollout 332/9766, Reward: 271.484±23.062, Episode_length: 245.900±15.896\n", ++ "Rollout 333/9766, Reward: 275.736±16.713, Episode_length: 235.700±15.950\n", ++ "Rollout 334/9766, Reward: 195.654±244.576, Episode_length: 204.900±46.597\n", ++ "Rollout 335/9766, Reward: 280.296±10.965, Episode_length: 213.500±22.664\n", ++ "Rollout 336/9766, Reward: 270.642±16.896, Episode_length: 210.600±15.951\n", ++ "Rollout 337/9766, Reward: 279.389±17.322, Episode_length: 229.500±14.921\n", ++ "Rollout 338/9766, Reward: 285.805±12.745, Episode_length: 240.200±13.934\n", ++ "Rollout 339/9766, Reward: 283.046±19.023, Episode_length: 227.200±16.851\n", ++ "Rollout 340/9766, Reward: 285.238±18.688, Episode_length: 234.500±13.596\n", ++ "Rollout 341/9766, Reward: 261.812±34.014, Episode_length: 293.300±155.072\n", ++ "Rollout 342/9766, Reward: 280.803±12.348, Episode_length: 242.300±23.311\n", ++ "Rollout 343/9766, Reward: 183.330±251.113, Episode_length: 237.000±107.282\n", ++ "Rollout 344/9766, Reward: 281.592±20.743, Episode_length: 228.700±17.378\n", ++ "Rollout 345/9766, Reward: 282.871±16.906, Episode_length: 222.100±18.157\n", ++ "Rollout 346/9766, Reward: 275.689±17.942, Episode_length: 217.700±17.176\n", ++ "Rollout 347/9766, Reward: 272.288±16.524, Episode_length: 231.900±19.872\n", ++ "Rollout 348/9766, Reward: 274.811±9.785, Episode_length: 217.400±23.419\n", ++ "Rollout 349/9766, Reward: -222.309±506.101, Episode_length: 231.200±200.922\n", ++ "Rollout 350/9766, Reward: 34.963±397.136, Episode_length: 355.100±326.298\n", ++ "Rollout 351/9766, Reward: 165.731±254.725, Episode_length: 339.100±250.882\n", ++ "Rollout 352/9766, Reward: 245.134±54.075, Episode_length: 386.200±307.707\n", ++ "Rollout 353/9766, Reward: 90.287±277.635, Episode_length: 232.500±133.209\n", ++ "Rollout 354/9766, Reward: 254.105±18.998, Episode_length: 263.500±85.017\n", ++ "Rollout 355/9766, Reward: 31.455±234.354, Episode_length: 523.100±319.825\n", ++ "Rollout 356/9766, Reward: 259.562±17.830, Episode_length: 245.700±31.171\n", ++ "Rollout 357/9766, Reward: 259.914±37.045, Episode_length: 361.300±247.049\n", ++ "Rollout 358/9766, Reward: 262.999±34.294, Episode_length: 313.100±229.484\n", ++ "Rollout 359/9766, Reward: 198.105±52.208, Episode_length: 772.500±347.514\n", ++ "Rollout 360/9766, Reward: 270.850±16.755, Episode_length: 233.900±17.196\n", ++ "Rollout 361/9766, Reward: 272.751±10.983, Episode_length: 230.100±20.092\n", ++ "Rollout 362/9766, Reward: 283.054±21.944, Episode_length: 238.300±27.074\n", ++ "Rollout 363/9766, Reward: 280.356±22.502, Episode_length: 233.800±21.591\n", ++ "Rollout 364/9766, Reward: 271.891±21.387, Episode_length: 234.600±31.702\n", ++ "Rollout 365/9766, Reward: 281.371±18.139, Episode_length: 236.800±25.278\n", ++ "Rollout 366/9766, Reward: 267.580±15.764, Episode_length: 265.200±25.849\n", ++ "Rollout 367/9766, Reward: 263.525±19.697, Episode_length: 276.400±27.986\n", ++ "Rollout 368/9766, Reward: 264.966±18.290, Episode_length: 258.500±21.704\n", ++ "Rollout 369/9766, Reward: 276.187±14.336, Episode_length: 266.800±25.635\n", ++ "Rollout 370/9766, Reward: 265.293±21.944, Episode_length: 264.600±20.704\n", ++ "Rollout 371/9766, Reward: 268.966±18.235, Episode_length: 306.200±139.363\n", ++ "Rollout 372/9766, Reward: 258.482±19.725, Episode_length: 251.300±17.539\n", ++ "Rollout 373/9766, Reward: 275.311±17.188, Episode_length: 255.200±26.739\n", ++ "Rollout 374/9766, Reward: 269.393±16.291, Episode_length: 234.100±14.983\n", ++ "Rollout 375/9766, Reward: 278.450±17.683, Episode_length: 234.100±22.278\n", ++ "Rollout 376/9766, Reward: 272.829±15.354, Episode_length: 223.700±21.147\n", ++ "Rollout 377/9766, Reward: 242.750±42.755, Episode_length: 378.600±310.845\n", ++ "Rollout 378/9766, Reward: 262.167±35.434, Episode_length: 240.400±71.371\n", ++ "Rollout 379/9766, Reward: 257.664±47.100, Episode_length: 290.700±237.561\n", ++ "Rollout 380/9766, Reward: 278.739±16.315, Episode_length: 215.300±21.457\n", ++ "Rollout 381/9766, Reward: 279.335±18.181, Episode_length: 221.200±19.379\n", ++ "Rollout 382/9766, Reward: 279.159±23.495, Episode_length: 196.100±21.445\n", ++ "Rollout 383/9766, Reward: 258.947±12.911, Episode_length: 207.400±24.913\n", ++ "Rollout 384/9766, Reward: 283.849±19.265, Episode_length: 211.300±19.885\n", ++ "Rollout 385/9766, Reward: 282.227±12.521, Episode_length: 203.500±16.354\n", ++ "Rollout 386/9766, Reward: 277.138±24.143, Episode_length: 279.300±186.203\n", ++ "Rollout 387/9766, Reward: 270.715±36.707, Episode_length: 298.800±235.929\n", ++ "Rollout 388/9766, Reward: 269.951±19.706, Episode_length: 209.900±26.319\n", ++ "Rollout 389/9766, Reward: 270.718±35.020, Episode_length: 300.200±234.699\n", ++ "Rollout 390/9766, Reward: 277.672±21.603, Episode_length: 284.400±151.489\n", ++ "Rollout 391/9766, Reward: 262.314±16.288, Episode_length: 220.400±13.230\n", ++ "Rollout 392/9766, Reward: 278.788±16.795, Episode_length: 226.400±24.602\n", ++ "Rollout 393/9766, Reward: 237.321±64.556, Episode_length: 393.000±304.129\n", ++ "Rollout 394/9766, Reward: 275.693±15.708, Episode_length: 225.900±23.050\n", ++ "Rollout 395/9766, Reward: 266.185±24.222, Episode_length: 238.900±26.440\n", ++ "Rollout 396/9766, Reward: 244.938±45.933, Episode_length: 390.100±305.490\n", ++ "Rollout 397/9766, Reward: 188.409±61.994, Episode_length: 712.400±353.313\n", ++ "Rollout 398/9766, Reward: 177.307±61.476, Episode_length: 792.200±317.995\n", ++ "Rollout 399/9766, Reward: 214.158±46.475, Episode_length: 618.300±381.753\n", ++ "Rollout 400/9766, Reward: 268.473±14.791, Episode_length: 239.700±18.243\n", ++ "Rollout 401/9766, Reward: 264.964±43.526, Episode_length: 323.200±226.444\n", ++ "Rollout 402/9766, Reward: 279.781±12.231, Episode_length: 232.700±20.664\n", ++ "Rollout 403/9766, Reward: 226.534±59.989, Episode_length: 547.300±371.478\n", ++ "Rollout 404/9766, Reward: 207.537±200.469, Episode_length: 238.600±63.072\n", ++ "Rollout 405/9766, Reward: 268.809±17.057, Episode_length: 329.300±225.337\n", ++ "Rollout 406/9766, Reward: 262.274±14.541, Episode_length: 236.600±24.715\n", ++ "Rollout 407/9766, Reward: 263.679±39.311, Episode_length: 304.300±232.929\n", ++ "Rollout 408/9766, Reward: 285.544±21.607, Episode_length: 316.000±226.947\n", ++ "Rollout 409/9766, Reward: 261.596±28.124, Episode_length: 338.400±235.415\n", ++ "Rollout 410/9766, Reward: 262.218±16.242, Episode_length: 296.400±111.825\n", ++ "Rollout 411/9766, Reward: 270.249±17.821, Episode_length: 238.400±72.465\n", ++ "Rollout 412/9766, Reward: 252.133±45.034, Episode_length: 373.600±313.895\n", ++ "Rollout 413/9766, Reward: 278.936±14.674, Episode_length: 229.800±32.787\n", ++ "Rollout 414/9766, Reward: 278.133±17.841, Episode_length: 225.700±16.267\n", ++ "Rollout 415/9766, Reward: 272.765±14.175, Episode_length: 214.600±20.996\n", ++ "Rollout 416/9766, Reward: 275.792±19.510, Episode_length: 227.400±19.043\n", ++ "Rollout 417/9766, Reward: 280.881±19.861, Episode_length: 237.500±39.636\n", ++ "Rollout 418/9766, Reward: 245.212±18.778, Episode_length: 550.000±112.263\n", ++ "Rollout 419/9766, Reward: 246.924±15.551, Episode_length: 456.400±54.425\n", ++ "Rollout 420/9766, Reward: 273.511±34.013, Episode_length: 323.700±226.998\n", ++ "Rollout 421/9766, Reward: 267.416±15.046, Episode_length: 225.400±26.733\n", ++ "Rollout 422/9766, Reward: 279.601±16.054, Episode_length: 215.700±29.004\n", ++ "Rollout 423/9766, Reward: 251.646±34.412, Episode_length: 291.100±237.010\n", ++ "Rollout 424/9766, Reward: 253.721±30.123, Episode_length: 478.400±277.632\n", ++ "Rollout 425/9766, Reward: 280.123±16.137, Episode_length: 230.700±28.089\n", ++ "Rollout 426/9766, Reward: 279.233±12.689, Episode_length: 209.000±14.880\n", ++ "Rollout 427/9766, Reward: 272.937±17.341, Episode_length: 201.100±24.044\n", ++ "Rollout 428/9766, Reward: 276.972±13.424, Episode_length: 196.800±19.323\n", ++ "Rollout 429/9766, Reward: 270.492±13.888, Episode_length: 192.100±13.435\n", ++ "Rollout 430/9766, Reward: 272.168±20.392, Episode_length: 189.500±19.765\n", ++ "Rollout 431/9766, Reward: 278.209±16.279, Episode_length: 186.800±14.979\n", ++ "Rollout 432/9766, Reward: 273.553±14.776, Episode_length: 191.000±12.033\n", ++ "Rollout 433/9766, Reward: 277.266±18.001, Episode_length: 195.000±23.178\n", ++ "Rollout 434/9766, Reward: 280.478±9.864, Episode_length: 200.700±39.396\n", ++ "Rollout 435/9766, Reward: 275.544±12.811, Episode_length: 209.000±17.810\n", ++ "Rollout 436/9766, Reward: 265.918±46.007, Episode_length: 284.200±240.163\n", ++ "Rollout 437/9766, Reward: 196.403±157.111, Episode_length: 245.200±60.503\n", ++ "Rollout 438/9766, Reward: 253.964±45.614, Episode_length: 295.100±236.904\n", ++ "Rollout 439/9766, Reward: 257.654±36.014, Episode_length: 280.500±118.923\n", ++ "Rollout 440/9766, Reward: 241.074±30.539, Episode_length: 354.700±218.490\n", ++ "Rollout 441/9766, Reward: 271.518±17.709, Episode_length: 218.100±20.945\n", ++ "Rollout 442/9766, Reward: 135.622±213.000, Episode_length: 362.500±236.543\n", ++ "Rollout 443/9766, Reward: 288.694±14.927, Episode_length: 207.500±19.551\n", ++ "Rollout 444/9766, Reward: 257.626±44.415, Episode_length: 312.800±232.374\n", ++ "Rollout 445/9766, Reward: 285.779±21.582, Episode_length: 228.400±25.617\n", ++ "Rollout 446/9766, Reward: 273.357±23.139, Episode_length: 230.400±26.326\n", ++ "Rollout 447/9766, Reward: 272.076±15.946, Episode_length: 227.700±17.883\n", ++ "Rollout 448/9766, Reward: 285.281±10.870, Episode_length: 231.000±16.230\n", ++ "Rollout 449/9766, Reward: 276.285±16.550, Episode_length: 226.800±14.183\n", ++ "Rollout 450/9766, Reward: 235.593±56.623, Episode_length: 386.500±307.036\n", ++ "Rollout 451/9766, Reward: 276.653±20.447, Episode_length: 239.000±30.584\n", ++ "Rollout 452/9766, Reward: 265.145±25.487, Episode_length: 310.000±140.952\n", ++ "Rollout 453/9766, Reward: 241.107±57.056, Episode_length: 383.600±308.490\n", ++ "Rollout 454/9766, Reward: 248.721±51.039, Episode_length: 318.200±227.997\n", ++ "Rollout 455/9766, Reward: 257.152±32.683, Episode_length: 277.500±77.961\n", ++ "Rollout 456/9766, Reward: 268.648±23.830, Episode_length: 262.900±19.882\n", ++ "Rollout 457/9766, Reward: 190.247±203.608, Episode_length: 246.700±69.188\n", ++ "Rollout 458/9766, Reward: 145.808±139.422, Episode_length: 564.200±356.725\n", ++ "Rollout 459/9766, Reward: 254.171±18.754, Episode_length: 238.300±20.650\n", ++ "Rollout 460/9766, Reward: 268.459±18.779, Episode_length: 226.300±18.810\n", ++ "Rollout 461/9766, Reward: 273.056±19.799, Episode_length: 225.300±23.622\n", ++ "Rollout 462/9766, Reward: 275.409±20.320, Episode_length: 215.300±20.838\n", ++ "Rollout 463/9766, Reward: 269.628±21.400, Episode_length: 211.000±15.317\n", ++ "Rollout 464/9766, Reward: 283.854±14.368, Episode_length: 226.500±25.492\n", ++ "Rollout 465/9766, Reward: 278.838±15.897, Episode_length: 203.100±22.674\n", ++ "Rollout 466/9766, Reward: 279.702±17.468, Episode_length: 200.400±19.148\n", ++ "Rollout 467/9766, Reward: 273.189±18.434, Episode_length: 211.300±20.298\n", ++ "Rollout 468/9766, Reward: 277.038±16.460, Episode_length: 201.300±26.706\n", ++ "Rollout 469/9766, Reward: 269.322±9.498, Episode_length: 200.000±20.789\n", ++ "Rollout 470/9766, Reward: 272.593±15.172, Episode_length: 271.100±165.692\n", ++ "Rollout 471/9766, Reward: 261.342±35.813, Episode_length: 293.200±240.105\n", ++ "Rollout 472/9766, Reward: 268.567±16.542, Episode_length: 204.600±22.571\n", ++ "Rollout 473/9766, Reward: 264.395±35.803, Episode_length: 284.700±240.065\n", ++ "Rollout 474/9766, Reward: 287.911±10.724, Episode_length: 216.900±23.914\n", ++ "Rollout 475/9766, Reward: 276.165±18.370, Episode_length: 241.500±23.032\n", ++ "Rollout 476/9766, Reward: 284.182±12.077, Episode_length: 219.500±24.221\n", ++ "Rollout 477/9766, Reward: 277.592±13.504, Episode_length: 246.500±22.272\n", ++ "Rollout 478/9766, Reward: 266.007±37.433, Episode_length: 444.200±311.576\n", ++ "Rollout 479/9766, Reward: 261.202±30.586, Episode_length: 316.700±228.539\n", ++ "Rollout 480/9766, Reward: 265.597±21.434, Episode_length: 278.000±107.186\n", ++ "Rollout 481/9766, Reward: 279.668±21.924, Episode_length: 239.500±20.076\n", ++ "Rollout 482/9766, Reward: 271.198±14.827, Episode_length: 247.300±26.755\n", ++ "Rollout 483/9766, Reward: 263.799±16.398, Episode_length: 265.300±28.903\n", ++ "Rollout 484/9766, Reward: 247.205±19.560, Episode_length: 360.900±69.868\n", ++ "Rollout 485/9766, Reward: 267.288±21.502, Episode_length: 271.100±30.940\n", ++ "Rollout 486/9766, Reward: 268.320±20.050, Episode_length: 277.600±47.411\n", ++ "Rollout 487/9766, Reward: 273.555±17.824, Episode_length: 315.100±221.141\n", ++ "Rollout 488/9766, Reward: 280.273±13.015, Episode_length: 245.700±23.854\n", ++ "Rollout 489/9766, Reward: 273.370±11.132, Episode_length: 255.500±26.387\n", ++ "Rollout 490/9766, Reward: 275.384±11.907, Episode_length: 267.600±18.527\n", ++ "Rollout 491/9766, Reward: 269.934±14.593, Episode_length: 238.100±20.603\n", ++ "Rollout 492/9766, Reward: -2.014±269.612, Episode_length: 175.100±94.768\n", ++ "Rollout 493/9766, Reward: 155.251±323.274, Episode_length: 305.500±65.191\n", ++ "Rollout 494/9766, Reward: 239.639±46.819, Episode_length: 498.300±325.206\n", ++ "Rollout 495/9766, Reward: 255.727±46.496, Episode_length: 377.700±209.287\n", ++ "Rollout 496/9766, Reward: 253.349±37.947, Episode_length: 368.800±210.869\n", ++ "Rollout 497/9766, Reward: 246.675±42.251, Episode_length: 362.000±214.260\n", ++ "Rollout 498/9766, Reward: 258.423±13.905, Episode_length: 291.800±24.408\n", ++ "Rollout 499/9766, Reward: 260.162±9.003, Episode_length: 307.600±21.951\n", ++ "Rollout 500/9766, Reward: 250.530±18.496, Episode_length: 305.300±26.807\n", ++ "Rollout 501/9766, Reward: 127.533±19.902, Episode_length: 1000.000±0.000\n", ++ "Rollout 502/9766, Reward: -93.957±377.487, Episode_length: 561.300±381.334\n", ++ "Rollout 503/9766, Reward: 19.413±239.896, Episode_length: 752.600±385.434\n", ++ "Rollout 504/9766, Reward: 71.158±270.530, Episode_length: 828.900±304.048\n", ++ "Rollout 505/9766, Reward: 129.334±314.197, Episode_length: 500.300±308.065\n", ++ "Rollout 506/9766, Reward: 264.653±10.248, Episode_length: 326.500±26.519\n", ++ "Rollout 507/9766, Reward: -140.372±620.708, Episode_length: 224.800±59.442\n", ++ "Rollout 508/9766, Reward: 272.070±16.523, Episode_length: 280.900±24.970\n", ++ "Rollout 509/9766, Reward: -24.656±610.831, Episode_length: 248.700±55.911\n", ++ "Rollout 510/9766, Reward: 263.241±18.492, Episode_length: 272.500±32.967\n", ++ "Rollout 511/9766, Reward: 266.988±19.937, Episode_length: 259.000±29.455\n", ++ "Rollout 512/9766, Reward: 62.084±509.550, Episode_length: 404.200±300.570\n", ++ "Rollout 513/9766, Reward: 266.220±14.640, Episode_length: 269.100±35.750\n", ++ "Rollout 514/9766, Reward: 271.159±16.327, Episode_length: 263.500±37.206\n", ++ "Rollout 515/9766, Reward: 275.012±13.887, Episode_length: 267.200±34.196\n", ++ "Rollout 516/9766, Reward: -39.574±913.886, Episode_length: 249.700±24.828\n", ++ "Rollout 517/9766, Reward: -358.886±1231.045, Episode_length: 256.800±44.850\n", ++ "Rollout 518/9766, Reward: -24.583±635.404, Episode_length: 350.600±224.042\n", ++ "Rollout 519/9766, Reward: 264.334±25.965, Episode_length: 253.900±25.010\n", ++ "Rollout 520/9766, Reward: 42.518±664.665, Episode_length: 257.200±45.790\n", ++ "Rollout 521/9766, Reward: 261.097±17.491, Episode_length: 232.900±19.419\n", ++ "Rollout 522/9766, Reward: 258.482±11.307, Episode_length: 238.200±21.605\n", ++ "Rollout 523/9766, Reward: 268.418±11.998, Episode_length: 248.800±20.029\n", ++ "Rollout 524/9766, Reward: 275.939±16.832, Episode_length: 265.000±39.322\n", ++ "Rollout 525/9766, Reward: 270.472±19.209, Episode_length: 235.200±22.022\n", ++ "Rollout 526/9766, Reward: 271.429±8.843, Episode_length: 236.400±39.266\n", ++ "Rollout 527/9766, Reward: 274.122±9.634, Episode_length: 238.700±37.143\n", ++ "Rollout 528/9766, Reward: 245.709±46.783, Episode_length: 392.300±306.661\n", ++ "Rollout 529/9766, Reward: 240.518±51.303, Episode_length: 396.000±304.781\n", ++ "Rollout 530/9766, Reward: 245.050±41.641, Episode_length: 308.600±234.407\n", ++ "Rollout 531/9766, Reward: 272.215±15.375, Episode_length: 243.400±30.965\n", ++ "Rollout 532/9766, Reward: 179.038±292.463, Episode_length: 220.200±23.426\n", ++ "Rollout 533/9766, Reward: 279.749±15.345, Episode_length: 244.300±46.834\n", ++ "Rollout 534/9766, Reward: 276.075±13.808, Episode_length: 254.700±40.905\n", ++ "Rollout 535/9766, Reward: 278.476±18.333, Episode_length: 249.500±16.286\n", ++ "Rollout 536/9766, Reward: 12.629±764.467, Episode_length: 254.500±39.187\n", ++ "Rollout 537/9766, Reward: 275.148±12.907, Episode_length: 239.500±31.718\n", ++ "Rollout 538/9766, Reward: 271.406±10.766, Episode_length: 231.300±25.366\n", ++ "Rollout 539/9766, Reward: 269.290±20.283, Episode_length: 236.800±33.343\n", ++ "Rollout 540/9766, Reward: 267.839±23.750, Episode_length: 332.400±214.153\n", ++ "Rollout 541/9766, Reward: 263.340±16.716, Episode_length: 266.700±63.690\n", ++ "Rollout 542/9766, Reward: 256.236±15.669, Episode_length: 257.200±23.710\n", ++ "Rollout 543/9766, Reward: 266.051±15.283, Episode_length: 263.900±26.212\n", ++ "Rollout 544/9766, Reward: 250.636±38.657, Episode_length: 338.300±223.238\n", ++ "Rollout 545/9766, Reward: 261.203±19.547, Episode_length: 254.800±24.347\n", ++ "Rollout 546/9766, Reward: 265.658±21.601, Episode_length: 256.500±24.622\n", ++ "Rollout 547/9766, Reward: 248.303±36.134, Episode_length: 408.600±293.627\n", ++ "Rollout 548/9766, Reward: 253.041±38.752, Episode_length: 319.000±230.319\n", ++ "Rollout 549/9766, Reward: 266.196±15.164, Episode_length: 248.900±34.204\n", ++ "Rollout 550/9766, Reward: 259.283±43.818, Episode_length: 386.700±286.113\n", ++ "Rollout 551/9766, Reward: 243.766±48.124, Episode_length: 410.700±297.551\n", ++ "Rollout 552/9766, Reward: 282.137±13.667, Episode_length: 246.100±35.243\n", ++ "Rollout 553/9766, Reward: 281.247±11.304, Episode_length: 261.000±33.864\n", ++ "Rollout 554/9766, Reward: 262.635±18.948, Episode_length: 248.100±33.222\n", ++ "Rollout 555/9766, Reward: 270.275±26.684, Episode_length: 251.800±29.610\n", ++ "Rollout 556/9766, Reward: 264.466±42.022, Episode_length: 324.400±228.449\n", ++ "Rollout 557/9766, Reward: 231.804±67.355, Episode_length: 476.000±344.696\n", ++ "Rollout 558/9766, Reward: 257.049±33.833, Episode_length: 320.400±229.641\n", ++ "Rollout 559/9766, Reward: 268.050±16.431, Episode_length: 296.500±106.704\n", ++ "Rollout 560/9766, Reward: 239.452±63.318, Episode_length: 394.100±304.104\n", ++ "Rollout 561/9766, Reward: 269.201±16.274, Episode_length: 237.100±29.491\n", ++ "Rollout 562/9766, Reward: 278.688±15.923, Episode_length: 299.200±171.538\n", ++ "Rollout 563/9766, Reward: 264.532±18.285, Episode_length: 219.300±15.704\n", ++ "Rollout 564/9766, Reward: 255.715±39.238, Episode_length: 312.400±231.623\n", ++ "Rollout 565/9766, Reward: 260.539±39.868, Episode_length: 305.800±232.230\n", ++ "Rollout 566/9766, Reward: 0.321±393.154, Episode_length: 303.700±238.036\n", ++ "Rollout 567/9766, Reward: 253.727±36.314, Episode_length: 307.900±231.580\n", ++ "Rollout 568/9766, Reward: 268.383±14.348, Episode_length: 219.100±27.479\n", ++ "Rollout 569/9766, Reward: 209.355±186.294, Episode_length: 207.900±51.789\n", ++ "Rollout 570/9766, Reward: 131.469±275.555, Episode_length: 186.100±53.304\n", ++ "Rollout 571/9766, Reward: -473.318±871.785, Episode_length: 167.900±74.715\n", ++ "Rollout 572/9766, Reward: -6.266±421.020, Episode_length: 174.900±54.544\n", ++ "Rollout 573/9766, Reward: -604.052±1453.896, Episode_length: 162.700±67.862\n", ++ "Rollout 574/9766, Reward: -907.663±1794.624, Episode_length: 192.300±80.764\n", ++ "Rollout 575/9766, Reward: 13.489±372.641, Episode_length: 256.800±255.447\n", ++ "Rollout 576/9766, Reward: -4.854±387.437, Episode_length: 277.300±249.317\n", ++ "Rollout 577/9766, Reward: -115.268±483.086, Episode_length: 208.200±105.904\n", ++ "Rollout 578/9766, Reward: -369.650±1075.999, Episode_length: 318.700±237.123\n", ++ "Rollout 579/9766, Reward: -79.759±519.180, Episode_length: 265.600±252.015\n", ++ "Rollout 580/9766, Reward: -266.339±1147.423, Episode_length: 211.600±89.644\n", ++ "Rollout 581/9766, Reward: 259.808±31.029, Episode_length: 262.100±65.902\n", ++ "Rollout 582/9766, Reward: 245.058±56.493, Episode_length: 364.500±220.073\n", ++ "Rollout 583/9766, Reward: 248.091±40.911, Episode_length: 305.000±232.417\n", ++ "Rollout 584/9766, Reward: 217.238±50.526, Episode_length: 533.000±382.050\n", ++ "Rollout 585/9766, Reward: 272.134±10.669, Episode_length: 208.100±38.342\n", ++ "Rollout 586/9766, Reward: 268.568±21.617, Episode_length: 204.200±18.010\n", ++ "Rollout 587/9766, Reward: 233.383±49.945, Episode_length: 408.000±303.547\n", ++ "Rollout 588/9766, Reward: 276.076±20.694, Episode_length: 224.700±27.677\n", ++ "Rollout 589/9766, Reward: 252.957±34.618, Episode_length: 294.400±236.961\n", ++ "Rollout 590/9766, Reward: 246.478±15.272, Episode_length: 227.800±47.851\n", ++ "Rollout 591/9766, Reward: 263.587±18.355, Episode_length: 265.800±171.083\n", ++ "Rollout 592/9766, Reward: 250.916±31.329, Episode_length: 442.500±310.906\n", ++ "Rollout 593/9766, Reward: 214.411±74.176, Episode_length: 282.600±239.908\n", ++ "Rollout 594/9766, Reward: 203.312±59.692, Episode_length: 620.700±380.186\n", ++ "Rollout 595/9766, Reward: 190.938±86.570, Episode_length: 292.800±236.688\n", ++ "Rollout 596/9766, Reward: 211.752±55.119, Episode_length: 470.500±348.139\n", ++ "Rollout 597/9766, Reward: 203.867±89.685, Episode_length: 313.600±230.558\n", ++ "Rollout 598/9766, Reward: 223.724±67.058, Episode_length: 295.200±163.027\n", ++ "Rollout 599/9766, Reward: 239.790±36.173, Episode_length: 323.400±230.307\n", ++ "Rollout 600/9766, Reward: 243.366±29.473, Episode_length: 314.000±228.824\n", ++ "Rollout 601/9766, Reward: 206.234±54.161, Episode_length: 578.800±352.275\n", ++ "Rollout 602/9766, Reward: 190.306±73.979, Episode_length: 539.700±298.540\n", ++ "Rollout 603/9766, Reward: 32.853±354.213, Episode_length: 403.800±265.031\n", ++ "Rollout 604/9766, Reward: 209.961±118.301, Episode_length: 271.500±84.684\n", ++ "Rollout 605/9766, Reward: 158.971±106.257, Episode_length: 812.000±328.681\n", ++ "Rollout 606/9766, Reward: 192.894±48.556, Episode_length: 783.400±331.408\n", ++ "Rollout 607/9766, Reward: 58.463±471.681, Episode_length: 254.300±70.376\n", ++ "Rollout 608/9766, Reward: 228.443±48.425, Episode_length: 480.900±340.451\n", ++ "Rollout 609/9766, Reward: 259.053±31.425, Episode_length: 366.500±214.907\n", ++ "Rollout 610/9766, Reward: 262.991±14.355, Episode_length: 298.700±20.717\n", ++ "Rollout 611/9766, Reward: 232.838±42.364, Episode_length: 426.800±227.452\n", ++ "Rollout 612/9766, Reward: 264.586±21.112, Episode_length: 303.500±37.543\n", ++ "Rollout 613/9766, Reward: 262.664±18.172, Episode_length: 299.300±32.585\n", ++ "Rollout 614/9766, Reward: 265.105±18.883, Episode_length: 285.400±74.930\n", ++ "Rollout 615/9766, Reward: 274.381±13.785, Episode_length: 258.300±26.196\n", ++ "Rollout 616/9766, Reward: 269.464±21.396, Episode_length: 258.100±23.607\n", ++ "Rollout 617/9766, Reward: 273.248±13.356, Episode_length: 246.000±30.341\n", ++ "Rollout 618/9766, Reward: 266.383±13.716, Episode_length: 235.900±12.637\n", ++ "Rollout 619/9766, Reward: 275.050±23.140, Episode_length: 244.800±29.849\n", ++ "Rollout 620/9766, Reward: 279.225±24.903, Episode_length: 243.000±23.039\n", ++ "Rollout 621/9766, Reward: 267.324±18.639, Episode_length: 230.600±21.606\n", ++ "Rollout 622/9766, Reward: 269.573±18.123, Episode_length: 233.400±30.549\n", ++ "Rollout 623/9766, Reward: 287.149±14.805, Episode_length: 244.400±19.845\n", ++ "Rollout 624/9766, Reward: 269.985±34.294, Episode_length: 326.600±226.486\n", ++ "Rollout 625/9766, Reward: 281.255±12.986, Episode_length: 247.300±28.464\n", ++ "Rollout 626/9766, Reward: 269.032±18.767, Episode_length: 236.800±26.746\n", ++ "Rollout 627/9766, Reward: 281.973±12.848, Episode_length: 237.100±25.098\n", ++ "Rollout 628/9766, Reward: 277.580±13.804, Episode_length: 249.000±26.926\n", ++ "Rollout 629/9766, Reward: 286.317±15.015, Episode_length: 257.500±26.755\n", ++ "Rollout 630/9766, Reward: 278.520±17.144, Episode_length: 239.100±22.945\n", ++ "Rollout 631/9766, Reward: 262.996±22.629, Episode_length: 234.000±17.939\n", ++ "Rollout 632/9766, Reward: 278.334±17.492, Episode_length: 231.100±24.255\n", ++ "Rollout 633/9766, Reward: 262.233±26.866, Episode_length: 293.100±235.880\n", ++ "Rollout 634/9766, Reward: 276.518±18.848, Episode_length: 223.500±20.026\n", ++ "Rollout 635/9766, Reward: 272.877±17.781, Episode_length: 221.800±19.798\n", ++ "Rollout 636/9766, Reward: 273.706±17.249, Episode_length: 217.700±25.279\n", ++ "Rollout 637/9766, Reward: 269.011±24.039, Episode_length: 209.300±16.000\n", ++ "Rollout 638/9766, Reward: 285.188±20.724, Episode_length: 215.500±19.684\n", ++ "Rollout 639/9766, Reward: 287.454±19.352, Episode_length: 231.700±22.978\n", ++ "Rollout 640/9766, Reward: 260.268±45.590, Episode_length: 299.800±234.027\n", ++ "Rollout 641/9766, Reward: 283.309±18.229, Episode_length: 225.800±18.176\n", ++ "Rollout 642/9766, Reward: 276.356±23.118, Episode_length: 202.500±23.235\n", ++ "Rollout 643/9766, Reward: 258.860±61.439, Episode_length: 373.200±313.884\n", ++ "Rollout 644/9766, Reward: 251.282±42.493, Episode_length: 284.100±239.107\n", ++ "Rollout 645/9766, Reward: 275.517±19.683, Episode_length: 224.300±28.566\n", ++ "Rollout 646/9766, Reward: 246.307±39.304, Episode_length: 274.200±242.763\n", ++ "Rollout 647/9766, Reward: 246.559±45.133, Episode_length: 283.800±239.618\n", ++ "Rollout 648/9766, Reward: 268.938±27.024, Episode_length: 216.700±22.285\n", ++ "Rollout 649/9766, Reward: 223.030±87.212, Episode_length: 388.200±307.785\n", ++ "Rollout 650/9766, Reward: 252.070±40.486, Episode_length: 295.000±236.775\n", ++ "Rollout 651/9766, Reward: 257.188±36.579, Episode_length: 316.900±229.703\n", ++ "Rollout 652/9766, Reward: 217.997±58.869, Episode_length: 445.600±363.498\n", ++ "Rollout 653/9766, Reward: 248.726±41.335, Episode_length: 291.200±237.054\n", ++ "Rollout 654/9766, Reward: 269.930±24.404, Episode_length: 220.300±25.160\n", ++ "Rollout 655/9766, Reward: 216.430±75.931, Episode_length: 582.300±373.750\n", ++ "Rollout 656/9766, Reward: 231.053±44.370, Episode_length: 339.200±242.470\n", ++ "Rollout 657/9766, Reward: 275.420±10.702, Episode_length: 224.100±36.369\n", ++ "Rollout 658/9766, Reward: 227.952±65.159, Episode_length: 438.100±320.116\n", ++ "Rollout 659/9766, Reward: 253.046±32.006, Episode_length: 272.800±242.744\n", ++ "Rollout 660/9766, Reward: 243.998±63.589, Episode_length: 350.400±277.742\n", ++ "Rollout 661/9766, Reward: 255.980±26.124, Episode_length: 383.600±179.513\n", ++ "Rollout 662/9766, Reward: 239.323±41.825, Episode_length: 323.300±234.451\n", ++ "Rollout 663/9766, Reward: 243.654±46.829, Episode_length: 514.400±342.004\n", ++ "Rollout 664/9766, Reward: 271.486±19.961, Episode_length: 212.800±34.292\n", ++ "Rollout 665/9766, Reward: 226.820±85.497, Episode_length: 327.800±257.459\n", ++ "Rollout 666/9766, Reward: 272.377±16.858, Episode_length: 205.000±19.586\n", ++ "Rollout 667/9766, Reward: 281.750±11.116, Episode_length: 209.300±24.067\n", ++ "Rollout 668/9766, Reward: -59.289±403.616, Episode_length: 142.200±48.176\n", ++ "Rollout 669/9766, Reward: 8.864±344.505, Episode_length: 328.500±303.543\n", ++ "Rollout 670/9766, Reward: 255.128±57.351, Episode_length: 287.500±238.224\n", ++ "Rollout 671/9766, Reward: 227.744±154.952, Episode_length: 196.400±37.612\n", ++ "Rollout 672/9766, Reward: 266.334±41.508, Episode_length: 283.000±239.467\n", ++ "Rollout 673/9766, Reward: 281.483±19.839, Episode_length: 214.300±23.757\n", ++ "Rollout 674/9766, Reward: 287.498±18.956, Episode_length: 207.000±26.115\n", ++ "Rollout 675/9766, Reward: 278.899±17.174, Episode_length: 207.300±18.709\n", ++ "Rollout 676/9766, Reward: 272.755±17.310, Episode_length: 217.500±9.657\n", ++ "Rollout 677/9766, Reward: 267.638±29.657, Episode_length: 291.900±236.449\n", ++ "Rollout 678/9766, Reward: 270.825±22.361, Episode_length: 221.600±19.184\n", ++ "Rollout 679/9766, Reward: 158.440±37.194, Episode_length: 976.000±72.000\n", ++ "Rollout 680/9766, Reward: 180.804±167.932, Episode_length: 497.800±219.621\n", ++ "Rollout 681/9766, Reward: 198.014±55.674, Episode_length: 629.600±304.005\n", ++ "Rollout 682/9766, Reward: 206.012±56.466, Episode_length: 620.900±339.323\n", ++ "Rollout 683/9766, Reward: 219.518±38.773, Episode_length: 638.200±335.973\n", ++ "Rollout 684/9766, Reward: 215.367±39.975, Episode_length: 512.100±240.788\n", ++ "Rollout 685/9766, Reward: 210.401±37.055, Episode_length: 469.300±256.983\n", ++ "Rollout 686/9766, Reward: 214.797±52.598, Episode_length: 514.300±201.211\n", ++ "Rollout 687/9766, Reward: 170.400±58.466, Episode_length: 660.700±300.078\n", ++ "Rollout 688/9766, Reward: -185.980±805.084, Episode_length: 417.600±295.815\n", ++ "Rollout 689/9766, Reward: 39.114±576.696, Episode_length: 467.700±278.693\n", ++ "Rollout 690/9766, Reward: 248.216±40.095, Episode_length: 353.300±227.943\n", ++ "Rollout 691/9766, Reward: 248.208±35.390, Episode_length: 333.200±223.633\n", ++ "Rollout 692/9766, Reward: 256.872±30.513, Episode_length: 309.300±231.311\n", ++ "Rollout 693/9766, Reward: 209.530±60.837, Episode_length: 693.400±363.307\n", ++ "Rollout 694/9766, Reward: 268.844±22.992, Episode_length: 282.000±137.561\n", ++ "Rollout 695/9766, Reward: 267.911±16.459, Episode_length: 244.000±23.879\n", ++ "Rollout 696/9766, Reward: 269.960±19.096, Episode_length: 231.500±16.711\n", ++ "Rollout 697/9766, Reward: 259.005±41.295, Episode_length: 302.800±234.065\n", ++ "Rollout 698/9766, Reward: 268.041±20.856, Episode_length: 235.600±30.523\n", ++ "Rollout 699/9766, Reward: 210.632±73.825, Episode_length: 373.700±315.788\n", ++ "Rollout 700/9766, Reward: 259.856±19.403, Episode_length: 231.900±35.004\n", ++ "Rollout 701/9766, Reward: 246.636±34.527, Episode_length: 302.500±236.721\n", ++ "Rollout 702/9766, Reward: 255.308±39.975, Episode_length: 283.500±240.228\n", ++ "Rollout 703/9766, Reward: 256.525±57.015, Episode_length: 399.300±301.170\n", ++ "Rollout 704/9766, Reward: 67.770±552.149, Episode_length: 293.100±238.122\n", ++ "Rollout 705/9766, Reward: 239.748±47.664, Episode_length: 453.900±348.281\n", ++ "Rollout 706/9766, Reward: 243.568±60.305, Episode_length: 224.800±28.698\n", ++ "Rollout 707/9766, Reward: 280.277±15.794, Episode_length: 225.700±12.474\n", ++ "Rollout 708/9766, Reward: 273.286±41.922, Episode_length: 319.100±228.552\n", ++ "Rollout 709/9766, Reward: 270.861±27.515, Episode_length: 256.500±110.456\n", ++ "Rollout 710/9766, Reward: 246.717±71.466, Episode_length: 209.200±22.728\n", ++ "Rollout 711/9766, Reward: 278.298±17.369, Episode_length: 220.100±25.571\n", ++ "Rollout 712/9766, Reward: 281.219±23.091, Episode_length: 223.800±24.453\n", ++ "Rollout 713/9766, Reward: 253.074±68.722, Episode_length: 228.400±29.763\n", ++ "Rollout 714/9766, Reward: 144.677±394.606, Episode_length: 224.900±48.403\n", ++ "Rollout 715/9766, Reward: 159.661±267.367, Episode_length: 219.100±48.653\n", ++ "Rollout 716/9766, Reward: 266.425±35.392, Episode_length: 304.300±234.809\n", ++ "Rollout 717/9766, Reward: 175.432±224.429, Episode_length: 315.700±231.263\n", ++ "Rollout 718/9766, Reward: 62.612±403.967, Episode_length: 242.000±50.543\n", ++ "Rollout 719/9766, Reward: 160.290±307.690, Episode_length: 247.900±54.726\n", ++ "Rollout 720/9766, Reward: 167.279±310.938, Episode_length: 239.300±58.152\n", ++ "Rollout 721/9766, Reward: 183.551±275.368, Episode_length: 228.600±62.012\n", ++ "Rollout 722/9766, Reward: 264.651±39.177, Episode_length: 315.200±228.862\n", ++ "Rollout 723/9766, Reward: 272.654±18.213, Episode_length: 253.300±32.056\n", ++ "Rollout 724/9766, Reward: 266.674±21.586, Episode_length: 215.700±26.321\n", ++ "Rollout 725/9766, Reward: 273.860±13.859, Episode_length: 231.400±25.515\n", ++ "Rollout 726/9766, Reward: 279.850±17.281, Episode_length: 227.100±24.386\n", ++ "Rollout 727/9766, Reward: 273.796±15.269, Episode_length: 218.500±29.292\n", ++ "Rollout 728/9766, Reward: 262.651±46.007, Episode_length: 292.600±237.108\n", ++ "Rollout 729/9766, Reward: 272.590±17.623, Episode_length: 223.700±25.152\n", ++ "Rollout 730/9766, Reward: 271.413±17.389, Episode_length: 211.500±26.097\n", ++ "Rollout 731/9766, Reward: 252.101±43.991, Episode_length: 450.600±333.970\n", ++ "Rollout 732/9766, Reward: 272.750±14.580, Episode_length: 219.700±27.394\n", ++ "Rollout 733/9766, Reward: 242.898±61.909, Episode_length: 476.000±329.894\n", ++ "Rollout 734/9766, Reward: 267.579±42.550, Episode_length: 316.700±232.058\n", ++ "Rollout 735/9766, Reward: 270.136±15.720, Episode_length: 218.200±36.948\n", ++ "Rollout 736/9766, Reward: 254.211±43.545, Episode_length: 308.900±231.901\n", ++ "Rollout 737/9766, Reward: 278.049±12.723, Episode_length: 211.800±39.194\n", ++ "Rollout 738/9766, Reward: 283.282±18.970, Episode_length: 254.700±151.609\n", ++ "Rollout 739/9766, Reward: 280.827±15.195, Episode_length: 232.200±30.462\n", ++ "Rollout 740/9766, Reward: 276.867±16.284, Episode_length: 241.100±36.977\n", ++ "Rollout 741/9766, Reward: 284.714±18.105, Episode_length: 236.600±42.949\n", ++ "Rollout 742/9766, Reward: 276.709±13.589, Episode_length: 226.100±24.801\n", ++ "Rollout 743/9766, Reward: 262.173±15.646, Episode_length: 220.700±37.414\n", ++ "Rollout 744/9766, Reward: 268.984±33.738, Episode_length: 301.800±236.343\n", ++ "Rollout 745/9766, Reward: 272.111±14.303, Episode_length: 217.100±39.068\n", ++ "Rollout 746/9766, Reward: 264.626±34.471, Episode_length: 288.100±239.125\n", ++ "Rollout 747/9766, Reward: -355.264±412.602, Episode_length: 124.500±46.427\n", ++ "Rollout 748/9766, Reward: 120.724±329.340, Episode_length: 211.100±62.505\n", ++ "Rollout 749/9766, Reward: -165.096±435.382, Episode_length: 209.300±207.925\n", ++ "Rollout 750/9766, Reward: -262.447±362.757, Episode_length: 138.200±73.921\n", ++ "Rollout 751/9766, Reward: -296.787±381.891, Episode_length: 134.800±67.596\n", ++ "Rollout 752/9766, Reward: -433.341±242.210, Episode_length: 92.700±27.817\n", ++ "Rollout 753/9766, Reward: -411.778±348.999, Episode_length: 141.900±99.596\n", ++ "Rollout 754/9766, Reward: -426.314±257.109, Episode_length: 121.800±50.917\n", ++ "Rollout 755/9766, Reward: -392.306±343.454, Episode_length: 137.600±54.250\n", ++ "Rollout 756/9766, Reward: 110.761±308.586, Episode_length: 205.800±55.535\n", ++ "Rollout 757/9766, Reward: -72.809±416.009, Episode_length: 267.900±250.707\n", ++ "Rollout 758/9766, Reward: -232.357±423.068, Episode_length: 162.500±64.091\n", ++ "Rollout 759/9766, Reward: 19.427±530.594, Episode_length: 236.400±69.766\n", ++ "Rollout 760/9766, Reward: 78.542±415.824, Episode_length: 214.300±54.845\n", ++ "Rollout 761/9766, Reward: 188.670±269.437, Episode_length: 230.800±49.264\n", ++ "Rollout 762/9766, Reward: 9.270±408.671, Episode_length: 184.000±58.050\n", ++ "Rollout 763/9766, Reward: -269.946±755.374, Episode_length: 272.700±250.393\n", ++ "Rollout 764/9766, Reward: 27.278±390.491, Episode_length: 188.000±48.953\n", ++ "Rollout 765/9766, Reward: 182.908±270.981, Episode_length: 208.500±50.765\n", ++ "Rollout 766/9766, Reward: 140.002±425.821, Episode_length: 222.400±45.857\n", ++ "Rollout 767/9766, Reward: 198.702±226.473, Episode_length: 250.200±42.548\n", ++ "Rollout 768/9766, Reward: 269.652±12.257, Episode_length: 237.300±51.633\n", ++ "Rollout 769/9766, Reward: 273.739±14.980, Episode_length: 291.100±222.450\n", ++ "Rollout 770/9766, Reward: 269.691±14.812, Episode_length: 228.200±30.623\n", ++ "Rollout 771/9766, Reward: 41.493±664.860, Episode_length: 224.600±38.210\n", ++ "Rollout 772/9766, Reward: 126.273±463.720, Episode_length: 233.600±46.744\n", ++ "Rollout 773/9766, Reward: 22.156±756.817, Episode_length: 232.100±45.676\n", ++ "Rollout 774/9766, Reward: 266.819±16.647, Episode_length: 203.700±16.131\n", ++ "Rollout 775/9766, Reward: 92.903±464.664, Episode_length: 294.400±237.122\n", ++ "Rollout 776/9766, Reward: -322.000±938.222, Episode_length: 216.400±32.219\n", ++ "Rollout 777/9766, Reward: 248.965±39.952, Episode_length: 374.400±314.009\n", ++ "Rollout 778/9766, Reward: 270.043±15.087, Episode_length: 212.400±20.548\n", ++ "Rollout 779/9766, Reward: 276.689±16.548, Episode_length: 247.300±27.896\n", ++ "Rollout 780/9766, Reward: 103.170±262.291, Episode_length: 331.900±232.547\n", ++ "Rollout 781/9766, Reward: 180.497±97.883, Episode_length: 543.600±373.873\n", ++ "Rollout 782/9766, Reward: 225.179±54.100, Episode_length: 424.400±307.431\n", ++ "Rollout 783/9766, Reward: 116.990±427.980, Episode_length: 313.700±232.582\n", ++ "Rollout 784/9766, Reward: 68.720±589.290, Episode_length: 333.000±227.016\n", ++ "Rollout 785/9766, Reward: 193.765±127.646, Episode_length: 307.600±233.506\n", ++ "Rollout 786/9766, Reward: -13.016±625.818, Episode_length: 284.600±239.771\n", ++ "Rollout 787/9766, Reward: 276.517±18.647, Episode_length: 240.500±44.155\n", ++ "Rollout 788/9766, Reward: 199.328±97.613, Episode_length: 386.600±310.066\n", ++ "Rollout 789/9766, Reward: 244.461±75.021, Episode_length: 229.700±44.681\n", ++ "Rollout 790/9766, Reward: 2.058±754.031, Episode_length: 290.400±238.336\n", ++ "Rollout 791/9766, Reward: 154.400±309.317, Episode_length: 393.600±306.131\n", ++ "Rollout 792/9766, Reward: 260.781±52.476, Episode_length: 312.400±233.147\n", ++ "Rollout 793/9766, Reward: 269.505±16.910, Episode_length: 215.600±38.474\n", ++ "Rollout 794/9766, Reward: 239.600±46.687, Episode_length: 382.300±306.231\n", ++ "Rollout 795/9766, Reward: 264.862±10.264, Episode_length: 224.000±21.052\n", ++ "Rollout 796/9766, Reward: 279.188±13.347, Episode_length: 247.200±49.666\n", ++ "Rollout 797/9766, Reward: 266.138±25.894, Episode_length: 204.500±17.043\n", ++ "Rollout 798/9766, Reward: 279.869±18.178, Episode_length: 213.500±35.775\n", ++ "Rollout 799/9766, Reward: 269.555±17.539, Episode_length: 229.400±31.017\n", ++ "Rollout 800/9766, Reward: 231.605±52.520, Episode_length: 541.500±347.749\n", ++ "Rollout 801/9766, Reward: 277.807±15.591, Episode_length: 213.900±27.898\n", ++ "Rollout 802/9766, Reward: 277.988±24.693, Episode_length: 273.200±172.966\n", ++ "Rollout 803/9766, Reward: 276.727±15.207, Episode_length: 240.300±40.122\n", ++ "Rollout 804/9766, Reward: 277.714±28.035, Episode_length: 229.300±70.609\n", ++ "Rollout 805/9766, Reward: 286.163±9.930, Episode_length: 218.000±36.989\n", ++ "Rollout 806/9766, Reward: 289.476±13.020, Episode_length: 225.300±43.875\n", ++ "Rollout 807/9766, Reward: 271.819±20.447, Episode_length: 220.100±22.841\n", ++ "Rollout 808/9766, Reward: 276.630±19.698, Episode_length: 220.200±48.645\n", ++ "Rollout 809/9766, Reward: 271.488±21.857, Episode_length: 214.600±17.042\n", ++ "Rollout 810/9766, Reward: 285.280±12.466, Episode_length: 225.600±27.030\n", ++ "Rollout 811/9766, Reward: 222.037±80.972, Episode_length: 356.000±321.281\n", ++ "Rollout 812/9766, Reward: 247.744±22.465, Episode_length: 260.500±46.027\n", ++ "Rollout 813/9766, Reward: 270.866±20.595, Episode_length: 219.500±26.417\n", ++ "Rollout 814/9766, Reward: 219.849±44.120, Episode_length: 346.300±232.691\n", ++ "Rollout 815/9766, Reward: 280.021±20.006, Episode_length: 222.100±45.522\n", ++ "Rollout 816/9766, Reward: 213.006±47.053, Episode_length: 518.100±308.788\n", ++ "Rollout 817/9766, Reward: 229.943±35.774, Episode_length: 353.700±145.940\n", ++ "Rollout 818/9766, Reward: 182.452±86.665, Episode_length: 548.600±339.588\n", ++ "Rollout 819/9766, Reward: 221.805±60.592, Episode_length: 448.900±307.717\n", ++ "Rollout 820/9766, Reward: 254.156±23.880, Episode_length: 276.900±60.436\n", ++ "Rollout 821/9766, Reward: 243.650±54.361, Episode_length: 359.200±233.938\n", ++ "Rollout 822/9766, Reward: 235.757±32.045, Episode_length: 329.800±197.216\n", ++ "Rollout 823/9766, Reward: 233.467±32.158, Episode_length: 405.700±224.396\n", ++ "Rollout 824/9766, Reward: 218.808±58.628, Episode_length: 437.900±310.017\n", ++ "Rollout 825/9766, Reward: 224.613±56.956, Episode_length: 388.400±308.872\n", ++ "Rollout 826/9766, Reward: 246.120±49.453, Episode_length: 307.300±233.837\n", ++ "Rollout 827/9766, Reward: 209.428±68.639, Episode_length: 546.000±372.857\n", ++ "Rollout 828/9766, Reward: 236.194±45.195, Episode_length: 416.400±296.706\n", ++ "Rollout 829/9766, Reward: 243.985±39.560, Episode_length: 297.900±235.267\n", ++ "Rollout 830/9766, Reward: 217.663±55.113, Episode_length: 471.200±351.882\n", ++ "Rollout 831/9766, Reward: 243.186±58.542, Episode_length: 375.800±314.559\n", ++ "Rollout 832/9766, Reward: 205.865±64.407, Episode_length: 538.600±381.054\n", ++ "Rollout 833/9766, Reward: 259.541±25.366, Episode_length: 213.000±49.970\n", ++ "Rollout 834/9766, Reward: 261.378±44.671, Episode_length: 289.000±237.675\n", ++ "Rollout 835/9766, Reward: 247.025±51.232, Episode_length: 433.700±348.069\n", ++ "Rollout 836/9766, Reward: 270.449±44.391, Episode_length: 288.600±238.539\n", ++ "Rollout 837/9766, Reward: 281.545±16.522, Episode_length: 209.000±30.345\n", ++ "Rollout 838/9766, Reward: 277.245±11.979, Episode_length: 191.400±28.587\n", ++ "Rollout 839/9766, Reward: 261.765±43.727, Episode_length: 282.200±247.195\n", ++ "Rollout 840/9766, Reward: 287.314±22.637, Episode_length: 186.600±19.566\n", ++ "Rollout 841/9766, Reward: 264.626±15.057, Episode_length: 199.400±26.759\n", ++ "Rollout 842/9766, Reward: 254.572±47.103, Episode_length: 364.200±318.620\n", ++ "Rollout 843/9766, Reward: 265.432±18.657, Episode_length: 198.500±25.343\n", ++ "Rollout 844/9766, Reward: 269.080±18.436, Episode_length: 279.000±222.757\n", ++ "Rollout 845/9766, Reward: 241.262±58.861, Episode_length: 356.000±322.678\n", ++ "Rollout 846/9766, Reward: 224.844±63.306, Episode_length: 404.800±325.775\n", ++ "Rollout 847/9766, Reward: 246.760±51.500, Episode_length: 351.700±297.286\n", ++ "Rollout 848/9766, Reward: 262.338±17.790, Episode_length: 284.300±151.717\n", ++ "Rollout 849/9766, Reward: 272.966±22.909, Episode_length: 209.000±19.935\n", ++ "Rollout 850/9766, Reward: 233.839±79.139, Episode_length: 440.100±367.068\n", ++ "Rollout 851/9766, Reward: 251.889±46.574, Episode_length: 354.600±323.268\n", ++ "Rollout 852/9766, Reward: 252.576±48.960, Episode_length: 353.400±324.250\n", ++ "Rollout 853/9766, Reward: 235.554±47.643, Episode_length: 418.200±335.892\n", ++ "Rollout 854/9766, Reward: 270.456±19.485, Episode_length: 192.100±16.195\n", ++ "Rollout 855/9766, Reward: 272.773±18.462, Episode_length: 246.900±121.698\n", ++ "Rollout 856/9766, Reward: 236.801±45.606, Episode_length: 521.800±390.811\n", ++ "Rollout 857/9766, Reward: 269.089±15.374, Episode_length: 207.300±17.989\n", ++ "Rollout 858/9766, Reward: 209.772±59.167, Episode_length: 614.800±385.409\n", ++ "Rollout 859/9766, Reward: 273.372±19.774, Episode_length: 216.100±23.730\n", ++ "Rollout 860/9766, Reward: 249.885±60.590, Episode_length: 385.700±310.479\n", ++ "Rollout 861/9766, Reward: 273.425±19.334, Episode_length: 213.400±19.770\n", ++ "Rollout 862/9766, Reward: 272.302±23.797, Episode_length: 287.300±153.204\n", ++ "Rollout 863/9766, Reward: 260.623±45.336, Episode_length: 368.100±295.455\n", ++ "Rollout 864/9766, Reward: 279.471±17.950, Episode_length: 222.900±48.651\n", ++ "Rollout 865/9766, Reward: 273.002±23.758, Episode_length: 235.500±59.690\n", ++ "Rollout 866/9766, Reward: 282.249±16.420, Episode_length: 216.200±22.895\n", ++ "Rollout 867/9766, Reward: 266.246±16.342, Episode_length: 214.800±29.137\n", ++ "Rollout 868/9766, Reward: 273.463±21.459, Episode_length: 233.000±34.068\n", ++ "Rollout 869/9766, Reward: 276.520±11.975, Episode_length: 225.700±27.753\n", ++ "Rollout 870/9766, Reward: 274.557±22.677, Episode_length: 273.300±177.224\n", ++ "Rollout 871/9766, Reward: 267.737±21.947, Episode_length: 202.700±22.145\n", ++ "Rollout 872/9766, Reward: 283.195±15.538, Episode_length: 206.700±19.246\n", ++ "Rollout 873/9766, Reward: 278.579±16.369, Episode_length: 192.800±18.745\n", ++ "Rollout 874/9766, Reward: 253.298±35.235, Episode_length: 274.400±242.712\n", ++ "Rollout 875/9766, Reward: 272.626±17.521, Episode_length: 279.900±175.120\n", ++ "Rollout 876/9766, Reward: 250.405±61.686, Episode_length: 183.400±25.897\n", ++ "Rollout 877/9766, Reward: 265.240±35.843, Episode_length: 364.300±297.427\n", ++ "Rollout 878/9766, Reward: 266.171±41.911, Episode_length: 280.400±240.936\n", ++ "Rollout 879/9766, Reward: 271.935±12.545, Episode_length: 201.300±15.060\n", ++ "Rollout 880/9766, Reward: 260.667±33.617, Episode_length: 272.500±242.992\n", ++ "Rollout 881/9766, Reward: 274.722±16.978, Episode_length: 228.400±50.938\n", ++ "Rollout 882/9766, Reward: 279.796±16.449, Episode_length: 206.600±26.383\n", ++ "Rollout 883/9766, Reward: 279.872±14.371, Episode_length: 196.800±25.015\n", ++ "Rollout 884/9766, Reward: 280.590±23.397, Episode_length: 202.300±30.692\n", ++ "Rollout 885/9766, Reward: 278.479±16.481, Episode_length: 208.900±21.672\n", ++ "Rollout 886/9766, Reward: 271.311±37.741, Episode_length: 273.700±242.851\n", ++ "Rollout 887/9766, Reward: 261.225±15.773, Episode_length: 261.000±214.324\n", ++ "Rollout 888/9766, Reward: 269.250±12.730, Episode_length: 176.800±14.098\n", ++ "Rollout 889/9766, Reward: 284.323±17.601, Episode_length: 195.400±35.251\n", ++ "Rollout 890/9766, Reward: 251.627±50.002, Episode_length: 389.900±311.194\n", ++ "Rollout 891/9766, Reward: 263.668±40.165, Episode_length: 330.200±255.941\n", ++ "Rollout 892/9766, Reward: 241.023±55.771, Episode_length: 379.700±312.999\n", ++ "Rollout 893/9766, Reward: 273.922±19.904, Episode_length: 398.100±278.616\n", ++ "Rollout 894/9766, Reward: 273.706±35.398, Episode_length: 295.500±236.179\n", ++ "Rollout 895/9766, Reward: 204.795±57.135, Episode_length: 689.000±382.013\n", ++ "Rollout 896/9766, Reward: 199.096±55.291, Episode_length: 744.600±360.638\n", ++ "Rollout 897/9766, Reward: 278.496±16.556, Episode_length: 218.100±26.079\n", ++ "Rollout 898/9766, Reward: 263.665±37.756, Episode_length: 381.900±298.727\n", ++ "Rollout 899/9766, Reward: 279.708±17.400, Episode_length: 214.800±17.186\n", ++ "Rollout 900/9766, Reward: 210.216±62.440, Episode_length: 816.000±313.790\n", ++ "Rollout 901/9766, Reward: 288.340±16.946, Episode_length: 212.700±26.310\n", ++ "Rollout 902/9766, Reward: 283.254±18.164, Episode_length: 223.400±50.887\n", ++ "Rollout 903/9766, Reward: 284.699±16.266, Episode_length: 235.300±108.198\n", ++ "Rollout 904/9766, Reward: 284.813±15.635, Episode_length: 281.700±181.471\n", ++ "Rollout 905/9766, Reward: 275.705±13.379, Episode_length: 187.800±24.754\n", ++ "Rollout 906/9766, Reward: 286.950±19.154, Episode_length: 204.000±17.349\n", ++ "Rollout 907/9766, Reward: 278.679±21.501, Episode_length: 192.100±22.621\n", ++ "Rollout 908/9766, Reward: 280.456±23.168, Episode_length: 194.800±20.009\n", ++ "Rollout 909/9766, Reward: 283.174±9.832, Episode_length: 178.200±15.555\n", ++ "Rollout 910/9766, Reward: 252.833±51.237, Episode_length: 453.100±362.758\n", ++ "Rollout 911/9766, Reward: 220.049±54.531, Episode_length: 870.300±199.184\n", ++ "Rollout 912/9766, Reward: 259.258±60.173, Episode_length: 535.000±353.547\n", ++ "Rollout 913/9766, Reward: 233.864±53.931, Episode_length: 594.200±406.008\n", ++ "Rollout 914/9766, Reward: 223.041±53.793, Episode_length: 920.400±111.302\n", ++ "Rollout 915/9766, Reward: 189.268±52.537, Episode_length: 835.300±329.528\n", ++ "Rollout 916/9766, Reward: 230.349±46.600, Episode_length: 705.500±370.238\n", ++ "Rollout 917/9766, Reward: 235.960±48.014, Episode_length: 507.800±401.898\n", ++ "Rollout 918/9766, Reward: 278.129±16.583, Episode_length: 179.100±20.393\n", ++ "Rollout 919/9766, Reward: 242.820±49.358, Episode_length: 558.500±377.119\n", ++ "Rollout 920/9766, Reward: 290.331±16.766, Episode_length: 258.200±204.017\n", ++ "Rollout 921/9766, Reward: 288.039±12.687, Episode_length: 172.300±17.601\n", ++ "Rollout 922/9766, Reward: 283.065±14.548, Episode_length: 179.000±20.857\n", ++ "Rollout 923/9766, Reward: 287.173±14.254, Episode_length: 189.300±18.155\n", ++ "Rollout 924/9766, Reward: 286.737±10.353, Episode_length: 186.800±18.395\n", ++ "Rollout 925/9766, Reward: 278.760±13.481, Episode_length: 176.500±20.392\n", ++ "Rollout 926/9766, Reward: 289.240±21.849, Episode_length: 189.400±27.840\n", ++ "Rollout 927/9766, Reward: 287.781±15.964, Episode_length: 255.800±199.337\n", ++ "Rollout 928/9766, Reward: 284.316±19.799, Episode_length: 188.300±8.844\n", ++ "Rollout 929/9766, Reward: 273.816±17.928, Episode_length: 200.800±41.935\n", ++ "Rollout 930/9766, Reward: 268.701±30.307, Episode_length: 278.900±240.988\n", ++ "Rollout 931/9766, Reward: 278.386±20.779, Episode_length: 184.300±16.571\n", ++ "Rollout 932/9766, Reward: 288.171±12.992, Episode_length: 195.400±23.148\n", ++ "Rollout 933/9766, Reward: 288.443±21.216, Episode_length: 191.300±29.668\n", ++ "Rollout 934/9766, Reward: 270.473±21.899, Episode_length: 187.800±19.354\n", ++ "Rollout 935/9766, Reward: 281.491±25.571, Episode_length: 198.900±22.967\n", ++ "Rollout 936/9766, Reward: 278.934±18.007, Episode_length: 181.300±13.609\n", ++ "Rollout 937/9766, Reward: 285.215±19.692, Episode_length: 187.600±28.196\n", ++ "Rollout 938/9766, Reward: 295.699±6.405, Episode_length: 199.400±20.046\n", ++ "Rollout 939/9766, Reward: 293.234±18.488, Episode_length: 198.500±22.272\n", ++ "Rollout 940/9766, Reward: 276.851±21.365, Episode_length: 186.100±20.310\n", ++ "Rollout 941/9766, Reward: 283.405±13.837, Episode_length: 187.600±20.510\n", ++ "Rollout 942/9766, Reward: 282.104±22.848, Episode_length: 184.000±18.466\n", ++ "Rollout 943/9766, Reward: 288.243±12.761, Episode_length: 189.200±12.448\n", ++ "Rollout 944/9766, Reward: 280.281±48.213, Episode_length: 277.200±241.852\n", ++ "Rollout 945/9766, Reward: 284.561±21.678, Episode_length: 187.800±25.490\n", ++ "Rollout 946/9766, Reward: 278.505±10.871, Episode_length: 186.400±13.245\n", ++ "Rollout 947/9766, Reward: 270.171±30.182, Episode_length: 271.700±243.655\n", ++ "Rollout 948/9766, Reward: 285.194±14.426, Episode_length: 195.600±11.723\n", ++ "Rollout 949/9766, Reward: 278.115±15.839, Episode_length: 202.800±61.545\n", ++ "Rollout 950/9766, Reward: 278.648±12.299, Episode_length: 182.500±23.817\n", ++ "Rollout 951/9766, Reward: 276.733±21.062, Episode_length: 184.000±27.900\n", ++ "Rollout 952/9766, Reward: 290.154±12.728, Episode_length: 192.500±37.006\n", ++ "Rollout 953/9766, Reward: 282.198±21.413, Episode_length: 192.800±24.555\n", ++ "Rollout 954/9766, Reward: 283.929±17.609, Episode_length: 192.100±18.955\n", ++ "Rollout 955/9766, Reward: 280.702±21.013, Episode_length: 181.000±24.278\n", ++ "Rollout 956/9766, Reward: 291.755±14.571, Episode_length: 195.900±22.871\n", ++ "Rollout 957/9766, Reward: 294.240±19.496, Episode_length: 197.300±21.836\n", ++ "Rollout 958/9766, Reward: 275.494±20.600, Episode_length: 232.500±147.292\n", ++ "Rollout 959/9766, Reward: 259.314±58.619, Episode_length: 355.900±322.778\n", ++ "Rollout 960/9766, Reward: 285.580±8.271, Episode_length: 209.500±29.901\n", ++ "Rollout 961/9766, Reward: 284.661±16.540, Episode_length: 208.300±26.062\n", ++ "Rollout 962/9766, Reward: 291.026±16.588, Episode_length: 206.900±25.157\n", ++ "Rollout 963/9766, Reward: 288.773±15.446, Episode_length: 215.800±23.874\n", ++ "Rollout 964/9766, Reward: 254.311±71.230, Episode_length: 197.200±32.354\n", ++ "Rollout 965/9766, Reward: 278.128±16.528, Episode_length: 201.600±22.232\n", ++ "Rollout 966/9766, Reward: -168.542±362.755, Episode_length: 139.000±47.021\n", ++ "Rollout 967/9766, Reward: 44.346±330.743, Episode_length: 167.900±29.167\n", ++ "Rollout 968/9766, Reward: 276.981±14.886, Episode_length: 225.200±39.683\n", ++ "Rollout 969/9766, Reward: 284.695±16.949, Episode_length: 202.800±24.547\n", ++ "Rollout 970/9766, Reward: 281.752±13.437, Episode_length: 205.100±26.617\n", ++ "Rollout 971/9766, Reward: 291.507±10.054, Episode_length: 208.500±26.860\n", ++ "Rollout 972/9766, Reward: -26.637±459.749, Episode_length: 168.500±46.830\n", ++ "Rollout 973/9766, Reward: 289.018±13.402, Episode_length: 201.400±24.598\n", ++ "Rollout 974/9766, Reward: 281.692±19.058, Episode_length: 192.600±24.957\n", ++ "Rollout 975/9766, Reward: 263.865±35.292, Episode_length: 275.000±242.028\n", ++ "Rollout 976/9766, Reward: 292.079±13.573, Episode_length: 200.300±29.712\n", ++ "Rollout 977/9766, Reward: 282.097±16.529, Episode_length: 186.700±11.748\n", ++ "Rollout 978/9766, Reward: 277.697±14.212, Episode_length: 188.000±11.636\n", ++ "Rollout 979/9766, Reward: 288.945±17.027, Episode_length: 210.500±36.368\n", ++ "Rollout 980/9766, Reward: 281.758±22.194, Episode_length: 193.800±23.769\n", ++ "Rollout 981/9766, Reward: 210.833±210.753, Episode_length: 201.800±32.542\n", ++ "Rollout 982/9766, Reward: 196.319±234.670, Episode_length: 191.300±33.499\n", ++ "Rollout 983/9766, Reward: 276.974±18.535, Episode_length: 207.000±28.910\n", ++ "Rollout 984/9766, Reward: 278.223±13.906, Episode_length: 191.800±8.400\n", ++ "Rollout 985/9766, Reward: 272.378±23.318, Episode_length: 233.400±146.170\n", ++ "Rollout 986/9766, Reward: 273.495±39.008, Episode_length: 299.700±241.632\n", ++ "Rollout 987/9766, Reward: 265.766±35.544, Episode_length: 281.500±241.224\n", ++ "Rollout 988/9766, Reward: 282.963±19.994, Episode_length: 195.100±16.507\n", ++ "Rollout 989/9766, Reward: 274.329±15.934, Episode_length: 174.900±13.479\n", ++ "Rollout 990/9766, Reward: 273.481±17.128, Episode_length: 192.800±26.320\n", ++ "Rollout 991/9766, Reward: 283.500±14.677, Episode_length: 187.800±16.382\n", ++ "Rollout 992/9766, Reward: 280.862±15.697, Episode_length: 193.900±19.736\n", ++ "Rollout 993/9766, Reward: 284.952±12.554, Episode_length: 214.000±26.522\n", ++ "Rollout 994/9766, Reward: 283.220±17.871, Episode_length: 191.200±20.385\n", ++ "Rollout 995/9766, Reward: 290.274±11.677, Episode_length: 210.200±28.248\n", ++ "Rollout 996/9766, Reward: 274.623±16.344, Episode_length: 185.400±14.458\n", ++ "Rollout 997/9766, Reward: 292.154±20.742, Episode_length: 203.600±23.299\n", ++ "Rollout 998/9766, Reward: 283.374±16.422, Episode_length: 209.800±29.305\n", ++ "Rollout 999/9766, Reward: 294.545±6.809, Episode_length: 209.300±25.223\n", ++ "Rollout 1000/9766, Reward: 281.179±13.305, Episode_length: 189.800±20.581\n", ++ "Rollout 1001/9766, Reward: 209.501±227.694, Episode_length: 207.700±43.361\n", ++ "Rollout 1002/9766, Reward: 282.582±15.097, Episode_length: 202.300±25.620\n", ++ "Rollout 1003/9766, Reward: 203.364±237.539, Episode_length: 209.600±31.724\n", ++ "Rollout 1004/9766, Reward: 274.875±15.456, Episode_length: 202.300±24.968\n", ++ "Rollout 1005/9766, Reward: 282.165±15.289, Episode_length: 210.500±21.299\n", ++ "Rollout 1006/9766, Reward: 269.637±17.451, Episode_length: 198.600±20.031\n", ++ "Rollout 1007/9766, Reward: 197.309±207.853, Episode_length: 190.600±26.815\n", ++ "Rollout 1008/9766, Reward: 147.952±436.594, Episode_length: 216.100±31.870\n", ++ "Rollout 1009/9766, Reward: 277.492±18.936, Episode_length: 211.800±26.324\n", ++ "Rollout 1010/9766, Reward: 284.130±11.349, Episode_length: 209.500±20.954\n", ++ "Rollout 1011/9766, Reward: 290.408±12.492, Episode_length: 226.800±40.693\n", ++ "Rollout 1012/9766, Reward: 288.169±16.506, Episode_length: 209.300±23.448\n", ++ "Rollout 1013/9766, Reward: 283.728±17.917, Episode_length: 206.800±23.129\n", ++ "Rollout 1014/9766, Reward: 278.959±9.799, Episode_length: 207.400±32.879\n", ++ "Rollout 1015/9766, Reward: 279.314±21.917, Episode_length: 206.800±29.407\n", ++ "Rollout 1016/9766, Reward: 276.627±14.926, Episode_length: 208.600±16.566\n", ++ "Rollout 1017/9766, Reward: 267.795±38.961, Episode_length: 293.000±237.229\n", ++ "Rollout 1018/9766, Reward: 270.285±16.305, Episode_length: 203.500±19.515\n", ++ "Rollout 1019/9766, Reward: 285.730±18.305, Episode_length: 209.900±21.612\n", ++ "Rollout 1020/9766, Reward: 282.963±19.480, Episode_length: 207.500±16.687\n", ++ "Rollout 1021/9766, Reward: 277.888±6.698, Episode_length: 204.300±22.280\n", ++ "Rollout 1022/9766, Reward: 285.786±16.009, Episode_length: 226.200±23.957\n", ++ "Rollout 1023/9766, Reward: 277.378±15.167, Episode_length: 206.300±21.955\n", ++ "Rollout 1024/9766, Reward: 272.821±12.640, Episode_length: 189.900±16.896\n", ++ "Rollout 1025/9766, Reward: 280.804±14.786, Episode_length: 193.000±23.537\n", ++ "Rollout 1026/9766, Reward: 288.203±8.831, Episode_length: 195.600±20.417\n", ++ "Rollout 1027/9766, Reward: 287.096±15.723, Episode_length: 213.200±21.780\n", ++ "Rollout 1028/9766, Reward: 278.465±16.040, Episode_length: 204.600±24.188\n", ++ "Rollout 1029/9766, Reward: 296.724±15.032, Episode_length: 205.900±29.518\n", ++ "Rollout 1030/9766, Reward: 295.988±8.654, Episode_length: 193.100±27.205\n", ++ "Rollout 1031/9766, Reward: 285.796±17.461, Episode_length: 194.400±23.825\n", ++ "Rollout 1032/9766, Reward: 295.189±13.090, Episode_length: 203.800±29.607\n", ++ "Rollout 1033/9766, Reward: 294.080±17.167, Episode_length: 203.500±23.453\n", ++ "Rollout 1034/9766, Reward: 293.282±10.358, Episode_length: 192.800±19.385\n", ++ "Rollout 1035/9766, Reward: 285.013±20.175, Episode_length: 189.000±18.149\n", ++ "Rollout 1036/9766, Reward: 287.397±22.568, Episode_length: 197.100±26.779\n", ++ "Rollout 1037/9766, Reward: 285.231±10.131, Episode_length: 186.300±22.481\n", ++ "Rollout 1038/9766, Reward: 282.758±19.781, Episode_length: 186.600±21.228\n", ++ "Rollout 1039/9766, Reward: 287.608±12.425, Episode_length: 184.800±17.645\n", ++ "Rollout 1040/9766, Reward: 267.818±36.054, Episode_length: 266.600±245.341\n", ++ "Rollout 1041/9766, Reward: 280.548±14.646, Episode_length: 178.300±26.119\n", ++ "Rollout 1042/9766, Reward: 277.010±38.988, Episode_length: 266.200±245.562\n", ++ "Rollout 1043/9766, Reward: 288.905±20.862, Episode_length: 197.000±28.740\n", ++ "Rollout 1044/9766, Reward: 270.837±45.619, Episode_length: 271.900±243.810\n", ++ "Rollout 1045/9766, Reward: 288.745±14.019, Episode_length: 189.900±32.083\n", ++ "Rollout 1046/9766, Reward: 275.998±16.165, Episode_length: 196.200±17.342\n", ++ "Rollout 1047/9766, Reward: 285.199±21.182, Episode_length: 211.900±24.801\n", ++ "Rollout 1048/9766, Reward: 279.961±13.785, Episode_length: 202.700±27.864\n", ++ "Rollout 1049/9766, Reward: 279.047±13.233, Episode_length: 193.900±18.447\n", ++ "Rollout 1050/9766, Reward: 277.084±20.017, Episode_length: 215.900±29.579\n", ++ "Rollout 1051/9766, Reward: 282.707±14.659, Episode_length: 204.100±29.501\n", ++ "Rollout 1052/9766, Reward: 278.895±21.283, Episode_length: 206.500±35.906\n", ++ "Rollout 1053/9766, Reward: 271.449±22.398, Episode_length: 234.800±108.548\n", ++ "Rollout 1054/9766, Reward: 153.877±44.087, Episode_length: 764.000±301.803\n", ++ "Rollout 1055/9766, Reward: 195.582±54.283, Episode_length: 569.600±290.227\n", ++ "Rollout 1056/9766, Reward: 197.811±59.470, Episode_length: 694.900±263.411\n", ++ "Rollout 1057/9766, Reward: 172.928±54.454, Episode_length: 781.400±290.047\n", ++ "Rollout 1058/9766, Reward: 183.246±53.104, Episode_length: 636.000±306.120\n", ++ "Rollout 1059/9766, Reward: 188.108±50.918, Episode_length: 691.400±318.700\n", ++ "Rollout 1060/9766, Reward: 207.289±52.753, Episode_length: 529.300±317.835\n", ++ "Rollout 1061/9766, Reward: 186.775±52.813, Episode_length: 594.000±333.187\n", ++ "Rollout 1062/9766, Reward: 201.789±44.995, Episode_length: 471.900±278.370\n", ++ "Rollout 1063/9766, Reward: 195.090±55.869, Episode_length: 535.500±263.420\n", ++ "Rollout 1064/9766, Reward: 210.762±48.183, Episode_length: 526.300±293.287\n", ++ "Rollout 1065/9766, Reward: 195.986±68.244, Episode_length: 549.300±312.205\n", ++ "Rollout 1066/9766, Reward: 60.330±375.337, Episode_length: 559.600±365.738\n", ++ "Rollout 1067/9766, Reward: -223.140±672.510, Episode_length: 304.600±245.858\n", ++ "Rollout 1068/9766, Reward: -101.450±560.852, Episode_length: 492.800±346.536\n", ++ "Rollout 1069/9766, Reward: -356.569±678.930, Episode_length: 364.700±273.512\n", ++ "Rollout 1070/9766, Reward: 80.805±437.109, Episode_length: 461.000±330.866\n", ++ "Rollout 1071/9766, Reward: 216.959±53.750, Episode_length: 449.600±291.867\n", ++ "Rollout 1072/9766, Reward: 191.605±50.966, Episode_length: 633.600±310.894\n", ++ "Rollout 1073/9766, Reward: -57.407±837.026, Episode_length: 493.400±269.784\n", ++ "Rollout 1074/9766, Reward: 207.790±50.381, Episode_length: 570.200±352.283\n", ++ "Rollout 1075/9766, Reward: 173.478±53.861, Episode_length: 723.600±345.501\n", ++ "Rollout 1076/9766, Reward: 205.190±50.186, Episode_length: 538.800±330.173\n", ++ "Rollout 1077/9766, Reward: 232.775±32.325, Episode_length: 443.900±251.953\n", ++ "Rollout 1078/9766, Reward: 178.553±77.905, Episode_length: 701.100±317.124\n", ++ "Rollout 1079/9766, Reward: -49.080±867.103, Episode_length: 384.200±283.422\n", ++ "Rollout 1080/9766, Reward: 243.360±53.366, Episode_length: 406.200±302.216\n", ++ "Rollout 1081/9766, Reward: 233.982±40.768, Episode_length: 431.100±232.639\n", ++ "Rollout 1082/9766, Reward: 241.259±44.249, Episode_length: 473.800±254.264\n", ++ "Rollout 1083/9766, Reward: 226.058±46.939, Episode_length: 568.900±309.664\n", ++ "Rollout 1084/9766, Reward: 239.655±50.614, Episode_length: 345.500±238.411\n", ++ "Rollout 1085/9766, Reward: 198.524±60.336, Episode_length: 536.600±333.147\n", ++ "Rollout 1086/9766, Reward: 190.336±89.232, Episode_length: 342.500±178.461\n", ++ "Rollout 1087/9766, Reward: 253.477±25.662, Episode_length: 269.000±122.026\n", ++ "Rollout 1088/9766, Reward: 236.535±55.132, Episode_length: 388.100±309.369\n", ++ "Rollout 1089/9766, Reward: 247.171±48.982, Episode_length: 305.800±248.371\n", ++ "Rollout 1090/9766, Reward: 241.220±61.129, Episode_length: 369.500±316.230\n", ++ "Rollout 1091/9766, Reward: 251.536±23.391, Episode_length: 265.500±110.406\n", ++ "Rollout 1092/9766, Reward: 245.855±44.518, Episode_length: 331.800±225.938\n", ++ "Rollout 1093/9766, Reward: 218.455±87.355, Episode_length: 363.000±318.733\n", ++ "Rollout 1094/9766, Reward: 247.113±36.347, Episode_length: 290.400±238.934\n", ++ "Rollout 1095/9766, Reward: 255.084±52.475, Episode_length: 323.700±235.009\n", ++ "Rollout 1096/9766, Reward: 255.671±47.148, Episode_length: 356.300±231.003\n", ++ "Rollout 1097/9766, Reward: 222.332±56.058, Episode_length: 420.500±302.141\n", ++ "Rollout 1098/9766, Reward: 219.586±68.738, Episode_length: 493.400±348.216\n", ++ "Rollout 1099/9766, Reward: 271.875±20.842, Episode_length: 218.800±19.717\n", ++ "Rollout 1100/9766, Reward: 267.274±16.922, Episode_length: 221.400±24.274\n", ++ "Rollout 1101/9766, Reward: 290.024±19.577, Episode_length: 216.100±23.210\n", ++ "Rollout 1102/9766, Reward: 284.052±16.935, Episode_length: 219.900±18.119\n", ++ "Rollout 1103/9766, Reward: 271.385±12.933, Episode_length: 215.600±21.010\n", ++ "Rollout 1104/9766, Reward: 280.165±13.494, Episode_length: 230.800±19.271\n", ++ "Rollout 1105/9766, Reward: 262.292±58.764, Episode_length: 303.500±233.404\n", ++ "Rollout 1106/9766, Reward: 259.572±47.409, Episode_length: 302.100±233.821\n", ++ "Rollout 1107/9766, Reward: 274.312±25.759, Episode_length: 214.000±26.092\n", ++ "Rollout 1108/9766, Reward: 273.578±27.734, Episode_length: 293.900±219.445\n", ++ "Rollout 1109/9766, Reward: 265.380±53.784, Episode_length: 281.900±240.098\n", ++ "Rollout 1110/9766, Reward: 271.424±16.019, Episode_length: 199.200±22.207\n", ++ "Rollout 1111/9766, Reward: 277.815±18.085, Episode_length: 204.700±19.074\n", ++ "Rollout 1112/9766, Reward: 262.725±49.398, Episode_length: 290.800±237.144\n", ++ "Rollout 1113/9766, Reward: 260.500±33.549, Episode_length: 245.700±53.234\n", ++ "Rollout 1114/9766, Reward: 267.093±51.380, Episode_length: 301.900±233.829\n", ++ "Rollout 1115/9766, Reward: 265.462±19.053, Episode_length: 209.900±23.484\n", ++ "Rollout 1116/9766, Reward: 269.854±16.514, Episode_length: 197.300±20.756\n", ++ "Rollout 1117/9766, Reward: 276.663±17.531, Episode_length: 234.500±84.031\n", ++ "Rollout 1118/9766, Reward: 273.156±20.009, Episode_length: 209.800±21.651\n", ++ "Rollout 1119/9766, Reward: 264.351±46.740, Episode_length: 305.600±232.029\n", ++ "Rollout 1120/9766, Reward: 280.348±13.002, Episode_length: 238.000±54.380\n", ++ "Rollout 1121/9766, Reward: 250.134±46.773, Episode_length: 352.500±324.179\n", ++ "Rollout 1122/9766, Reward: 257.062±27.645, Episode_length: 296.000±219.447\n", ++ "Rollout 1123/9766, Reward: 256.785±72.682, Episode_length: 312.100±230.349\n", ++ "Rollout 1124/9766, Reward: 286.685±13.919, Episode_length: 242.300±73.709\n", ++ "Rollout 1125/9766, Reward: 251.206±47.780, Episode_length: 290.100±236.957\n", ++ "Rollout 1126/9766, Reward: 274.059±18.874, Episode_length: 203.500±17.154\n", ++ "Rollout 1127/9766, Reward: 263.555±59.347, Episode_length: 280.700±241.532\n", ++ "Rollout 1128/9766, Reward: 254.027±42.151, Episode_length: 329.500±274.090\n", ++ "Rollout 1129/9766, Reward: 256.258±44.111, Episode_length: 280.800±240.714\n", ++ "Rollout 1130/9766, Reward: 257.106±40.385, Episode_length: 283.200±239.297\n", ++ "Rollout 1131/9766, Reward: 267.794±44.724, Episode_length: 343.600±267.226\n", ++ "Rollout 1132/9766, Reward: 253.718±39.533, Episode_length: 320.500±255.581\n", ++ "Rollout 1133/9766, Reward: 266.770±34.980, Episode_length: 337.100±273.127\n", ++ "Rollout 1134/9766, Reward: 274.447±20.316, Episode_length: 282.200±230.001\n", ++ "Rollout 1135/9766, Reward: 239.466±54.329, Episode_length: 353.500±324.071\n", ++ "Rollout 1136/9766, Reward: 254.428±48.147, Episode_length: 281.100±240.158\n", ++ "Rollout 1137/9766, Reward: 226.429±67.048, Episode_length: 520.400±355.902\n", ++ "Rollout 1138/9766, Reward: 280.431±19.074, Episode_length: 293.300±225.402\n", ++ "Rollout 1139/9766, Reward: 238.870±66.967, Episode_length: 379.300±310.915\n", ++ "Rollout 1140/9766, Reward: 275.018±18.838, Episode_length: 210.500±21.823\n", ++ "Rollout 1141/9766, Reward: 268.739±21.939, Episode_length: 204.200±14.013\n", ++ "Rollout 1142/9766, Reward: 279.824±19.511, Episode_length: 204.900±19.664\n", ++ "Rollout 1143/9766, Reward: 289.934±21.194, Episode_length: 210.500±23.926\n", ++ "Rollout 1144/9766, Reward: 271.000±23.389, Episode_length: 202.100±18.539\n", ++ "Rollout 1145/9766, Reward: 253.912±64.921, Episode_length: 366.200±317.474\n", ++ "Rollout 1146/9766, Reward: 125.770±319.443, Episode_length: 189.000±59.968\n", ++ "Rollout 1147/9766, Reward: 190.659±272.626, Episode_length: 184.000±37.873\n", ++ "Rollout 1148/9766, Reward: 187.508±262.104, Episode_length: 190.400±43.816\n", ++ "Rollout 1149/9766, Reward: 264.987±15.663, Episode_length: 196.400±20.126\n", ++ "Rollout 1150/9766, Reward: 284.585±20.401, Episode_length: 220.300±18.477\n", ++ "Rollout 1151/9766, Reward: 269.855±16.070, Episode_length: 212.600±14.500\n", ++ "Rollout 1152/9766, Reward: 276.079±19.185, Episode_length: 209.500±12.800\n", ++ "Rollout 1153/9766, Reward: 276.333±40.655, Episode_length: 311.200±230.805\n", ++ "Rollout 1154/9766, Reward: 284.946±15.398, Episode_length: 203.400±20.505\n", ++ "Rollout 1155/9766, Reward: 286.204±13.745, Episode_length: 210.900±10.074\n", ++ "Rollout 1156/9766, Reward: 271.796±22.739, Episode_length: 197.100±21.778\n", ++ "Rollout 1157/9766, Reward: 276.229±17.382, Episode_length: 211.300±14.423\n", ++ "Rollout 1158/9766, Reward: 285.293±21.024, Episode_length: 213.200±31.224\n", ++ "Rollout 1159/9766, Reward: 267.609±42.236, Episode_length: 277.800±241.231\n", ++ "Rollout 1160/9766, Reward: 283.291±14.652, Episode_length: 202.800±14.034\n", ++ "Rollout 1161/9766, Reward: 281.320±13.234, Episode_length: 196.600±23.144\n", ++ "Rollout 1162/9766, Reward: 261.464±41.176, Episode_length: 272.500±243.261\n", ++ "Rollout 1163/9766, Reward: 277.985±17.038, Episode_length: 200.900±25.809\n", ++ "Rollout 1164/9766, Reward: 272.619±41.516, Episode_length: 273.200±243.368\n", ++ "Rollout 1165/9766, Reward: 286.850±18.970, Episode_length: 200.200±22.829\n", ++ "Rollout 1166/9766, Reward: 285.124±17.577, Episode_length: 271.700±226.351\n", ++ "Rollout 1167/9766, Reward: 280.066±17.599, Episode_length: 201.500±33.176\n", ++ "Rollout 1168/9766, Reward: 287.267±23.542, Episode_length: 208.700±22.729\n", ++ "Rollout 1169/9766, Reward: 282.827±19.430, Episode_length: 199.100±19.378\n", ++ "Rollout 1170/9766, Reward: 136.233±24.988, Episode_length: 1000.000±0.000\n", ++ "Rollout 1171/9766, Reward: 144.803±19.562, Episode_length: 1000.000±0.000\n", ++ "Rollout 1172/9766, Reward: 145.222±40.195, Episode_length: 927.400±217.800\n", ++ "Rollout 1173/9766, Reward: 285.032±15.618, Episode_length: 274.200±231.579\n", ++ "Rollout 1174/9766, Reward: 160.897±41.526, Episode_length: 990.100±29.700\n", ++ "Rollout 1175/9766, Reward: 264.779±33.474, Episode_length: 273.800±242.632\n", ++ "Rollout 1176/9766, Reward: 154.787±21.012, Episode_length: 1000.000±0.000\n", ++ "Rollout 1177/9766, Reward: 275.352±20.003, Episode_length: 319.300±232.418\n", ++ "Rollout 1178/9766, Reward: 286.751±13.583, Episode_length: 195.700±18.591\n", ++ "Rollout 1179/9766, Reward: 284.419±14.192, Episode_length: 203.000±26.582\n", ++ "Rollout 1180/9766, Reward: 278.544±19.370, Episode_length: 201.900±27.373\n", ++ "Rollout 1181/9766, Reward: 285.523±14.539, Episode_length: 197.000±31.966\n", ++ "Rollout 1182/9766, Reward: 279.786±16.212, Episode_length: 204.800±22.017\n", ++ "Rollout 1183/9766, Reward: 279.809±8.586, Episode_length: 198.100±20.067\n", ++ "Rollout 1184/9766, Reward: 280.837±15.866, Episode_length: 200.900±26.946\n", ++ "Rollout 1185/9766, Reward: 256.495±50.068, Episode_length: 280.800±240.869\n", ++ "Rollout 1186/9766, Reward: 272.821±18.899, Episode_length: 211.200±22.008\n", ++ "Rollout 1187/9766, Reward: 277.514±14.721, Episode_length: 210.000±31.375\n", ++ "Rollout 1188/9766, Reward: 277.868±21.772, Episode_length: 202.600±17.850\n", ++ "Rollout 1189/9766, Reward: 95.704±544.522, Episode_length: 204.300±21.415\n", ++ "Rollout 1190/9766, Reward: 275.496±13.961, Episode_length: 192.400±18.938\n", ++ "Rollout 1191/9766, Reward: 295.668±9.493, Episode_length: 222.700±17.263\n", ++ "Rollout 1192/9766, Reward: 270.390±44.448, Episode_length: 292.100±236.885\n", ++ "Rollout 1193/9766, Reward: 284.871±23.234, Episode_length: 204.200±24.400\n", ++ "Rollout 1194/9766, Reward: 264.048±38.924, Episode_length: 268.200±244.375\n", ++ "Rollout 1195/9766, Reward: 290.917±14.423, Episode_length: 204.900±24.781\n", ++ "Rollout 1196/9766, Reward: 288.037±21.112, Episode_length: 225.000±30.767\n", ++ "Rollout 1197/9766, Reward: 277.427±22.118, Episode_length: 281.100±211.695\n", ++ "Rollout 1198/9766, Reward: 272.893±24.528, Episode_length: 186.400±18.145\n", ++ "Rollout 1199/9766, Reward: 263.615±15.827, Episode_length: 367.700±276.759\n", ++ "Rollout 1200/9766, Reward: 280.999±23.112, Episode_length: 211.300±31.375\n", ++ "Rollout 1201/9766, Reward: 253.730±51.556, Episode_length: 283.100±239.886\n", ++ "Rollout 1202/9766, Reward: 272.698±26.032, Episode_length: 318.000±200.931\n", ++ "Rollout 1203/9766, Reward: 248.245±53.052, Episode_length: 372.000±314.612\n", ++ "Rollout 1204/9766, Reward: 216.179±68.468, Episode_length: 652.200±346.272\n", ++ "Rollout 1205/9766, Reward: 253.858±45.677, Episode_length: 360.300±257.640\n", ++ "Rollout 1206/9766, Reward: 235.938±60.706, Episode_length: 450.700±356.373\n", ++ "Rollout 1207/9766, Reward: 256.280±41.426, Episode_length: 377.800±307.538\n", ++ "Rollout 1208/9766, Reward: 264.840±16.964, Episode_length: 219.300±30.997\n", ++ "Rollout 1209/9766, Reward: 241.208±80.113, Episode_length: 341.300±245.514\n", ++ "Rollout 1210/9766, Reward: 246.706±54.081, Episode_length: 390.800±312.751\n", ++ "Rollout 1211/9766, Reward: 237.418±53.113, Episode_length: 364.100±318.298\n", ++ "Rollout 1212/9766, Reward: 257.246±42.084, Episode_length: 384.900±254.013\n", ++ "Rollout 1213/9766, Reward: 268.140±41.643, Episode_length: 288.200±238.181\n", ++ "Rollout 1214/9766, Reward: 254.869±44.890, Episode_length: 327.400±278.872\n", ++ "Rollout 1215/9766, Reward: 272.197±22.638, Episode_length: 257.100±188.901\n", ++ "Rollout 1216/9766, Reward: 257.094±32.204, Episode_length: 267.100±245.127\n", ++ "Rollout 1217/9766, Reward: 265.578±42.812, Episode_length: 283.100±239.763\n", ++ "Rollout 1218/9766, Reward: 278.021±19.407, Episode_length: 203.300±22.172\n", ++ "Rollout 1219/9766, Reward: 272.966±25.392, Episode_length: 187.100±17.073\n", ++ "Rollout 1220/9766, Reward: 179.042±46.321, Episode_length: 963.300±84.697\n", ++ "Rollout 1221/9766, Reward: 257.154±45.173, Episode_length: 417.200±348.518\n", ++ "Rollout 1222/9766, Reward: 196.324±44.922, Episode_length: 762.400±363.072\n", ++ "Rollout 1223/9766, Reward: 230.525±100.229, Episode_length: 270.500±244.854\n", ++ "Rollout 1224/9766, Reward: 254.741±51.413, Episode_length: 526.100±339.754\n", ++ "Rollout 1225/9766, Reward: 211.046±55.812, Episode_length: 759.400±366.450\n", ++ "Rollout 1226/9766, Reward: 277.466±22.406, Episode_length: 232.000±89.233\n", ++ "Rollout 1227/9766, Reward: 265.244±20.773, Episode_length: 190.400±14.277\n", ++ "Rollout 1228/9766, Reward: 258.263±48.570, Episode_length: 344.600±286.311\n", ++ "Rollout 1229/9766, Reward: 263.783±42.778, Episode_length: 277.300±242.341\n", ++ "Rollout 1230/9766, Reward: 284.762±21.714, Episode_length: 209.000±32.339\n", ++ "Rollout 1231/9766, Reward: 284.975±24.478, Episode_length: 205.100±24.978\n", ++ "Rollout 1232/9766, Reward: 281.542±12.547, Episode_length: 198.400±28.838\n", ++ "Rollout 1233/9766, Reward: 288.630±29.283, Episode_length: 209.500±43.482\n", ++ "Rollout 1234/9766, Reward: 284.889±15.667, Episode_length: 207.300±27.597\n", ++ "Rollout 1235/9766, Reward: 275.090±18.799, Episode_length: 209.000±47.523\n", ++ "Rollout 1236/9766, Reward: 283.196±23.964, Episode_length: 225.800±34.137\n", ++ "Rollout 1237/9766, Reward: 283.917±17.748, Episode_length: 183.100±25.264\n", ++ "Rollout 1238/9766, Reward: 283.045±15.235, Episode_length: 204.200±15.105\n", ++ "Rollout 1239/9766, Reward: 261.630±15.319, Episode_length: 184.800±15.158\n", ++ "Rollout 1240/9766, Reward: 274.597±18.839, Episode_length: 195.500±29.588\n", ++ "Rollout 1241/9766, Reward: 276.571±18.665, Episode_length: 200.000±27.572\n", ++ "Rollout 1242/9766, Reward: 287.945±17.969, Episode_length: 213.600±25.216\n", ++ "Rollout 1243/9766, Reward: 279.233±13.477, Episode_length: 200.500±20.235\n", ++ "Rollout 1244/9766, Reward: 282.709±13.718, Episode_length: 188.600±17.310\n", ++ "Rollout 1245/9766, Reward: 280.216±19.143, Episode_length: 187.600±23.913\n", ++ "Rollout 1246/9766, Reward: 292.980±11.982, Episode_length: 210.500±19.459\n", ++ "Rollout 1247/9766, Reward: 285.622±17.397, Episode_length: 212.100±25.762\n", ++ "Rollout 1248/9766, Reward: 265.844±23.950, Episode_length: 231.700±56.267\n", ++ "Rollout 1249/9766, Reward: 285.467±25.096, Episode_length: 208.400±29.581\n", ++ "Rollout 1250/9766, Reward: 278.187±20.662, Episode_length: 247.300±153.857\n", ++ "Rollout 1251/9766, Reward: 270.363±15.167, Episode_length: 193.600±25.267\n", ++ "Rollout 1252/9766, Reward: 268.588±34.421, Episode_length: 275.200±242.924\n", ++ "Rollout 1253/9766, Reward: 272.388±35.432, Episode_length: 277.500±241.514\n", ++ "Rollout 1254/9766, Reward: 287.096±14.337, Episode_length: 195.100±22.528\n", ++ "Rollout 1255/9766, Reward: 290.907±12.922, Episode_length: 203.200±22.485\n", ++ "Rollout 1256/9766, Reward: 282.515±17.499, Episode_length: 194.400±18.832\n", ++ "Rollout 1257/9766, Reward: 284.279±9.819, Episode_length: 217.200±24.041\n", ++ "Rollout 1258/9766, Reward: 278.186±15.197, Episode_length: 206.000±22.122\n", ++ "Rollout 1259/9766, Reward: 267.205±13.180, Episode_length: 207.500±22.232\n", ++ "Rollout 1260/9766, Reward: 259.603±35.871, Episode_length: 281.800±241.150\n", ++ "Rollout 1261/9766, Reward: 282.558±10.289, Episode_length: 217.900±33.789\n", ++ "Rollout 1262/9766, Reward: 273.005±18.295, Episode_length: 213.700±31.065\n", ++ "Rollout 1263/9766, Reward: 283.675±17.673, Episode_length: 228.700±30.858\n", ++ "Rollout 1264/9766, Reward: 278.959±10.350, Episode_length: 208.700±19.591\n", ++ "Rollout 1265/9766, Reward: 278.592±21.412, Episode_length: 256.400±147.556\n", ++ "Rollout 1266/9766, Reward: 247.256±48.553, Episode_length: 436.200±315.142\n", ++ "Rollout 1267/9766, Reward: 272.963±37.555, Episode_length: 292.900±236.712\n", ++ "Rollout 1268/9766, Reward: 272.412±10.190, Episode_length: 191.600±15.519\n", ++ "Rollout 1269/9766, Reward: 271.805±21.476, Episode_length: 195.600±15.292\n", ++ "Rollout 1270/9766, Reward: 149.515±48.684, Episode_length: 942.700±171.900\n", ++ "Rollout 1271/9766, Reward: 192.822±56.597, Episode_length: 654.100±313.256\n", ++ "Rollout 1272/9766, Reward: 218.882±54.658, Episode_length: 552.300±299.448\n", ++ "Rollout 1273/9766, Reward: 200.117±47.310, Episode_length: 603.800±328.525\n", ++ "Rollout 1274/9766, Reward: 206.275±67.430, Episode_length: 546.100±304.949\n", ++ "Rollout 1275/9766, Reward: 167.235±51.416, Episode_length: 922.400±219.474\n", ++ "Rollout 1276/9766, Reward: 262.996±43.160, Episode_length: 330.600±240.129\n", ++ "Rollout 1277/9766, Reward: 179.499±61.785, Episode_length: 789.400±275.755\n", ++ "Rollout 1278/9766, Reward: 272.210±18.068, Episode_length: 197.700±24.298\n", ++ "Rollout 1279/9766, Reward: 276.411±18.713, Episode_length: 201.000±28.681\n", ++ "Rollout 1280/9766, Reward: 274.080±17.148, Episode_length: 198.600±18.661\n", ++ "Rollout 1281/9766, Reward: 267.416±37.156, Episode_length: 277.000±241.608\n", ++ "Rollout 1282/9766, Reward: 280.979±11.206, Episode_length: 203.700±27.037\n", ++ "Rollout 1283/9766, Reward: 141.915±380.691, Episode_length: 184.900±32.843\n", ++ "Rollout 1284/9766, Reward: 254.855±36.151, Episode_length: 287.200±238.781\n", ++ "Rollout 1285/9766, Reward: 278.307±14.801, Episode_length: 211.300±15.950\n", ++ "Rollout 1286/9766, Reward: 277.809±18.816, Episode_length: 207.700±25.487\n", ++ "Rollout 1287/9766, Reward: 275.434±15.171, Episode_length: 215.400±34.662\n", ++ "Rollout 1288/9766, Reward: 239.680±57.899, Episode_length: 515.600±380.911\n", ++ "Rollout 1289/9766, Reward: 251.795±46.501, Episode_length: 362.700±319.263\n", ++ "Rollout 1290/9766, Reward: 269.164±30.924, Episode_length: 278.700±241.407\n", ++ "Rollout 1291/9766, Reward: 270.452±21.008, Episode_length: 201.300±19.432\n", ++ "Rollout 1292/9766, Reward: 278.710±20.346, Episode_length: 204.900±22.563\n", ++ "Rollout 1293/9766, Reward: 256.768±44.284, Episode_length: 347.300±301.167\n", ++ "Rollout 1294/9766, Reward: 278.498±23.050, Episode_length: 198.500±23.209\n", ++ "Rollout 1295/9766, Reward: 269.997±39.344, Episode_length: 275.400±242.010\n", ++ "Rollout 1296/9766, Reward: 273.221±15.508, Episode_length: 200.400±19.195\n", ++ "Rollout 1297/9766, Reward: 278.310±13.338, Episode_length: 240.900±142.994\n", ++ "Rollout 1298/9766, Reward: 277.115±27.300, Episode_length: 215.700±52.267\n", ++ "Rollout 1299/9766, Reward: -49.552±454.910, Episode_length: 164.600±66.938\n", ++ "Rollout 1300/9766, Reward: 276.805±16.844, Episode_length: 198.900±19.264\n", ++ "Rollout 1301/9766, Reward: 280.111±19.506, Episode_length: 224.500±27.627\n", ++ "Rollout 1302/9766, Reward: 281.999±16.627, Episode_length: 210.100±13.910\n", ++ "Rollout 1303/9766, Reward: 288.582±9.757, Episode_length: 230.000±16.019\n", ++ "Rollout 1304/9766, Reward: 275.403±16.801, Episode_length: 210.900±21.426\n", ++ "Rollout 1305/9766, Reward: 277.589±21.066, Episode_length: 214.200±28.340\n", ++ "Rollout 1306/9766, Reward: 276.719±24.133, Episode_length: 219.700±58.210\n", ++ "Rollout 1307/9766, Reward: 257.920±48.769, Episode_length: 314.100±239.413\n", ++ "Rollout 1308/9766, Reward: 251.996±72.330, Episode_length: 272.000±244.008\n", ++ "Rollout 1309/9766, Reward: 265.594±35.511, Episode_length: 319.000±236.097\n", ++ "Rollout 1310/9766, Reward: 281.708±17.365, Episode_length: 215.500±28.150\n", ++ "Rollout 1311/9766, Reward: 278.628±15.870, Episode_length: 251.400±160.469\n", ++ "Rollout 1312/9766, Reward: 263.086±16.185, Episode_length: 201.900±28.133\n", ++ "Rollout 1313/9766, Reward: 224.394±155.898, Episode_length: 237.400±58.672\n", ++ "Rollout 1314/9766, Reward: 261.251±32.249, Episode_length: 343.400±249.114\n", ++ "Rollout 1315/9766, Reward: 223.880±138.204, Episode_length: 254.100±101.246\n", ++ "Rollout 1316/9766, Reward: 280.540±14.748, Episode_length: 206.300±33.344\n", ++ "Rollout 1317/9766, Reward: 270.241±13.857, Episode_length: 198.900±17.495\n", ++ "Rollout 1318/9766, Reward: 278.234±22.494, Episode_length: 226.300±31.897\n", ++ "Rollout 1319/9766, Reward: 286.787±13.538, Episode_length: 220.800±31.362\n", ++ "Rollout 1320/9766, Reward: 278.049±17.625, Episode_length: 197.800±28.858\n", ++ "Rollout 1321/9766, Reward: 284.775±16.651, Episode_length: 204.000±47.034\n", ++ "Rollout 1322/9766, Reward: 288.402±7.434, Episode_length: 209.800±31.077\n", ++ "Rollout 1323/9766, Reward: 284.461±19.251, Episode_length: 219.700±48.549\n", ++ "Rollout 1324/9766, Reward: 275.741±17.708, Episode_length: 206.200±34.807\n", ++ "Rollout 1325/9766, Reward: 285.896±13.881, Episode_length: 196.200±31.406\n", ++ "Rollout 1326/9766, Reward: 283.423±18.351, Episode_length: 208.300±42.652\n", ++ "Rollout 1327/9766, Reward: 280.417±14.979, Episode_length: 202.800±31.419\n", ++ "Rollout 1328/9766, Reward: 281.577±17.911, Episode_length: 207.000±48.718\n", ++ "Rollout 1329/9766, Reward: 283.400±17.882, Episode_length: 224.000±39.444\n", ++ "Rollout 1330/9766, Reward: 285.281±15.797, Episode_length: 223.500±46.881\n", ++ "Rollout 1331/9766, Reward: 288.478±23.006, Episode_length: 219.700±43.040\n", ++ "Rollout 1332/9766, Reward: 273.677±32.853, Episode_length: 266.500±245.695\n", ++ "Rollout 1333/9766, Reward: 282.210±17.282, Episode_length: 181.900±18.987\n", ++ "Rollout 1334/9766, Reward: 274.746±20.937, Episode_length: 268.300±137.387\n", ++ "Rollout 1335/9766, Reward: 269.414±20.731, Episode_length: 256.000±120.191\n", ++ "Rollout 1336/9766, Reward: 280.713±13.848, Episode_length: 239.200±74.417\n", ++ "Rollout 1337/9766, Reward: 277.358±21.162, Episode_length: 233.000±38.294\n", ++ "Rollout 1338/9766, Reward: 267.585±14.530, Episode_length: 226.800±30.610\n", ++ "Rollout 1339/9766, Reward: 276.684±17.806, Episode_length: 218.400±19.739\n", ++ "Rollout 1340/9766, Reward: 286.031±16.358, Episode_length: 230.000±30.486\n", ++ "Rollout 1341/9766, Reward: 268.567±19.441, Episode_length: 217.800±20.856\n", ++ "Rollout 1342/9766, Reward: 270.795±23.089, Episode_length: 215.500±16.132\n", ++ "Rollout 1343/9766, Reward: 280.656±19.113, Episode_length: 224.700±22.253\n", ++ "Rollout 1344/9766, Reward: 272.896±17.239, Episode_length: 216.500±28.963\n", ++ "Rollout 1345/9766, Reward: 283.852±11.478, Episode_length: 228.300±38.053\n", ++ "Rollout 1346/9766, Reward: 284.734±15.269, Episode_length: 209.300±30.932\n", ++ "Rollout 1347/9766, Reward: 293.729±15.228, Episode_length: 225.600±32.466\n", ++ "Rollout 1348/9766, Reward: 266.107±55.003, Episode_length: 379.700±310.862\n", ++ "Rollout 1349/9766, Reward: 225.731±50.806, Episode_length: 600.700±393.032\n", ++ "Rollout 1350/9766, Reward: 277.588±19.901, Episode_length: 206.500±26.039\n", ++ "Rollout 1351/9766, Reward: 282.726±17.799, Episode_length: 222.100±24.615\n", ++ "Rollout 1352/9766, Reward: 270.593±11.742, Episode_length: 203.400±17.217\n", ++ "Rollout 1353/9766, Reward: 287.376±14.872, Episode_length: 236.200±35.558\n", ++ "Rollout 1354/9766, Reward: 205.113±211.340, Episode_length: 200.800±41.679\n", ++ "Rollout 1355/9766, Reward: 279.981±14.689, Episode_length: 206.500±26.341\n", ++ "Rollout 1356/9766, Reward: 222.053±175.249, Episode_length: 220.800±42.126\n", ++ "Rollout 1357/9766, Reward: 287.549±15.344, Episode_length: 205.000±32.370\n", ++ "Rollout 1358/9766, Reward: 275.554±17.395, Episode_length: 193.900±20.408\n", ++ "Rollout 1359/9766, Reward: 283.764±11.812, Episode_length: 213.800±31.160\n", ++ "Rollout 1360/9766, Reward: 268.160±36.893, Episode_length: 283.600±240.065\n", ++ "Rollout 1361/9766, Reward: 275.208±19.462, Episode_length: 196.000±34.860\n", ++ "Rollout 1362/9766, Reward: 271.485±20.832, Episode_length: 191.500±25.715\n", ++ "Rollout 1363/9766, Reward: 280.511±19.397, Episode_length: 184.200±32.062\n", ++ "Rollout 1364/9766, Reward: 66.971±621.389, Episode_length: 191.700±33.903\n", ++ "Rollout 1365/9766, Reward: 60.003±650.245, Episode_length: 196.300±13.521\n", ++ "Rollout 1366/9766, Reward: 287.299±14.055, Episode_length: 197.600±36.092\n", ++ "Rollout 1367/9766, Reward: 47.024±673.149, Episode_length: 190.400±23.290\n", ++ "Rollout 1368/9766, Reward: 276.372±15.737, Episode_length: 191.700±21.043\n", ++ "Rollout 1369/9766, Reward: 284.841±13.786, Episode_length: 210.000±27.878\n", ++ "Rollout 1370/9766, Reward: 281.240±21.642, Episode_length: 208.900±25.816\n", ++ "Rollout 1371/9766, Reward: 283.262±18.639, Episode_length: 208.900±27.190\n", ++ "Rollout 1372/9766, Reward: -143.940±624.209, Episode_length: 602.500±398.175\n", ++ "Rollout 1373/9766, Reward: 276.200±19.040, Episode_length: 197.800±26.427\n", ++ "Rollout 1374/9766, Reward: -201.414±858.499, Episode_length: 288.800±238.006\n", ++ "Rollout 1375/9766, Reward: 270.517±13.721, Episode_length: 195.800±18.702\n", ++ "Rollout 1376/9766, Reward: 280.018±11.617, Episode_length: 244.600±100.137\n", ++ "Rollout 1377/9766, Reward: 272.634±15.053, Episode_length: 198.900±24.857\n", ++ "Rollout 1378/9766, Reward: 87.884±599.167, Episode_length: 227.900±22.954\n", ++ "Rollout 1379/9766, Reward: 55.634±653.820, Episode_length: 264.400±162.487\n", ++ "Rollout 1380/9766, Reward: 54.313±685.986, Episode_length: 209.600±25.275\n", ++ "Rollout 1381/9766, Reward: 270.998±15.022, Episode_length: 207.400±23.303\n", ++ "Rollout 1382/9766, Reward: 284.437±12.820, Episode_length: 203.000±39.661\n", ++ "Rollout 1383/9766, Reward: 280.903±7.409, Episode_length: 218.100±33.774\n", ++ "Rollout 1384/9766, Reward: 38.671±676.074, Episode_length: 295.200±185.010\n", ++ "Rollout 1385/9766, Reward: 248.046±47.887, Episode_length: 292.600±237.681\n", ++ "Rollout 1386/9766, Reward: -133.749±824.423, Episode_length: 235.800±42.209\n", ++ "Rollout 1387/9766, Reward: -279.924±847.080, Episode_length: 264.300±240.858\n", ++ "Rollout 1388/9766, Reward: 242.137±58.883, Episode_length: 434.300±346.451\n", ++ "Rollout 1389/9766, Reward: -100.886±700.751, Episode_length: 262.600±246.642\n", ++ "Rollout 1390/9766, Reward: 243.304±58.617, Episode_length: 456.400±358.928\n", ++ "Rollout 1391/9766, Reward: 11.770±743.894, Episode_length: 342.800±230.969\n", ++ "Rollout 1392/9766, Reward: 114.431±506.914, Episode_length: 200.400±28.524\n", ++ "Rollout 1393/9766, Reward: 256.864±60.018, Episode_length: 473.700±320.545\n", ++ "Rollout 1394/9766, Reward: 257.549±41.199, Episode_length: 288.000±238.995\n", ++ "Rollout 1395/9766, Reward: 263.131±18.049, Episode_length: 203.400±28.486\n", ++ "Rollout 1396/9766, Reward: 238.879±62.291, Episode_length: 439.600±367.679\n", ++ "Rollout 1397/9766, Reward: 143.997±404.970, Episode_length: 187.500±25.212\n", ++ "Rollout 1398/9766, Reward: 295.747±13.235, Episode_length: 217.900±20.516\n", ++ "Rollout 1399/9766, Reward: 245.698±59.467, Episode_length: 429.900±373.779\n", ++ "Rollout 1400/9766, Reward: 272.423±50.323, Episode_length: 292.000±239.079\n", ++ "Rollout 1401/9766, Reward: 279.885±14.118, Episode_length: 207.200±19.395\n", ++ "Rollout 1402/9766, Reward: 279.125±17.147, Episode_length: 193.800±21.757\n", ++ "Rollout 1403/9766, Reward: 280.394±21.267, Episode_length: 198.300±29.014\n", ++ "Rollout 1404/9766, Reward: 280.129±22.952, Episode_length: 199.900±24.765\n", ++ "Rollout 1405/9766, Reward: 279.587±21.632, Episode_length: 202.100±34.474\n", ++ "Rollout 1406/9766, Reward: 278.818±15.200, Episode_length: 205.900±29.955\n", ++ "Rollout 1407/9766, Reward: 261.995±30.659, Episode_length: 266.200±245.074\n", ++ "Rollout 1408/9766, Reward: 288.428±22.331, Episode_length: 213.600±27.284\n", ++ "Rollout 1409/9766, Reward: 268.611±35.617, Episode_length: 269.400±244.065\n", ++ "Rollout 1410/9766, Reward: 280.645±14.938, Episode_length: 192.600±20.776\n", ++ "Rollout 1411/9766, Reward: 285.413±21.292, Episode_length: 205.400±22.606\n", ++ "Rollout 1412/9766, Reward: 286.230±15.817, Episode_length: 199.800±23.159\n", ++ "Rollout 1413/9766, Reward: 280.953±15.902, Episode_length: 261.300±210.821\n", ++ "Rollout 1414/9766, Reward: 273.586±35.035, Episode_length: 272.800±243.268\n", ++ "Rollout 1415/9766, Reward: 277.402±16.094, Episode_length: 193.100±29.757\n", ++ "Rollout 1416/9766, Reward: 288.525±10.427, Episode_length: 192.500±32.352\n", ++ "Rollout 1417/9766, Reward: 275.343±18.090, Episode_length: 207.700±44.061\n", ++ "Rollout 1418/9766, Reward: 276.034±17.466, Episode_length: 183.800±14.013\n", ++ "Rollout 1419/9766, Reward: 293.960±13.784, Episode_length: 287.100±179.036\n", ++ "Rollout 1420/9766, Reward: 286.743±12.041, Episode_length: 208.200±20.880\n", ++ "Rollout 1421/9766, Reward: 278.281±14.958, Episode_length: 191.500±25.939\n", ++ "Rollout 1422/9766, Reward: 290.757±26.095, Episode_length: 203.900±33.744\n", ++ "Rollout 1423/9766, Reward: 286.853±16.091, Episode_length: 200.700±28.277\n", ++ "Rollout 1424/9766, Reward: 286.433±21.544, Episode_length: 206.900±44.212\n", ++ "Rollout 1425/9766, Reward: 279.930±10.466, Episode_length: 207.500±27.016\n", ++ "Rollout 1426/9766, Reward: 239.326±146.465, Episode_length: 222.100±30.121\n", ++ "Rollout 1427/9766, Reward: 287.545±15.233, Episode_length: 205.300±27.576\n", ++ "Rollout 1428/9766, Reward: 284.389±14.373, Episode_length: 207.000±24.896\n", ++ "Rollout 1429/9766, Reward: 273.836±15.800, Episode_length: 201.300±17.309\n", ++ "Rollout 1430/9766, Reward: 273.502±15.633, Episode_length: 201.100±22.801\n", ++ "Rollout 1431/9766, Reward: 279.770±19.866, Episode_length: 208.800±28.572\n", ++ "Rollout 1432/9766, Reward: 232.774±147.531, Episode_length: 200.700±33.565\n", ++ "Rollout 1433/9766, Reward: 274.764±14.923, Episode_length: 199.300±26.276\n", ++ "Rollout 1434/9766, Reward: 288.644±15.043, Episode_length: 210.800±20.658\n", ++ "Rollout 1435/9766, Reward: 278.115±18.267, Episode_length: 202.500±30.017\n", ++ "Rollout 1436/9766, Reward: 278.443±16.497, Episode_length: 206.100±20.734\n", ++ "Rollout 1437/9766, Reward: 276.958±17.318, Episode_length: 196.000±14.853\n", ++ "Rollout 1438/9766, Reward: 278.417±10.896, Episode_length: 195.000±36.940\n", ++ "Rollout 1439/9766, Reward: 285.818±11.605, Episode_length: 202.500±24.529\n", ++ "Rollout 1440/9766, Reward: 276.130±17.799, Episode_length: 204.900±22.133\n", ++ "Rollout 1441/9766, Reward: 278.847±15.344, Episode_length: 221.000±37.916\n", ++ "Rollout 1442/9766, Reward: 281.216±16.065, Episode_length: 218.000±67.192\n", ++ "Rollout 1443/9766, Reward: 288.427±15.298, Episode_length: 222.900±28.811\n", ++ "Rollout 1444/9766, Reward: 279.062±14.803, Episode_length: 214.600±32.119\n", ++ "Rollout 1445/9766, Reward: 273.076±20.942, Episode_length: 211.500±24.772\n", ++ "Rollout 1446/9766, Reward: 279.379±16.231, Episode_length: 207.600±21.322\n", ++ "Rollout 1447/9766, Reward: 277.433±17.558, Episode_length: 225.100±43.066\n", ++ "Rollout 1448/9766, Reward: 267.646±12.647, Episode_length: 202.600±29.756\n", ++ "Rollout 1449/9766, Reward: 272.086±21.292, Episode_length: 213.200±29.526\n", ++ "Rollout 1450/9766, Reward: 268.885±43.872, Episode_length: 291.400±237.777\n", ++ "Rollout 1451/9766, Reward: 275.178±20.907, Episode_length: 205.200±29.103\n", ++ "Rollout 1452/9766, Reward: 282.963±18.987, Episode_length: 216.100±23.856\n", ++ "Rollout 1453/9766, Reward: 286.719±18.555, Episode_length: 221.400±26.744\n", ++ "Rollout 1454/9766, Reward: 282.118±14.827, Episode_length: 206.300±37.165\n", ++ "Rollout 1455/9766, Reward: 281.855±19.071, Episode_length: 193.300±19.733\n", ++ "Rollout 1456/9766, Reward: 287.053±21.189, Episode_length: 205.000±26.739\n", ++ "Rollout 1457/9766, Reward: 280.987±11.616, Episode_length: 185.100±23.175\n", ++ "Rollout 1458/9766, Reward: 277.113±19.801, Episode_length: 203.000±37.038\n", ++ "Rollout 1459/9766, Reward: 267.773±19.856, Episode_length: 204.600±40.643\n", ++ "Rollout 1460/9766, Reward: 287.388±15.595, Episode_length: 200.100±29.945\n", ++ "Rollout 1461/9766, Reward: 285.036±19.423, Episode_length: 208.200±37.204\n", ++ "Rollout 1462/9766, Reward: 282.414±17.026, Episode_length: 212.300±33.817\n", ++ "Rollout 1463/9766, Reward: 276.861±17.058, Episode_length: 194.600±27.811\n", ++ "Rollout 1464/9766, Reward: 292.077±15.035, Episode_length: 211.400±40.356\n", ++ "Rollout 1465/9766, Reward: 262.890±49.022, Episode_length: 287.100±239.019\n", ++ "Rollout 1466/9766, Reward: 286.438±19.439, Episode_length: 224.800±20.134\n", ++ "Rollout 1467/9766, Reward: 273.703±14.473, Episode_length: 194.500±18.742\n", ++ "Rollout 1468/9766, Reward: 278.410±10.763, Episode_length: 188.300±27.324\n", ++ "Rollout 1469/9766, Reward: 270.859±16.963, Episode_length: 187.100±19.419\n", ++ "Rollout 1470/9766, Reward: 287.954±16.857, Episode_length: 200.300±18.177\n", ++ "Rollout 1471/9766, Reward: 275.488±22.079, Episode_length: 200.000±28.128\n", ++ "Rollout 1472/9766, Reward: 276.437±16.850, Episode_length: 206.700±24.731\n", ++ "Rollout 1473/9766, Reward: 281.120±16.352, Episode_length: 210.500±23.479\n", ++ "Rollout 1474/9766, Reward: 268.248±19.578, Episode_length: 193.400±30.764\n", ++ "Rollout 1475/9766, Reward: 288.626±18.077, Episode_length: 214.600±32.373\n", ++ "Rollout 1476/9766, Reward: 293.132±12.590, Episode_length: 206.300±35.307\n", ++ "Rollout 1477/9766, Reward: 275.006±42.101, Episode_length: 264.800±246.937\n", ++ "Rollout 1478/9766, Reward: 285.814±13.969, Episode_length: 187.200±23.680\n", ++ "Rollout 1479/9766, Reward: 281.402±15.018, Episode_length: 212.900±31.713\n", ++ "Rollout 1480/9766, Reward: 282.546±16.529, Episode_length: 194.400±28.654\n", ++ "Rollout 1481/9766, Reward: 276.800±18.331, Episode_length: 195.500±22.892\n", ++ "Rollout 1482/9766, Reward: 281.657±9.878, Episode_length: 197.700±31.850\n", ++ "Rollout 1483/9766, Reward: 279.522±16.622, Episode_length: 192.800±15.158\n", ++ "Rollout 1484/9766, Reward: 282.963±18.671, Episode_length: 194.200±27.981\n", ++ "Rollout 1485/9766, Reward: 281.149±18.313, Episode_length: 202.300±35.936\n", ++ "Rollout 1486/9766, Reward: 272.299±15.891, Episode_length: 199.400±29.537\n", ++ "Rollout 1487/9766, Reward: 273.473±11.924, Episode_length: 184.700±22.334\n", ++ "Rollout 1488/9766, Reward: 280.715±13.354, Episode_length: 209.900±28.829\n", ++ "Rollout 1489/9766, Reward: 275.833±22.381, Episode_length: 197.400±32.623\n", ++ "Rollout 1490/9766, Reward: 284.538±13.330, Episode_length: 194.700±26.264\n", ++ "Rollout 1491/9766, Reward: 287.598±13.408, Episode_length: 192.100±21.050\n", ++ "Rollout 1492/9766, Reward: 266.036±36.683, Episode_length: 280.000±241.010\n", ++ "Rollout 1493/9766, Reward: 284.414±13.657, Episode_length: 195.200±23.760\n", ++ "Rollout 1494/9766, Reward: 283.055±16.370, Episode_length: 198.500±23.959\n", ++ "Rollout 1495/9766, Reward: 287.645±12.664, Episode_length: 189.800±39.663\n", ++ "Rollout 1496/9766, Reward: 273.838±19.532, Episode_length: 186.100±30.392\n", ++ "Rollout 1497/9766, Reward: 275.783±12.827, Episode_length: 183.500±26.135\n", ++ "Rollout 1498/9766, Reward: 263.879±12.397, Episode_length: 174.800±16.726\n", ++ "Rollout 1499/9766, Reward: 274.172±13.390, Episode_length: 198.300±45.933\n", ++ "Rollout 1500/9766, Reward: 239.599±65.150, Episode_length: 462.200±329.248\n", ++ "Rollout 1501/9766, Reward: 267.821±17.343, Episode_length: 202.200±25.353\n", ++ "Rollout 1502/9766, Reward: 274.976±14.033, Episode_length: 197.600±23.191\n", ++ "Rollout 1503/9766, Reward: 268.582±21.127, Episode_length: 193.100±23.488\n", ++ "Rollout 1504/9766, Reward: 262.363±38.011, Episode_length: 259.500±247.754\n", ++ "Rollout 1505/9766, Reward: 261.264±48.392, Episode_length: 267.400±246.252\n", ++ "Rollout 1506/9766, Reward: 257.720±49.917, Episode_length: 275.700±242.815\n", ++ "Rollout 1507/9766, Reward: 263.506±43.908, Episode_length: 268.600±245.013\n", ++ "Rollout 1508/9766, Reward: 281.392±21.825, Episode_length: 183.200±21.600\n", ++ "Rollout 1509/9766, Reward: 268.578±21.041, Episode_length: 239.800±161.197\n", ++ "Rollout 1510/9766, Reward: 274.883±14.184, Episode_length: 191.400±28.054\n", ++ "Rollout 1511/9766, Reward: 276.498±14.501, Episode_length: 204.100±25.890\n", ++ "Rollout 1512/9766, Reward: 253.899±44.469, Episode_length: 274.000±243.939\n", ++ "Rollout 1513/9766, Reward: 250.153±63.593, Episode_length: 362.200±321.012\n", ++ "Rollout 1514/9766, Reward: 254.537±42.030, Episode_length: 270.300±244.616\n", ++ "Rollout 1515/9766, Reward: 260.612±41.586, Episode_length: 279.100±242.474\n", ++ "Rollout 1516/9766, Reward: 275.092±25.354, Episode_length: 264.500±215.955\n", ++ "Rollout 1517/9766, Reward: 277.718±22.683, Episode_length: 186.800±39.587\n", ++ "Rollout 1518/9766, Reward: 285.606±13.983, Episode_length: 199.700±23.635\n", ++ "Rollout 1519/9766, Reward: 283.476±18.236, Episode_length: 205.400±37.313\n", ++ "Rollout 1520/9766, Reward: 248.356±61.943, Episode_length: 359.000±320.976\n", ++ "Rollout 1521/9766, Reward: 265.212±55.128, Episode_length: 293.200±237.035\n", ++ "Rollout 1522/9766, Reward: 262.568±52.427, Episode_length: 270.900±244.158\n", ++ "Rollout 1523/9766, Reward: 279.150±15.391, Episode_length: 191.500±20.274\n", ++ "Rollout 1524/9766, Reward: 274.463±16.095, Episode_length: 207.600±24.483\n", ++ "Rollout 1525/9766, Reward: 283.168±23.058, Episode_length: 203.800±22.471\n", ++ "Rollout 1526/9766, Reward: 274.397±6.327, Episode_length: 201.900±18.479\n", ++ "Rollout 1527/9766, Reward: 267.830±41.225, Episode_length: 285.000±239.898\n", ++ "Rollout 1528/9766, Reward: 255.589±39.478, Episode_length: 274.200±243.033\n", ++ "Rollout 1529/9766, Reward: 240.210±63.841, Episode_length: 543.700±348.732\n", ++ "Rollout 1530/9766, Reward: 250.812±42.395, Episode_length: 376.500±235.351\n", ++ "Rollout 1531/9766, Reward: 30.798±713.516, Episode_length: 274.900±52.940\n", ++ "Rollout 1532/9766, Reward: 231.343±144.747, Episode_length: 198.800±31.984\n", ++ "Rollout 1533/9766, Reward: 268.290±19.840, Episode_length: 215.600±40.847\n", ++ "Rollout 1534/9766, Reward: 258.440±49.793, Episode_length: 405.700±325.173\n", ++ "Rollout 1535/9766, Reward: 250.457±37.438, Episode_length: 370.500±295.134\n", ++ "Rollout 1536/9766, Reward: 222.861±57.463, Episode_length: 682.300±378.762\n", ++ "Rollout 1537/9766, Reward: 259.217±19.500, Episode_length: 247.400±125.645\n", ++ "Rollout 1538/9766, Reward: 284.200±17.473, Episode_length: 210.700±24.079\n", ++ "Rollout 1539/9766, Reward: 265.452±20.527, Episode_length: 199.000±33.556\n", ++ "Rollout 1540/9766, Reward: 197.499±118.050, Episode_length: 195.000±90.706\n", ++ "Rollout 1541/9766, Reward: 275.185±17.370, Episode_length: 215.500±35.736\n", ++ "Rollout 1542/9766, Reward: 268.349±25.615, Episode_length: 248.900±154.907\n", ++ "Rollout 1543/9766, Reward: 266.648±57.116, Episode_length: 271.200±243.962\n", ++ "Rollout 1544/9766, Reward: 284.957±15.452, Episode_length: 205.300±32.419\n", ++ "Rollout 1545/9766, Reward: 275.828±17.486, Episode_length: 202.200±28.202\n", ++ "Rollout 1546/9766, Reward: 280.467±13.180, Episode_length: 192.200±28.649\n", ++ "Rollout 1547/9766, Reward: 254.743±51.652, Episode_length: 330.500±287.549\n", ++ "Rollout 1548/9766, Reward: 264.630±18.495, Episode_length: 187.500±15.487\n", ++ "Rollout 1549/9766, Reward: 278.682±6.165, Episode_length: 192.400±21.837\n", ++ "Rollout 1550/9766, Reward: 35.382±479.679, Episode_length: 195.100±42.269\n", ++ "Rollout 1551/9766, Reward: 1.658±527.401, Episode_length: 189.000±40.269\n", ++ "Rollout 1552/9766, Reward: 277.800±10.540, Episode_length: 189.300±19.980\n", ++ "Rollout 1553/9766, Reward: 268.021±18.176, Episode_length: 195.700±18.693\n", ++ "Rollout 1554/9766, Reward: 261.848±27.723, Episode_length: 240.500±58.621\n", ++ "Rollout 1555/9766, Reward: 104.250±481.728, Episode_length: 284.900±243.407\n", ++ "Rollout 1556/9766, Reward: 237.261±43.455, Episode_length: 346.700±261.560\n", ++ "Rollout 1557/9766, Reward: 275.140±17.803, Episode_length: 201.700±32.784\n", ++ "Rollout 1558/9766, Reward: 242.452±66.362, Episode_length: 297.900±176.553\n", ++ "Rollout 1559/9766, Reward: 251.157±47.909, Episode_length: 326.400±233.283\n", ++ "Rollout 1560/9766, Reward: 254.181±24.706, Episode_length: 402.900±234.961\n", ++ "Rollout 1561/9766, Reward: 246.043±72.220, Episode_length: 214.900±45.720\n", ++ "Rollout 1562/9766, Reward: 251.910±34.941, Episode_length: 256.200±87.796\n", ++ "Rollout 1563/9766, Reward: 240.952±49.425, Episode_length: 359.000±236.296\n", ++ "Rollout 1564/9766, Reward: 253.237±22.978, Episode_length: 221.100±82.377\n", ++ "Rollout 1565/9766, Reward: 246.496±29.868, Episode_length: 358.300±155.801\n", ++ "Rollout 1566/9766, Reward: 128.691±429.544, Episode_length: 225.700±23.795\n", ++ "Rollout 1567/9766, Reward: 253.797±36.741, Episode_length: 402.900±293.849\n", ++ "Rollout 1568/9766, Reward: 265.539±13.078, Episode_length: 221.200±54.098\n", ++ "Rollout 1569/9766, Reward: 238.468±39.543, Episode_length: 315.000±127.197\n", ++ "Rollout 1570/9766, Reward: 161.529±342.994, Episode_length: 210.600±31.200\n", ++ "Rollout 1571/9766, Reward: 152.511±257.686, Episode_length: 283.500±234.140\n", ++ "Rollout 1572/9766, Reward: 256.904±49.150, Episode_length: 296.800±235.767\n", ++ "Rollout 1573/9766, Reward: 253.638±43.987, Episode_length: 338.700±254.258\n", ++ "Rollout 1574/9766, Reward: 257.327±56.340, Episode_length: 296.800±235.718\n", ++ "Rollout 1575/9766, Reward: 284.921±12.912, Episode_length: 244.600±41.083\n", ++ "Rollout 1576/9766, Reward: 253.305±56.187, Episode_length: 367.800±317.533\n", ++ "Rollout 1577/9766, Reward: 283.985±17.301, Episode_length: 214.600±28.556\n", ++ "Rollout 1578/9766, Reward: 284.977±34.619, Episode_length: 302.000±233.758\n", ++ "Rollout 1579/9766, Reward: 282.787±13.111, Episode_length: 274.900±213.764\n", ++ "Rollout 1580/9766, Reward: 206.681±206.433, Episode_length: 193.100±30.201\n", ++ "Rollout 1581/9766, Reward: 279.125±16.692, Episode_length: 194.800±23.853\n", ++ "Rollout 1582/9766, Reward: 280.687±15.103, Episode_length: 200.400±22.979\n", ++ "Rollout 1583/9766, Reward: 286.318±14.819, Episode_length: 212.000±34.029\n", ++ "Rollout 1584/9766, Reward: 265.865±44.129, Episode_length: 373.800±282.778\n", ++ "Rollout 1585/9766, Reward: 268.383±35.943, Episode_length: 272.400±244.220\n", ++ "Rollout 1586/9766, Reward: 162.010±329.955, Episode_length: 195.300±13.491\n", ++ "Rollout 1587/9766, Reward: 168.119±303.077, Episode_length: 280.900±243.852\n", ++ "Rollout 1588/9766, Reward: 183.076±294.543, Episode_length: 190.800±29.620\n", ++ "Rollout 1589/9766, Reward: 197.889±199.646, Episode_length: 263.200±246.360\n", ++ "Rollout 1590/9766, Reward: 287.381±19.666, Episode_length: 201.000±39.245\n", ++ "Rollout 1591/9766, Reward: 276.451±10.802, Episode_length: 193.600±25.390\n", ++ "Rollout 1592/9766, Reward: 287.737±19.640, Episode_length: 190.100±23.805\n", ++ "Rollout 1593/9766, Reward: 271.898±15.970, Episode_length: 199.300±28.827\n", ++ "Rollout 1594/9766, Reward: 267.525±37.459, Episode_length: 288.500±238.626\n", ++ "Rollout 1595/9766, Reward: 285.305±12.143, Episode_length: 194.300±20.659\n", ++ "Rollout 1596/9766, Reward: 286.374±15.465, Episode_length: 199.600±25.045\n", ++ "Rollout 1597/9766, Reward: 178.103±294.726, Episode_length: 192.200±18.915\n", ++ "Rollout 1598/9766, Reward: 163.697±370.517, Episode_length: 200.500±28.724\n", ++ "Rollout 1599/9766, Reward: 269.331±20.608, Episode_length: 183.000±21.406\n", ++ "Rollout 1600/9766, Reward: 282.302±12.390, Episode_length: 218.600±36.971\n", ++ "Rollout 1601/9766, Reward: 278.457±19.140, Episode_length: 286.200±218.465\n", ++ "Rollout 1602/9766, Reward: 281.680±16.818, Episode_length: 198.600±32.293\n", ++ "Rollout 1603/9766, Reward: 275.197±41.078, Episode_length: 289.400±238.357\n", ++ "Rollout 1604/9766, Reward: 284.124±12.415, Episode_length: 209.000±25.702\n", ++ "Rollout 1605/9766, Reward: 280.787±14.250, Episode_length: 190.900±32.740\n", ++ "Rollout 1606/9766, Reward: 279.924±11.229, Episode_length: 194.900±42.623\n", ++ "Rollout 1607/9766, Reward: 276.914±38.910, Episode_length: 301.300±233.994\n", ++ "Rollout 1608/9766, Reward: 269.341±35.389, Episode_length: 273.000±243.858\n", ++ "Rollout 1609/9766, Reward: 276.117±15.788, Episode_length: 197.400±22.384\n", ++ "Rollout 1610/9766, Reward: 284.780±13.634, Episode_length: 204.500±32.715\n", ++ "Rollout 1611/9766, Reward: 281.372±13.423, Episode_length: 199.600±29.901\n", ++ "Rollout 1612/9766, Reward: 279.358±13.307, Episode_length: 199.900±24.259\n", ++ "Rollout 1613/9766, Reward: 285.575±17.312, Episode_length: 188.200±28.470\n", ++ "Rollout 1614/9766, Reward: 283.014±14.520, Episode_length: 195.900±27.421\n", ++ "Rollout 1615/9766, Reward: 275.101±12.592, Episode_length: 200.900±19.149\n", ++ "Rollout 1616/9766, Reward: 268.395±38.898, Episode_length: 286.600±239.707\n", ++ "Rollout 1617/9766, Reward: 284.984±19.603, Episode_length: 197.000±27.328\n", ++ "Rollout 1618/9766, Reward: 278.864±16.341, Episode_length: 202.200±31.578\n", ++ "Rollout 1619/9766, Reward: 296.532±8.549, Episode_length: 221.600��22.317\n", ++ "Rollout 1620/9766, Reward: 271.878±17.298, Episode_length: 187.600±19.247\n", ++ "Rollout 1621/9766, Reward: 286.042±13.702, Episode_length: 194.600±23.517\n", ++ "Rollout 1622/9766, Reward: 297.965±12.026, Episode_length: 189.100±23.637\n", ++ "Rollout 1623/9766, Reward: 288.878±13.979, Episode_length: 195.500±33.833\n", ++ "Rollout 1624/9766, Reward: 284.090±18.652, Episode_length: 197.100±22.470\n", ++ "Rollout 1625/9766, Reward: 276.849±18.248, Episode_length: 182.800±25.325\n", ++ "Rollout 1626/9766, Reward: 284.882±16.045, Episode_length: 201.100±30.283\n", ++ "Rollout 1627/9766, Reward: 279.338±14.512, Episode_length: 185.700±21.863\n", ++ "Rollout 1628/9766, Reward: 289.610±18.181, Episode_length: 202.800±37.400\n", ++ "Rollout 1629/9766, Reward: 286.917±21.774, Episode_length: 194.100±24.809\n", ++ "Rollout 1630/9766, Reward: 292.988±14.007, Episode_length: 184.900±20.700\n", ++ "Rollout 1631/9766, Reward: 290.644±22.135, Episode_length: 196.500±33.218\n", ++ "Rollout 1632/9766, Reward: 286.308±13.004, Episode_length: 191.700±26.390\n", ++ "Rollout 1633/9766, Reward: 284.789±12.553, Episode_length: 186.800±20.851\n", ++ "Rollout 1634/9766, Reward: 200.383±213.564, Episode_length: 294.000±243.254\n", ++ "Rollout 1635/9766, Reward: -12.936±494.177, Episode_length: 178.800±28.858\n", ++ "Rollout 1636/9766, Reward: 160.476±344.129, Episode_length: 201.300±36.072\n", ++ "Rollout 1637/9766, Reward: 175.671±231.652, Episode_length: 215.300±23.567\n", ++ "Rollout 1638/9766, Reward: 125.511±462.227, Episode_length: 186.500±29.262\n", ++ "Rollout 1639/9766, Reward: 272.485±45.438, Episode_length: 328.900±255.500\n", ++ "Rollout 1640/9766, Reward: 279.572±22.805, Episode_length: 588.700±341.078\n", ++ "Rollout 1641/9766, Reward: 178.060±317.536, Episode_length: 186.200±33.163\n", ++ "Rollout 1642/9766, Reward: 177.643±294.878, Episode_length: 243.600±176.673\n", ++ "Rollout 1643/9766, Reward: 4.468±417.697, Episode_length: 203.300±139.312\n", ++ "Rollout 1644/9766, Reward: 171.637±335.952, Episode_length: 181.000±37.186\n", ++ "Rollout 1645/9766, Reward: 44.458±406.541, Episode_length: 163.000±36.103\n", ++ "Rollout 1646/9766, Reward: 95.182±376.206, Episode_length: 180.100±37.017\n", ++ "Rollout 1647/9766, Reward: 134.184±284.530, Episode_length: 197.200±42.778\n", ++ "Rollout 1648/9766, Reward: 288.549±13.905, Episode_length: 184.400±28.605\n", ++ "Rollout 1649/9766, Reward: 282.915±16.968, Episode_length: 197.700±13.447\n", ++ "Rollout 1650/9766, Reward: 269.552±16.399, Episode_length: 201.800±57.402\n", ++ "Rollout 1651/9766, Reward: 235.231±163.180, Episode_length: 201.900±31.838\n", ++ "Rollout 1652/9766, Reward: 133.636±406.123, Episode_length: 279.400±246.306\n", ++ "Rollout 1653/9766, Reward: 268.705±34.811, Episode_length: 277.900±242.607\n", ++ "Rollout 1654/9766, Reward: 275.148±12.855, Episode_length: 205.400±46.669\n", ++ "Rollout 1655/9766, Reward: 238.268±90.902, Episode_length: 337.400±297.699\n", ++ "Rollout 1656/9766, Reward: 212.674±157.323, Episode_length: 266.700±245.258\n", ++ "Rollout 1657/9766, Reward: 166.149±350.906, Episode_length: 211.800±53.289\n", ++ "Rollout 1658/9766, Reward: 280.042±17.769, Episode_length: 201.300±42.415\n", ++ "Rollout 1659/9766, Reward: 286.128±20.367, Episode_length: 262.700±143.873\n", ++ "Rollout 1660/9766, Reward: 206.468±195.426, Episode_length: 295.000±53.585\n", ++ "Rollout 1661/9766, Reward: 225.491±193.362, Episode_length: 213.000±46.729\n", ++ "Rollout 1662/9766, Reward: -113.555±664.286, Episode_length: 207.400±65.876\n", ++ "Rollout 1663/9766, Reward: 278.731±15.601, Episode_length: 185.100±18.501\n", ++ "Rollout 1664/9766, Reward: 285.472±12.481, Episode_length: 197.800±32.984\n", ++ "Rollout 1665/9766, Reward: 229.864±191.163, Episode_length: 204.300±26.355\n", ++ "Rollout 1666/9766, Reward: 241.779±77.689, Episode_length: 165.200±32.137\n", ++ "Rollout 1667/9766, Reward: 179.088±205.187, Episode_length: 567.900±381.161\n", ++ "Rollout 1668/9766, Reward: 244.982±53.402, Episode_length: 510.500±375.632\n", ++ "Rollout 1669/9766, Reward: 193.843±89.430, Episode_length: 517.400±398.012\n", ++ "Rollout 1670/9766, Reward: 187.204±121.164, Episode_length: 664.500±347.080\n", ++ "Rollout 1671/9766, Reward: 260.715±34.737, Episode_length: 298.200±239.806\n", ++ "Rollout 1672/9766, Reward: 242.138±60.477, Episode_length: 380.500±316.130\n", ++ "Rollout 1673/9766, Reward: 46.001±262.195, Episode_length: 287.500±248.601\n", ++ "Rollout 1674/9766, Reward: 160.838±207.262, Episode_length: 289.000±83.531\n", ++ "Rollout 1675/9766, Reward: -87.307±703.782, Episode_length: 401.000±243.011\n", ++ "Rollout 1676/9766, Reward: 102.384±193.873, Episode_length: 892.500±247.811\n", ++ "Rollout 1677/9766, Reward: -933.045±354.929, Episode_length: 177.500±45.520\n", ++ "Rollout 1678/9766, Reward: -536.081±672.426, Episode_length: 520.800±393.420\n", ++ "Rollout 1679/9766, Reward: -331.748±639.857, Episode_length: 521.100±397.558\n", ++ "Rollout 1680/9766, Reward: -376.139±847.138, Episode_length: 581.000±406.054\n", ++ "Rollout 1681/9766, Reward: -934.569±1180.323, Episode_length: 516.000±361.096\n", ++ "Rollout 1682/9766, Reward: -27.655±346.154, Episode_length: 669.900±382.386\n", ++ "Rollout 1683/9766, Reward: -62.046±311.063, Episode_length: 567.800±412.972\n", ++ "Rollout 1684/9766, Reward: -195.472±743.434, Episode_length: 755.500±373.439\n", ++ "Rollout 1685/9766, Reward: -244.562±629.351, Episode_length: 498.600±351.894\n", ++ "Rollout 1686/9766, Reward: -122.353±574.066, Episode_length: 642.200±367.782\n", ++ "Rollout 1687/9766, Reward: -844.307±856.675, Episode_length: 435.600±371.218\n", ++ "Rollout 1688/9766, Reward: -349.327±758.473, Episode_length: 505.300±366.772\n", ++ "Rollout 1689/9766, Reward: 152.278±158.997, Episode_length: 758.000±338.459\n", ++ "Rollout 1690/9766, Reward: -20.778±460.699, Episode_length: 476.000±335.626\n", ++ "Rollout 1691/9766, Reward: -111.579±447.261, Episode_length: 715.600±384.522\n", ++ "Rollout 1692/9766, Reward: -267.552±427.886, Episode_length: 481.700±423.917\n", ++ "Rollout 1693/9766, Reward: -311.979±697.130, Episode_length: 380.000±331.584\n", ++ "Rollout 1694/9766, Reward: -79.378±448.789, Episode_length: 747.300±369.391\n", ++ "Rollout 1695/9766, Reward: -307.005±522.217, Episode_length: 596.100±404.087\n", ++ "Rollout 1696/9766, Reward: -21.190±500.694, Episode_length: 729.300±332.621\n", ++ "Rollout 1697/9766, Reward: -554.654±501.323, Episode_length: 312.300±257.756\n", ++ "Rollout 1698/9766, Reward: -305.711±512.560, Episode_length: 417.900±315.166\n", ++ "Rollout 1699/9766, Reward: -532.217±728.719, Episode_length: 296.000±185.181\n", ++ "Rollout 1700/9766, Reward: -875.808±285.304, Episode_length: 134.400±20.061\n", ++ "Rollout 1701/9766, Reward: -664.223±231.047, Episode_length: 118.900±28.109\n", ++ "Rollout 1702/9766, Reward: -735.445±658.798, Episode_length: 248.100±174.895\n", ++ "Rollout 1703/9766, Reward: -1234.563±835.357, Episode_length: 279.300±157.043\n", ++ "Rollout 1704/9766, Reward: -1802.891±692.910, Episode_length: 322.800±174.446\n", ++ "Rollout 1705/9766, Reward: -1441.757±951.166, Episode_length: 402.500±301.046\n", ++ "Rollout 1706/9766, Reward: -1164.466±1117.237, Episode_length: 555.400±350.021\n", ++ "Rollout 1707/9766, Reward: -963.509±1124.279, Episode_length: 642.400±357.675\n", ++ "Rollout 1708/9766, Reward: -1560.807±897.064, Episode_length: 333.800±225.401\n", ++ "Rollout 1709/9766, Reward: -1410.172±1119.068, Episode_length: 251.600±40.704\n", ++ "Rollout 1710/9766, Reward: -228.654±884.240, Episode_length: 663.000±369.991\n", ++ "Rollout 1711/9766, Reward: -282.988±878.593, Episode_length: 784.600±331.748\n", ++ "Rollout 1712/9766, Reward: -516.410±894.590, Episode_length: 636.200±353.795\n", ++ "Rollout 1713/9766, Reward: -242.438±802.459, Episode_length: 266.100±60.566\n", ++ "Rollout 1714/9766, Reward: 266.619±32.441, Episode_length: 260.800±82.640\n", ++ "Rollout 1715/9766, Reward: 242.375±51.782, Episode_length: 412.200±255.139\n", ++ "Rollout 1716/9766, Reward: 277.812±12.982, Episode_length: 264.400±80.599\n", ++ "Rollout 1717/9766, Reward: 273.464±34.183, Episode_length: 260.500±87.603\n", ++ "Rollout 1718/9766, Reward: 275.948±29.446, Episode_length: 249.700±66.558\n", ++ "Rollout 1719/9766, Reward: 255.109±40.271, Episode_length: 396.100±290.932\n", ++ "Rollout 1720/9766, Reward: 260.927±41.973, Episode_length: 322.200±233.331\n", ++ "Rollout 1721/9766, Reward: 224.903±58.188, Episode_length: 698.700±341.987\n", ++ "Rollout 1722/9766, Reward: 236.924±78.140, Episode_length: 327.700±236.580\n", ++ "Rollout 1723/9766, Reward: 256.339±56.059, Episode_length: 315.400±239.668\n", ++ "Rollout 1724/9766, Reward: 214.842±65.933, Episode_length: 588.800±364.946\n", ++ "Rollout 1725/9766, Reward: 277.426±37.401, Episode_length: 355.300±307.954\n", ++ "Rollout 1726/9766, Reward: 264.320±50.841, Episode_length: 293.200±242.487\n", ++ "Rollout 1727/9766, Reward: 253.421±67.882, Episode_length: 193.000±16.667\n", ++ "Rollout 1728/9766, Reward: 247.243±58.184, Episode_length: 358.600±321.222\n", ++ "Rollout 1729/9766, Reward: 259.129±78.867, Episode_length: 191.300±25.338\n", ++ "Rollout 1730/9766, Reward: 270.432±14.164, Episode_length: 206.000±29.930\n", ++ "Rollout 1731/9766, Reward: 278.749±12.781, Episode_length: 210.100±43.115\n", ++ "Rollout 1732/9766, Reward: 281.677±22.109, Episode_length: 207.700±33.779\n", ++ "Rollout 1733/9766, Reward: 271.966±20.257, Episode_length: 202.000±18.719\n", ++ "Rollout 1734/9766, Reward: 275.573±14.840, Episode_length: 192.100±32.070\n", ++ "Rollout 1735/9766, Reward: 288.669±19.173, Episode_length: 215.900±36.035\n", ++ "Rollout 1736/9766, Reward: 288.049±14.498, Episode_length: 218.900±29.012\n", ++ "Rollout 1737/9766, Reward: 278.190±22.055, Episode_length: 202.700±29.903\n", ++ "Rollout 1738/9766, Reward: 288.772±16.236, Episode_length: 197.400±20.269\n", ++ "Rollout 1739/9766, Reward: 261.330±45.504, Episode_length: 377.000±312.364\n", ++ "Rollout 1740/9766, Reward: 283.967±18.744, Episode_length: 204.800±23.693\n", ++ "Rollout 1741/9766, Reward: 276.265±13.377, Episode_length: 195.000±15.007\n", ++ "Rollout 1742/9766, Reward: 290.510±16.522, Episode_length: 209.800±29.711\n", ++ "Rollout 1743/9766, Reward: 287.790±19.459, Episode_length: 209.300±20.460\n", ++ "Rollout 1744/9766, Reward: 224.385±47.066, Episode_length: 519.100±392.941\n", ++ "Rollout 1745/9766, Reward: 280.166±21.751, Episode_length: 204.500±20.675\n", ++ "Rollout 1746/9766, Reward: 283.513±14.120, Episode_length: 222.900±34.712\n", ++ "Rollout 1747/9766, Reward: 265.012±31.889, Episode_length: 274.500±242.594\n", ++ "Rollout 1748/9766, Reward: 215.324±59.778, Episode_length: 884.000±227.823\n", ++ "Rollout 1749/9766, Reward: 273.259±18.560, Episode_length: 217.000±30.146\n", ++ "Rollout 1750/9766, Reward: 283.675±12.565, Episode_length: 220.600±31.187\n", ++ "Rollout 1751/9766, Reward: 273.297±18.781, Episode_length: 204.900±22.709\n", ++ "Rollout 1752/9766, Reward: 280.077±19.541, Episode_length: 204.900±28.953\n", ++ "Rollout 1753/9766, Reward: 290.142±15.605, Episode_length: 224.500±26.364\n", ++ "Rollout 1754/9766, Reward: 271.828±21.787, Episode_length: 211.800±30.093\n", ++ "Rollout 1755/9766, Reward: 266.472±35.970, Episode_length: 293.800±237.664\n", ++ "Rollout 1756/9766, Reward: 278.143±20.513, Episode_length: 201.300±23.333\n", ++ "Rollout 1757/9766, Reward: 292.125±20.293, Episode_length: 224.700±21.527\n", ++ "Rollout 1758/9766, Reward: 285.824±9.492, Episode_length: 284.000±237.920\n", ++ "Rollout 1759/9766, Reward: 280.006±19.272, Episode_length: 208.400±16.584\n", ++ "Rollout 1760/9766, Reward: 284.059±16.798, Episode_length: 190.900±18.190\n", ++ "Rollout 1761/9766, Reward: 292.238±20.666, Episode_length: 201.700±21.057\n", ++ "Rollout 1762/9766, Reward: 288.513±20.019, Episode_length: 201.100±33.032\n", ++ "Rollout 1763/9766, Reward: 218.947±182.087, Episode_length: 209.800±32.621\n", ++ "Rollout 1764/9766, Reward: 286.720±12.891, Episode_length: 198.000±20.928\n", ++ "Rollout 1765/9766, Reward: 294.991±12.913, Episode_length: 190.100±41.327\n", ++ "Rollout 1766/9766, Reward: 284.018±17.360, Episode_length: 193.800±18.600\n", ++ "Rollout 1767/9766, Reward: 284.551±17.985, Episode_length: 213.400±41.675\n", ++ "Rollout 1768/9766, Reward: 281.536±16.704, Episode_length: 203.100±27.388\n", ++ "Rollout 1769/9766, Reward: 278.735±16.646, Episode_length: 193.400±14.921\n", ++ "Rollout 1770/9766, Reward: 272.195±24.456, Episode_length: 265.900±207.947\n", ++ "Rollout 1771/9766, Reward: 278.881±21.358, Episode_length: 190.400±16.566\n", ++ "Rollout 1772/9766, Reward: 285.932±14.032, Episode_length: 222.800±22.117\n", ++ "Rollout 1773/9766, Reward: 282.993±23.815, Episode_length: 207.000±30.143\n", ++ "Rollout 1774/9766, Reward: 296.846±15.019, Episode_length: 201.200±14.689\n", ++ "Rollout 1775/9766, Reward: 288.504±10.771, Episode_length: 208.400±25.421\n", ++ "Rollout 1776/9766, Reward: 289.495±19.252, Episode_length: 203.100±23.497\n", ++ "Rollout 1777/9766, Reward: 277.683±21.361, Episode_length: 207.300±27.137\n", ++ "Rollout 1778/9766, Reward: 289.814±16.402, Episode_length: 204.000±30.387\n", ++ "Rollout 1779/9766, Reward: 253.686±50.252, Episode_length: 440.200±367.179\n", ++ "Rollout 1780/9766, Reward: 282.692±22.221, Episode_length: 208.500±28.518\n", ++ "Rollout 1781/9766, Reward: 283.576±18.773, Episode_length: 192.600±27.299\n", ++ "Rollout 1782/9766, Reward: 288.520±13.310, Episode_length: 206.300±23.719\n", ++ "Rollout 1783/9766, Reward: 275.628±47.736, Episode_length: 282.600±240.446\n", ++ "Rollout 1784/9766, Reward: 218.791±193.143, Episode_length: 204.500±22.250\n", ++ "Rollout 1785/9766, Reward: 266.176±13.235, Episode_length: 203.700±25.259\n", ++ "Rollout 1786/9766, Reward: 264.779±43.329, Episode_length: 279.500±241.361\n", ++ "Rollout 1787/9766, Reward: 287.990±19.476, Episode_length: 203.700±16.444\n", ++ "Rollout 1788/9766, Reward: 259.607±38.973, Episode_length: 260.700±247.076\n", ++ "Rollout 1789/9766, Reward: 278.141±19.998, Episode_length: 267.200±180.860\n", ++ "Rollout 1790/9766, Reward: -68.858��676.208, Episode_length: 187.500±32.448\n", ++ "Rollout 1791/9766, Reward: 129.474±440.887, Episode_length: 204.600±47.032\n", ++ "Rollout 1792/9766, Reward: 270.615±17.523, Episode_length: 259.100±177.735\n", ++ "Rollout 1793/9766, Reward: 202.560±212.814, Episode_length: 257.500±190.133\n", ++ "Rollout 1794/9766, Reward: 168.933±174.468, Episode_length: 334.100±145.919\n", ++ "Rollout 1795/9766, Reward: 194.711±146.675, Episode_length: 261.600±153.095\n", ++ "Rollout 1796/9766, Reward: 195.775±187.852, Episode_length: 267.200±247.787\n", ++ "Rollout 1797/9766, Reward: 253.067±55.661, Episode_length: 281.600±241.447\n", ++ "Rollout 1798/9766, Reward: 280.439±23.133, Episode_length: 221.000±60.410\n", ++ "Rollout 1799/9766, Reward: 273.081±36.863, Episode_length: 355.300±283.621\n", ++ "Rollout 1800/9766, Reward: 280.880±10.634, Episode_length: 203.000±37.108\n", ++ "Rollout 1801/9766, Reward: 273.704±15.655, Episode_length: 198.500±28.514\n", ++ "Rollout 1802/9766, Reward: 284.369±17.972, Episode_length: 220.200±31.106\n", ++ "Rollout 1803/9766, Reward: 289.908±14.888, Episode_length: 214.100±57.479\n", ++ "Rollout 1804/9766, Reward: 275.964±39.684, Episode_length: 281.100±240.763\n", ++ "Rollout 1805/9766, Reward: 271.954±37.178, Episode_length: 296.100±239.758\n", ++ "Rollout 1806/9766, Reward: 267.359±32.327, Episode_length: 303.500±259.308\n", ++ "Rollout 1807/9766, Reward: 280.872±15.921, Episode_length: 199.600±22.606\n", ++ "Rollout 1808/9766, Reward: 288.494±10.907, Episode_length: 204.700±17.878\n", ++ "Rollout 1809/9766, Reward: 282.653±12.749, Episode_length: 207.300±27.745\n", ++ "Rollout 1810/9766, Reward: 277.051±13.712, Episode_length: 197.800±23.396\n", ++ "Rollout 1811/9766, Reward: 278.059±14.063, Episode_length: 199.400±35.973\n", ++ "Rollout 1812/9766, Reward: 293.021±12.389, Episode_length: 224.000±91.077\n", ++ "Rollout 1813/9766, Reward: 271.177±17.821, Episode_length: 296.200±207.757\n", ++ "Rollout 1814/9766, Reward: 231.001±55.742, Episode_length: 428.200±374.514\n", ++ "Rollout 1815/9766, Reward: 280.545±12.469, Episode_length: 207.900±56.408\n", ++ "Rollout 1816/9766, Reward: 277.843±16.889, Episode_length: 232.900±150.886\n", ++ "Rollout 1817/9766, Reward: 282.046±19.148, Episode_length: 195.000±26.359\n", ++ "Rollout 1818/9766, Reward: 285.235±11.814, Episode_length: 188.600±24.134\n", ++ "Rollout 1819/9766, Reward: 271.657±18.663, Episode_length: 182.500±13.147\n", ++ "Rollout 1820/9766, Reward: 289.803±19.862, Episode_length: 195.000±19.829\n", ++ "Rollout 1821/9766, Reward: 269.298±42.181, Episode_length: 331.400±272.044\n", ++ "Rollout 1822/9766, Reward: 284.208±16.661, Episode_length: 191.900±17.236\n", ++ "Rollout 1823/9766, Reward: 286.428±21.698, Episode_length: 208.700±21.744\n", ++ "Rollout 1824/9766, Reward: 280.976±14.201, Episode_length: 191.600±20.524\n", ++ "Rollout 1825/9766, Reward: 273.968±33.459, Episode_length: 290.000±238.121\n", ++ "Rollout 1826/9766, Reward: 288.409±15.348, Episode_length: 210.400±26.945\n", ++ "Rollout 1827/9766, Reward: 283.643±21.795, Episode_length: 198.900±29.754\n", ++ "Rollout 1828/9766, Reward: 284.710±22.766, Episode_length: 210.900±43.592\n", ++ "Rollout 1829/9766, Reward: 219.147±190.735, Episode_length: 209.300±35.341\n", ++ "Rollout 1830/9766, Reward: 241.729±44.814, Episode_length: 510.100±400.497\n", ++ "Rollout 1831/9766, Reward: 186.867±37.988, Episode_length: 985.500±43.500\n", ++ "Rollout 1832/9766, Reward: 176.056±28.098, Episode_length: 998.400±4.800\n", ++ "Rollout 1833/9766, Reward: 250.107±60.832, Episode_length: 488.300±371.002\n", ++ "Rollout 1834/9766, Reward: 272.147±18.992, Episode_length: 176.900±15.789\n", ++ "Rollout 1835/9766, Reward: 274.236±36.380, Episode_length: 271.700±243.739\n", ++ "Rollout 1836/9766, Reward: 279.754±15.777, Episode_length: 184.400±21.731\n", ++ "Rollout 1837/9766, Reward: 284.158±14.343, Episode_length: 186.500±25.664\n", ++ "Rollout 1838/9766, Reward: 284.894±18.506, Episode_length: 190.800±19.390\n", ++ "Rollout 1839/9766, Reward: 255.452±39.557, Episode_length: 340.100±330.353\n", ++ "Rollout 1840/9766, Reward: 277.445±15.872, Episode_length: 185.000±21.218\n", ++ "Rollout 1841/9766, Reward: 275.585±10.674, Episode_length: 181.900±13.693\n", ++ "Rollout 1842/9766, Reward: 277.802±10.707, Episode_length: 202.600±70.447\n", ++ "Rollout 1843/9766, Reward: 287.332±18.385, Episode_length: 178.800±23.769\n", ++ "Rollout 1844/9766, Reward: 288.257±17.029, Episode_length: 194.000±15.073\n", ++ "Rollout 1845/9766, Reward: 285.166±19.779, Episode_length: 177.200±19.894\n", ++ "Rollout 1846/9766, Reward: 276.613±14.203, Episode_length: 177.500±18.178\n", ++ "Rollout 1847/9766, Reward: 282.013±15.972, Episode_length: 184.900±27.530\n", ++ "Rollout 1848/9766, Reward: 282.343±13.648, Episode_length: 175.100±14.604\n", ++ "Rollout 1849/9766, Reward: 276.008±18.795, Episode_length: 221.500±105.712\n", ++ "Rollout 1850/9766, Reward: 279.993±16.929, Episode_length: 179.200±22.396\n", ++ "Rollout 1851/9766, Reward: 286.086±18.862, Episode_length: 182.300±21.024\n", ++ "Rollout 1852/9766, Reward: 287.147±12.939, Episode_length: 217.800±106.676\n", ++ "Rollout 1853/9766, Reward: 286.231±15.836, Episode_length: 178.700±20.377\n", ++ "Rollout 1854/9766, Reward: 260.370±84.151, Episode_length: 184.200±31.789\n", ++ "Rollout 1855/9766, Reward: 277.201±23.645, Episode_length: 189.200±17.713\n", ++ "Rollout 1856/9766, Reward: 292.795±22.244, Episode_length: 196.400±22.074\n", ++ "Rollout 1857/9766, Reward: 285.307±12.086, Episode_length: 185.300±23.074\n", ++ "Rollout 1858/9766, Reward: 278.785±18.472, Episode_length: 184.200±20.980\n", ++ "Rollout 1859/9766, Reward: 287.209±21.660, Episode_length: 187.500±18.800\n", ++ "Rollout 1860/9766, Reward: 262.286±17.361, Episode_length: 427.400±107.649\n", ++ "Rollout 1861/9766, Reward: 198.663±51.428, Episode_length: 863.400±251.800\n", ++ "Rollout 1862/9766, Reward: 244.899±72.620, Episode_length: 254.100±250.812\n", ++ "Rollout 1863/9766, Reward: 173.030±42.451, Episode_length: 977.900±66.300\n", ++ "Rollout 1864/9766, Reward: 209.637±41.050, Episode_length: 669.700±404.565\n", ++ "Rollout 1865/9766, Reward: 229.360±55.054, Episode_length: 687.500±349.540\n", ++ "Rollout 1866/9766, Reward: 241.747±46.374, Episode_length: 486.000±391.466\n", ++ "Rollout 1867/9766, Reward: 154.413±21.793, Episode_length: 1000.000±0.000\n", ++ "Rollout 1868/9766, Reward: 175.838±52.026, Episode_length: 852.900±294.516\n", ++ "Rollout 1869/9766, Reward: 136.660±53.472, Episode_length: 908.200±275.400\n", ++ "Rollout 1870/9766, Reward: 194.821±71.270, Episode_length: 707.100±361.950\n", ++ "Rollout 1871/9766, Reward: 181.017±49.441, Episode_length: 884.700±231.576\n", ++ "Rollout 1872/9766, Reward: 163.617±43.194, Episode_length: 916.500±250.500\n", ++ "Rollout 1873/9766, Reward: 147.778±15.064, Episode_length: 1000.000±0.000\n", ++ "Rollout 1874/9766, Reward: -50.467±371.165, Episode_length: 844.500±311.000\n", ++ "Rollout 1875/9766, Reward: -52.651±263.889, Episode_length: 566.900±436.168\n", ++ "Rollout 1876/9766, Reward: 153.555±49.665, Episode_length: 922.700±231.900\n", ++ "Rollout 1877/9766, Reward: 129.617±15.756, Episode_length: 1000.000±0.000\n", ++ "Rollout 1878/9766, Reward: -98.104±529.957, Episode_length: 784.000±331.362\n", ++ "Rollout 1879/9766, Reward: -79.955±467.153, Episode_length: 844.900±310.250\n", ++ "Rollout 1880/9766, Reward: 171.413±34.787, Episode_length: 928.100±215.700\n", ++ "Rollout 1881/9766, Reward: 245.521±63.260, Episode_length: 512.100±338.866\n", ++ "Rollout 1882/9766, Reward: 259.708±45.823, Episode_length: 356.200±323.626\n", ++ "Rollout 1883/9766, Reward: 261.173±46.800, Episode_length: 322.000±232.561\n", ++ "Rollout 1884/9766, Reward: 292.453±12.827, Episode_length: 233.100±75.840\n", ++ "Rollout 1885/9766, Reward: 284.120±10.988, Episode_length: 194.800±19.964\n", ++ "Rollout 1886/9766, Reward: 265.714±38.088, Episode_length: 293.600±237.645\n", ++ "Rollout 1887/9766, Reward: 275.546±17.124, Episode_length: 183.700±12.506\n", ++ "Rollout 1888/9766, Reward: 269.002±33.592, Episode_length: 265.900±245.412\n", ++ "Rollout 1889/9766, Reward: 214.435±62.155, Episode_length: 757.800±366.901\n", ++ "Rollout 1890/9766, Reward: 250.615±50.422, Episode_length: 537.400±369.404\n", ++ "Rollout 1891/9766, Reward: 168.623±46.928, Episode_length: 917.300±248.100\n", ++ "Rollout 1892/9766, Reward: 148.504±15.754, Episode_length: 1000.000±0.000\n", ++ "Rollout 1893/9766, Reward: 184.605±42.042, Episode_length: 921.200±236.400\n", ++ "Rollout 1894/9766, Reward: 186.693±46.837, Episode_length: 833.900±332.222\n", ++ "Rollout 1895/9766, Reward: 253.408±57.879, Episode_length: 351.300±324.906\n", ++ "Rollout 1896/9766, Reward: 271.344±16.745, Episode_length: 183.400±17.048\n", ++ "Rollout 1897/9766, Reward: 267.010±35.089, Episode_length: 322.400±290.501\n", ++ "Rollout 1898/9766, Reward: 288.204±14.269, Episode_length: 184.300±20.572\n", ++ "Rollout 1899/9766, Reward: 242.008±54.320, Episode_length: 595.800±404.464\n", ++ "Rollout 1900/9766, Reward: 245.030±56.052, Episode_length: 511.100±399.617\n", ++ "Rollout 1901/9766, Reward: 201.422±69.984, Episode_length: 693.500±375.609\n", ++ "Rollout 1902/9766, Reward: 173.120±53.513, Episode_length: 846.700±306.847\n", ++ "Rollout 1903/9766, Reward: 169.424±59.065, Episode_length: 844.900±310.229\n", ++ "Rollout 1904/9766, Reward: 242.391±56.675, Episode_length: 479.100±381.825\n", ++ "Rollout 1905/9766, Reward: 268.347±30.980, Episode_length: 295.100±268.831\n", ++ "Rollout 1906/9766, Reward: 287.523±18.804, Episode_length: 225.800±88.018\n", ++ "Rollout 1907/9766, Reward: 293.275±8.835, Episode_length: 207.100±22.165\n", ++ "Rollout 1908/9766, Reward: 280.561±19.872, Episode_length: 174.700±22.235\n", ++ "Rollout 1909/9766, Reward: 292.419±14.798, Episode_length: 191.100±25.762\n", ++ "Rollout 1910/9766, Reward: 283.035±45.367, Episode_length: 275.600±242.740\n", ++ "Rollout 1911/9766, Reward: 267.969±38.365, Episode_length: 274.900±246.911\n", ++ "Rollout 1912/9766, Reward: 284.276±29.470, Episode_length: 197.500±44.619\n", ++ "Rollout 1913/9766, Reward: 284.967±19.658, Episode_length: 268.700±180.049\n", ++ "Rollout 1914/9766, Reward: 280.180±18.299, Episode_length: 237.400±179.928\n", ++ "Rollout 1915/9766, Reward: 269.998±17.203, Episode_length: 250.700±213.213\n", ++ "Rollout 1916/9766, Reward: 259.138±48.104, Episode_length: 447.900±358.698\n", ++ "Rollout 1917/9766, Reward: 200.194±56.061, Episode_length: 851.000±296.056\n", ++ "Rollout 1918/9766, Reward: 260.697±13.238, Episode_length: 338.800±35.085\n", ++ "Rollout 1919/9766, Reward: 173.040±45.555, Episode_length: 994.300±17.100\n", ++ "Rollout 1920/9766, Reward: 229.509±65.589, Episode_length: 513.100±397.646\n", ++ "Rollout 1921/9766, Reward: 260.529±43.646, Episode_length: 265.900±245.610\n", ++ "Rollout 1922/9766, Reward: 276.249±22.722, Episode_length: 176.800±27.279\n", ++ "Rollout 1923/9766, Reward: 285.912±15.814, Episode_length: 267.200±170.026\n", ++ "Rollout 1924/9766, Reward: 276.851±37.685, Episode_length: 356.900±321.651\n", ++ "Rollout 1925/9766, Reward: 259.751±42.920, Episode_length: 357.600±322.067\n", ++ "Rollout 1926/9766, Reward: 255.103±60.284, Episode_length: 432.600±371.968\n", ++ "Rollout 1927/9766, Reward: 272.965±22.324, Episode_length: 229.600±146.198\n", ++ "Rollout 1928/9766, Reward: 291.346±16.491, Episode_length: 190.100±28.055\n", ++ "Rollout 1929/9766, Reward: 278.263±21.848, Episode_length: 183.100±40.582\n", ++ "Rollout 1930/9766, Reward: 283.630±18.508, Episode_length: 187.500±35.739\n", ++ "Rollout 1931/9766, Reward: 281.954±12.308, Episode_length: 181.800±32.618\n", ++ "Rollout 1932/9766, Reward: 280.443±13.983, Episode_length: 186.600±38.934\n", ++ "Rollout 1933/9766, Reward: 267.683±53.496, Episode_length: 284.900±241.386\n", ++ "Rollout 1934/9766, Reward: 281.531±22.608, Episode_length: 241.700±144.154\n", ++ "Rollout 1935/9766, Reward: 268.721±47.791, Episode_length: 285.300±241.429\n", ++ "Rollout 1936/9766, Reward: 279.719±15.111, Episode_length: 182.400±18.001\n", ++ "Rollout 1937/9766, Reward: 290.005±11.990, Episode_length: 194.900±31.904\n", ++ "Rollout 1938/9766, Reward: 287.869±10.523, Episode_length: 190.800±24.628\n", ++ "Rollout 1939/9766, Reward: 289.601±14.446, Episode_length: 198.300±31.834\n", ++ "Rollout 1940/9766, Reward: 214.883±197.197, Episode_length: 183.300±23.491\n", ++ "Rollout 1941/9766, Reward: 280.823±22.778, Episode_length: 184.400±18.233\n", ++ "Rollout 1942/9766, Reward: 286.101±18.934, Episode_length: 186.600±22.069\n", ++ "Rollout 1943/9766, Reward: 274.265±13.479, Episode_length: 166.200±24.572\n", ++ "Rollout 1944/9766, Reward: 291.851±21.244, Episode_length: 199.000±25.585\n", ++ "Rollout 1945/9766, Reward: 273.307±39.139, Episode_length: 262.600±247.712\n", ++ "Rollout 1946/9766, Reward: 281.239±16.013, Episode_length: 209.800±102.647\n", ++ "Rollout 1947/9766, Reward: 283.883±19.531, Episode_length: 193.000±29.268\n", ++ "Rollout 1948/9766, Reward: 275.823±17.330, Episode_length: 188.100±20.844\n", ++ "Rollout 1949/9766, Reward: 271.623±30.597, Episode_length: 274.200±242.565\n", ++ "Rollout 1950/9766, Reward: 274.496±36.053, Episode_length: 269.800±244.801\n", ++ "Rollout 1951/9766, Reward: 269.519±21.591, Episode_length: 191.800±25.965\n", ++ "Rollout 1952/9766, Reward: 236.404±106.447, Episode_length: 191.100±58.911\n", ++ "Rollout 1953/9766, Reward: 275.474±13.443, Episode_length: 210.300±43.088\n", ++ "Rollout 1954/9766, Reward: 260.850±40.898, Episode_length: 261.400±246.618\n", ++ "Rollout 1955/9766, Reward: 276.871±34.862, Episode_length: 328.500±287.807\n", ++ "Rollout 1956/9766, Reward: 289.618±17.340, Episode_length: 215.900±48.451\n", ++ "Rollout 1957/9766, Reward: 280.323±14.423, Episode_length: 193.800±28.017\n", ++ "Rollout 1958/9766, Reward: 292.879±13.304, Episode_length: 184.100±22.066\n", ++ "Rollout 1959/9766, Reward: 283.349±18.877, Episode_length: 183.000±21.545\n", ++ "Rollout 1960/9766, Reward: 282.775±16.097, Episode_length: 188.800±28.944\n", ++ "Rollout 1961/9766, Reward: 274.024±40.046, Episode_length: 268.100±244.843\n", ++ "Rollout 1962/9766, Reward: 286.780±16.197, Episode_length: 183.400±27.861\n", ++ "Rollout 1963/9766, Reward: 287.556±18.288, Episode_length: 186.400±18.139\n", ++ "Rollout 1964/9766, Reward: 283.343±11.807, Episode_length: 231.600±152.699\n", ++ "Rollout 1965/9766, Reward: 273.986±20.662, Episode_length: 181.500±34.532\n", ++ "Rollout 1966/9766, Reward: 281.812±19.046, Episode_length: 192.300±33.320\n", ++ "Rollout 1967/9766, Reward: 271.567±34.568, Episode_length: 261.700±246.997\n", ++ "Rollout 1968/9766, Reward: 268.022±31.961, Episode_length: 264.800±245.624\n", ++ "Rollout 1969/9766, Reward: 264.999±31.672, Episode_length: 253.200±249.300\n", ++ "Rollout 1970/9766, Reward: 285.052±19.608, Episode_length: 175.200±21.867\n", ++ "Rollout 1971/9766, Reward: 279.931±10.363, Episode_length: 189.300±14.846\n", ++ "Rollout 1972/9766, Reward: 284.901±21.171, Episode_length: 190.800±22.657\n", ++ "Rollout 1973/9766, Reward: 282.587±21.803, Episode_length: 186.900±26.894\n", ++ "Rollout 1974/9766, Reward: 271.193±31.292, Episode_length: 272.700±243.955\n", ++ "Rollout 1975/9766, Reward: 244.369±61.669, Episode_length: 427.800±375.325\n", ++ "Rollout 1976/9766, Reward: 269.816±19.620, Episode_length: 183.700±21.726\n", ++ "Rollout 1977/9766, Reward: 261.100±40.292, Episode_length: 268.600±245.023\n", ++ "Rollout 1978/9766, Reward: 275.932±41.104, Episode_length: 272.700±243.652\n", ++ "Rollout 1979/9766, Reward: 256.695±50.373, Episode_length: 342.000±329.466\n", ++ "Rollout 1980/9766, Reward: 276.301±15.830, Episode_length: 188.000±16.242\n", ++ "Rollout 1981/9766, Reward: 287.744±13.862, Episode_length: 268.700±194.448\n", ++ "Rollout 1982/9766, Reward: 270.893±37.765, Episode_length: 317.500±272.270\n", ++ "Rollout 1983/9766, Reward: 234.099±50.381, Episode_length: 422.300±378.604\n", ++ "Rollout 1984/9766, Reward: 273.788±16.625, Episode_length: 187.700±26.325\n", ++ "Rollout 1985/9766, Reward: 265.168±38.546, Episode_length: 273.400±243.640\n", ++ "Rollout 1986/9766, Reward: 244.781±48.373, Episode_length: 354.400±323.675\n", ++ "Rollout 1987/9766, Reward: 273.965±36.127, Episode_length: 261.600±246.598\n", ++ "Rollout 1988/9766, Reward: 275.097±11.224, Episode_length: 374.700±189.165\n", ++ "Rollout 1989/9766, Reward: 241.371±49.645, Episode_length: 431.000±373.246\n", ++ "Rollout 1990/9766, Reward: 226.900±93.231, Episode_length: 178.200±19.864\n", ++ "Rollout 1991/9766, Reward: 265.328±18.381, Episode_length: 232.300±138.988\n", ++ "Rollout 1992/9766, Reward: 227.822±69.607, Episode_length: 387.100±332.575\n", ++ "Rollout 1993/9766, Reward: 286.867±13.715, Episode_length: 191.200±19.297\n", ++ "Rollout 1994/9766, Reward: 250.325±56.051, Episode_length: 346.900±328.430\n", ++ "Rollout 1995/9766, Reward: 286.636±13.802, Episode_length: 197.800±19.874\n", ++ "Rollout 1996/9766, Reward: 259.164±38.547, Episode_length: 281.800±241.238\n", ++ "Rollout 1997/9766, Reward: 259.760±47.545, Episode_length: 354.400±323.420\n", ++ "Rollout 1998/9766, Reward: 280.882±16.805, Episode_length: 206.500±46.697\n", ++ "Rollout 1999/9766, Reward: 252.611±73.353, Episode_length: 200.700±28.986\n", ++ "Rollout 2000/9766, Reward: 290.768±13.297, Episode_length: 242.900±157.974\n", ++ "Rollout 2001/9766, Reward: 282.067±21.663, Episode_length: 177.100±20.191\n", ++ "Rollout 2002/9766, Reward: 284.255±21.860, Episode_length: 191.100±23.981\n", ++ "Rollout 2003/9766, Reward: 275.176±14.112, Episode_length: 178.000±16.852\n", ++ "Rollout 2004/9766, Reward: 281.022±19.339, Episode_length: 189.300±24.920\n", ++ "Rollout 2005/9766, Reward: 274.013±40.452, Episode_length: 264.800±245.609\n", ++ "Rollout 2006/9766, Reward: 290.908±10.765, Episode_length: 189.100±11.175\n", ++ "Rollout 2007/9766, Reward: 292.384±14.227, Episode_length: 196.800±24.453\n", ++ "Rollout 2008/9766, Reward: 284.319±14.766, Episode_length: 169.400±17.744\n", ++ "Rollout 2009/9766, Reward: 285.027±20.389, Episode_length: 266.800±239.430\n", ++ "Rollout 2010/9766, Reward: 297.927±9.152, Episode_length: 200.800±15.012\n", ++ "Rollout 2011/9766, Reward: 287.257±14.480, Episode_length: 192.000±24.593\n", ++ "Rollout 2012/9766, Reward: 281.685±21.073, Episode_length: 190.800±20.434\n", ++ "Rollout 2013/9766, Reward: 275.077±25.319, Episode_length: 191.700±55.254\n", ++ "Rollout 2014/9766, Reward: 279.548±21.453, Episode_length: 257.900±219.283\n", ++ "Rollout 2015/9766, Reward: 283.500±13.469, Episode_length: 192.900±26.901\n", ++ "Rollout 2016/9766, Reward: 272.823±18.361, Episode_length: 183.000±18.820\n", ++ "Rollout 2017/9766, Reward: 259.360±48.962, Episode_length: 273.400±243.286\n", ++ "Rollout 2018/9766, Reward: 268.943±15.604, Episode_length: 189.200±17.882\n", ++ "Rollout 2019/9766, Reward: 275.775±14.409, Episode_length: 198.600±30.991\n", ++ "Rollout 2020/9766, Reward: 244.416±40.764, Episode_length: 261.200±247.278\n", ++ "Rollout 2021/9766, Reward: -85.786±984.626, Episode_length: 434.200±341.843\n", ++ "Rollout 2022/9766, Reward: -26.969±902.976, Episode_length: 283.800±202.529\n", ++ "Rollout 2023/9766, Reward: 277.985±14.271, Episode_length: 213.700±81.384\n", ++ "Rollout 2024/9766, Reward: 243.286±52.599, Episode_length: 357.600±322.213\n", ++ "Rollout 2025/9766, Reward: 273.002±17.173, Episode_length: 210.900±29.673\n", ++ "Rollout 2026/9766, Reward: 256.153±37.834, Episode_length: 393.900±319.274\n", ++ "Rollout 2027/9766, Reward: 270.137±34.520, Episode_length: 320.700±267.504\n", ++ "Rollout 2028/9766, Reward: 286.216±10.047, Episode_length: 187.300±16.692\n", ++ "Rollout 2029/9766, Reward: 254.526±42.856, Episode_length: 393.000±328.868\n", ++ "Rollout 2030/9766, Reward: 272.288±39.523, Episode_length: 316.900±249.443\n", ++ "Rollout 2031/9766, Reward: 240.975±62.108, Episode_length: 512.800±398.273\n", ++ "Rollout 2032/9766, Reward: -416.426±1346.712, Episode_length: 454.600±349.967\n", ++ "Rollout 2033/9766, Reward: 242.332±55.463, Episode_length: 434.500±371.064\n", ++ "Rollout 2034/9766, Reward: 253.930±44.679, Episode_length: 350.800±325.743\n", ++ "Rollout 2035/9766, Reward: 235.942±57.139, Episode_length: 560.500±390.729\n", ++ "Rollout 2036/9766, Reward: -136.179±1109.415, Episode_length: 517.100±377.881\n", ++ "Rollout 2037/9766, Reward: -726.993±1514.210, Episode_length: 426.100±305.397\n", ++ "Rollout 2038/9766, Reward: -1730.204±1852.232, Episode_length: 439.500±249.273\n", ++ "Rollout 2039/9766, Reward: -178.063±468.220, Episode_length: 204.700±169.554\n", ++ "Rollout 2040/9766, Reward: -2.822±448.095, Episode_length: 183.500±72.385\n", ++ "Rollout 2041/9766, Reward: 94.058±364.390, Episode_length: 182.600±68.974\n", ++ "Rollout 2042/9766, Reward: 21.003±382.827, Episode_length: 287.900±291.592\n", ++ "Rollout 2043/9766, Reward: -1.928±426.592, Episode_length: 221.700±175.329\n", ++ "Rollout 2044/9766, Reward: 28.184±397.086, Episode_length: 160.900±49.365\n", ++ "Rollout 2045/9766, Reward: -46.589±350.571, Episode_length: 402.700±393.017\n", ++ "Rollout 2046/9766, Reward: 83.899±336.903, Episode_length: 497.600±371.294\n", ++ "Rollout 2047/9766, Reward: 19.679±348.291, Episode_length: 399.700±372.697\n", ++ "Rollout 2048/9766, Reward: 40.695±322.609, Episode_length: 481.300±396.527\n", ++ "Rollout 2049/9766, Reward: -57.175±407.347, Episode_length: 485.300±421.871\n", ++ "Rollout 2050/9766, Reward: 96.897±338.025, Episode_length: 248.600±254.136\n", ++ "Rollout 2051/9766, Reward: -335.451±644.767, Episode_length: 155.100±42.583\n", ++ "Rollout 2052/9766, Reward: -34.321±490.547, Episode_length: 161.800±36.381\n", ++ "Rollout 2053/9766, Reward: -169.164±435.820, Episode_length: 138.500±46.592\n", ++ "Rollout 2054/9766, Reward: -56.594±492.030, Episode_length: 246.900±252.347\n", ++ "Rollout 2055/9766, Reward: -29.935±362.327, Episode_length: 171.200±124.402\n", ++ "Rollout 2056/9766, Reward: 177.837±262.078, Episode_length: 258.200±249.290\n", ++ "Rollout 2057/9766, Reward: -214.214±480.637, Episode_length: 247.100±256.779\n", ++ "Rollout 2058/9766, Reward: 119.383±312.514, Episode_length: 183.200±38.112\n", ++ "Rollout 2059/9766, Reward: -163.477±462.373, Episode_length: 143.400±41.967\n", ++ "Rollout 2060/9766, Reward: -57.439±430.364, Episode_length: 172.200±63.149\n", ++ "Rollout 2061/9766, Reward: 255.254±43.530, Episode_length: 269.500±243.944\n", ++ "Rollout 2062/9766, Reward: 165.495±237.046, Episode_length: 379.400±311.196\n", ++ "Rollout 2063/9766, Reward: 237.654±33.337, Episode_length: 305.700±239.208\n", ++ "Rollout 2064/9766, Reward: 128.926±256.100, Episode_length: 243.200±90.129\n", ++ "Rollout 2065/9766, Reward: 185.829±204.253, Episode_length: 349.500±222.102\n", ++ "Rollout 2066/9766, Reward: 259.240±20.274, Episode_length: 235.600±55.283\n", ++ "Rollout 2067/9766, Reward: 257.506±24.200, Episode_length: 196.200±29.755\n", ++ "Rollout 2068/9766, Reward: 246.938±38.262, Episode_length: 340.200±280.751\n", ++ "Rollout 2069/9766, Reward: 256.976±18.515, Episode_length: 211.000±56.572\n", ++ "Rollout 2070/9766, Reward: 230.493±45.957, Episode_length: 345.700±327.629\n", ++ "Rollout 2071/9766, Reward: 225.327±63.209, Episode_length: 464.800±354.313\n", ++ "Rollout 2072/9766, Reward: 270.652±17.323, Episode_length: 208.900±46.410\n", ++ "Rollout 2073/9766, Reward: 266.200±37.095, Episode_length: 263.300±246.438\n", ++ "Rollout 2074/9766, Reward: 273.914±16.800, Episode_length: 192.700±22.244\n", ++ "Rollout 2075/9766, Reward: 240.561±78.250, Episode_length: 299.600±246.147\n", ++ "Rollout 2076/9766, Reward: 275.741±25.057, Episode_length: 211.500±36.006\n", ++ "Rollout 2077/9766, Reward: 244.863±55.269, Episode_length: 400.300±327.571\n", ++ "Rollout 2078/9766, Reward: 261.555±47.432, Episode_length: 361.600±319.686\n", ++ "Rollout 2079/9766, Reward: 281.206±14.335, Episode_length: 214.700±28.253\n", ++ "Rollout 2080/9766, Reward: 262.275±34.113, Episode_length: 276.400±241.787\n", ++ "Rollout 2081/9766, Reward: 258.763±38.728, Episode_length: 274.800±242.149\n", ++ "Rollout 2082/9766, Reward: 250.087±43.612, Episode_length: 469.100±293.042\n", ++ "Rollout 2083/9766, Reward: 270.317±40.073, Episode_length: 282.400±239.963\n", ++ "Rollout 2084/9766, Reward: 251.474±49.600, Episode_length: 323.700±237.296\n", ++ "Rollout 2085/9766, Reward: 266.810±16.934, Episode_length: 210.200±10.186\n", ++ "Rollout 2086/9766, Reward: 253.904±35.844, Episode_length: 336.600±229.408\n", ++ "Rollout 2087/9766, Reward: 267.650±18.728, Episode_length: 202.500±19.916\n", ++ "Rollout 2088/9766, Reward: 289.003±18.352, Episode_length: 220.000±33.097\n", ++ "Rollout 2089/9766, Reward: 280.269±20.954, Episode_length: 195.000±17.367\n", ++ "Rollout 2090/9766, Reward: 275.070±36.496, Episode_length: 287.700±238.852\n", ++ "Rollout 2091/9766, Reward: 273.466±35.493, Episode_length: 271.900±243.097\n", ++ "Rollout 2092/9766, Reward: 267.496±38.655, Episode_length: 276.500±244.576\n", ++ "Rollout 2093/9766, Reward: 279.226±15.457, Episode_length: 224.600±58.150\n", ++ "Rollout 2094/9766, Reward: 268.427±12.162, Episode_length: 194.200±23.583\n", ++ "Rollout 2095/9766, Reward: 271.805±26.506, Episode_length: 251.800±186.192\n", ++ "Rollout 2096/9766, Reward: 284.098±16.465, Episode_length: 214.300±76.020\n", ++ "Rollout 2097/9766, Reward: 268.286±20.202, Episode_length: 190.200±25.155\n", ++ "Rollout 2098/9766, Reward: 286.179±19.688, Episode_length: 186.000±33.278\n", ++ "Rollout 2099/9766, Reward: 283.087±15.085, Episode_length: 245.600±105.507\n", ++ "Rollout 2100/9766, Reward: 269.243±43.133, Episode_length: 287.100±238.621\n", ++ "Rollout 2101/9766, Reward: 278.591±25.735, Episode_length: 200.800±35.617\n", ++ "Rollout 2102/9766, Reward: 261.897±16.039, Episode_length: 263.700±217.958\n", ++ "Rollout 2103/9766, Reward: 263.353±86.214, Episode_length: 193.900±40.397\n", ++ "Rollout 2104/9766, Reward: 279.521±14.892, Episode_length: 203.900±28.770\n", ++ "Rollout 2105/9766, Reward: 282.949±12.863, Episode_length: 227.500±52.235\n", ++ "Rollout 2106/9766, Reward: 268.122±19.860, Episode_length: 258.500±195.382\n", ++ "Rollout 2107/9766, Reward: 273.671±19.589, Episode_length: 214.200±42.033\n", ++ "Rollout 2108/9766, Reward: 276.497±39.735, Episode_length: 293.800±236.453\n", ++ "Rollout 2109/9766, Reward: 267.113±41.670, Episode_length: 280.900±241.213\n", ++ "Rollout 2110/9766, Reward: 252.064±50.275, Episode_length: 359.100±321.191\n", ++ "Rollout 2111/9766, Reward: 284.603±19.663, Episode_length: 199.300±27.828\n", ++ "Rollout 2112/9766, Reward: 276.530±19.319, Episode_length: 201.600±30.569\n", ++ "Rollout 2113/9766, Reward: 288.616±8.402, Episode_length: 206.400±33.744\n", ++ "Rollout 2114/9766, Reward: 278.162±19.937, Episode_length: 250.400±144.645\n", ++ "Rollout 2115/9766, Reward: 278.527±16.209, Episode_length: 187.500±27.266\n", ++ "Rollout 2116/9766, Reward: 277.577±15.350, Episode_length: 204.400±29.729\n", ++ "Rollout 2117/9766, Reward: 265.181±34.469, Episode_length: 278.900±241.784\n", ++ "Rollout 2118/9766, Reward: 276.097±15.297, Episode_length: 257.100±137.221\n", ++ "Rollout 2119/9766, Reward: 283.098±18.635, Episode_length: 219.600±39.208\n", ++ "Rollout 2120/9766, Reward: 284.446±15.401, Episode_length: 199.000±54.831\n", ++ "Rollout 2121/9766, Reward: 254.789±37.400, Episode_length: 456.700±319.766\n", ++ "Rollout 2122/9766, Reward: 283.516±19.025, Episode_length: 226.500±81.333\n", ++ "Rollout 2123/9766, Reward: 285.271±21.900, Episode_length: 286.300±228.342\n", ++ "Rollout 2124/9766, Reward: 269.530±18.261, Episode_length: 208.800±56.922\n", ++ "Rollout 2125/9766, Reward: 258.993±49.803, Episode_length: 441.900±305.288\n", ++ "Rollout 2126/9766, Reward: 272.035±39.887, Episode_length: 271.400±243.738\n", ++ "Rollout 2127/9766, Reward: 280.069±17.401, Episode_length: 204.000±24.702\n", ++ "Rollout 2128/9766, Reward: 267.808±19.577, Episode_length: 191.000±33.389\n", ++ "Rollout 2129/9766, Reward: 257.088±58.392, Episode_length: 357.700±322.476\n", ++ "Rollout 2130/9766, Reward: 258.162±34.234, Episode_length: 310.500±244.220\n", ++ "Rollout 2131/9766, Reward: 255.737±43.026, Episode_length: 294.200±243.174\n", ++ "Rollout 2132/9766, Reward: 258.145±32.332, Episode_length: 246.900±76.145\n", ++ "Rollout 2133/9766, Reward: 240.392±25.668, Episode_length: 251.000±69.029\n", ++ "Rollout 2134/9766, Reward: 255.994±16.565, Episode_length: 231.200±109.649\n", ++ "Rollout 2135/9766, Reward: 243.714±40.505, Episode_length: 330.800±237.944\n", ++ "Rollout 2136/9766, Reward: 263.436±38.614, Episode_length: 269.600±244.157\n", ++ "Rollout 2137/9766, Reward: 249.922±47.317, Episode_length: 366.600±320.629\n", ++ "Rollout 2138/9766, Reward: 250.363±43.502, Episode_length: 358.200±322.388\n", ++ "Rollout 2139/9766, Reward: 266.628±37.619, Episode_length: 282.800±247.046\n", ++ "Rollout 2140/9766, Reward: 270.333±10.750, Episode_length: 213.400±43.930\n", ++ "Rollout 2141/9766, Reward: 251.908±80.131, Episode_length: 198.700±42.492\n", ++ "Rollout 2142/9766, Reward: 271.644±48.801, Episode_length: 276.600±244.088\n", ++ "Rollout 2143/9766, Reward: 280.963±17.084, Episode_length: 233.100±42.027\n", ++ "Rollout 2144/9766, Reward: 278.793±17.030, Episode_length: 197.300±21.293\n", ++ "Rollout 2145/9766, Reward: 276.234±16.058, Episode_length: 202.100±44.655\n", ++ "Rollout 2146/9766, Reward: 287.525±17.460, Episode_length: 188.400±20.215\n", ++ "Rollout 2147/9766, Reward: 253.618±53.029, Episode_length: 438.700±369.754\n", ++ "Rollout 2148/9766, Reward: 274.925±10.521, Episode_length: 209.400±48.190\n", ++ "Rollout 2149/9766, Reward: 284.841±18.384, Episode_length: 180.700±36.680\n", ++ "Rollout 2150/9766, Reward: 289.330±12.811, Episode_length: 207.100±60.335\n", ++ "Rollout 2151/9766, Reward: 265.718±35.633, Episode_length: 284.600±245.240\n", ++ "Rollout 2152/9766, Reward: 282.132±10.723, Episode_length: 185.500±11.612\n", ++ "Rollout 2153/9766, Reward: 292.636±8.481, Episode_length: 185.000±26.150\n", ++ "Rollout 2154/9766, Reward: 285.018±19.037, Episode_length: 187.700±24.860\n", ++ "Rollout 2155/9766, Reward: 272.197±21.272, Episode_length: 255.500±138.807\n", ++ "Rollout 2156/9766, Reward: 269.210±32.133, Episode_length: 284.100±241.937\n", ++ "Rollout 2157/9766, Reward: 269.124±34.392, Episode_length: 283.900±245.893\n", ++ "Rollout 2158/9766, Reward: 280.476±32.886, Episode_length: 176.000±19.261\n", ++ "Rollout 2159/9766, Reward: 282.946±19.842, Episode_length: 192.200±55.025\n", ++ "Rollout 2160/9766, Reward: 289.910±12.926, Episode_length: 223.700±54.976\n", ++ "Rollout 2161/9766, Reward: 280.015±17.441, Episode_length: 191.200±35.034\n", ++ "Rollout 2162/9766, Reward: 283.026±21.553, Episode_length: 185.800±20.034\n", ++ "Rollout 2163/9766, Reward: 276.756±16.679, Episode_length: 283.800±145.477\n", ++ "Rollout 2164/9766, Reward: 285.850±13.891, Episode_length: 186.400±16.548\n", ++ "Rollout 2165/9766, Reward: 266.752±37.085, Episode_length: 313.200±277.376\n", ++ "Rollout 2166/9766, Reward: 275.659±39.452, Episode_length: 271.500±243.661\n", ++ "Rollout 2167/9766, Reward: 276.655±31.533, Episode_length: 261.700±246.633\n", ++ "Rollout 2168/9766, Reward: 271.510±17.660, Episode_length: 181.300±30.660\n", ++ "Rollout 2169/9766, Reward: 280.687±12.127, Episode_length: 208.100±70.584\n", ++ "Rollout 2170/9766, Reward: 262.628±42.506, Episode_length: 385.700±337.369\n", ++ "Rollout 2171/9766, Reward: 283.411±21.879, Episode_length: 196.400±37.173\n", ++ "Rollout 2172/9766, Reward: 288.340±33.079, Episode_length: 275.800±242.345\n", ++ "Rollout 2173/9766, Reward: 274.063±30.663, Episode_length: 260.800±247.189\n", ++ "Rollout 2174/9766, Reward: 290.246±18.824, Episode_length: 343.900±317.521\n", ++ "Rollout 2175/9766, Reward: 281.980±17.556, Episode_length: 178.100±30.989\n", ++ "Rollout 2176/9766, Reward: 283.400±15.655, Episode_length: 187.000±23.165\n", ++ "Rollout 2177/9766, Reward: 279.748±12.522, Episode_length: 183.900±22.906\n", ++ "Rollout 2178/9766, Reward: 282.627±10.222, Episode_length: 189.600±35.766\n", ++ "Rollout 2179/9766, Reward: 215.206±201.885, Episode_length: 194.700±45.756\n", ++ "Rollout 2180/9766, Reward: 268.228±16.226, Episode_length: 212.600±51.814\n", ++ "Rollout 2181/9766, Reward: 276.203±15.785, Episode_length: 199.100±31.612\n", ++ "Rollout 2182/9766, Reward: 238.349±44.169, Episode_length: 441.300±366.897\n", ++ "Rollout 2183/9766, Reward: 263.169±37.692, Episode_length: 296.800±242.628\n", ++ "Rollout 2184/9766, Reward: 287.760±16.657, Episode_length: 208.600±19.790\n", ++ "Rollout 2185/9766, Reward: 271.810±32.510, Episode_length: 267.600±244.967\n", ++ "Rollout 2186/9766, Reward: 278.129±10.110, Episode_length: 199.300±34.811\n", ++ "Rollout 2187/9766, Reward: 286.707±11.769, Episode_length: 260.600±190.026\n", ++ "Rollout 2188/9766, Reward: 290.396±16.638, Episode_length: 192.600±18.896\n", ++ "Rollout 2189/9766, Reward: 259.153±50.648, Episode_length: 352.200±324.082\n", ++ "Rollout 2190/9766, Reward: 279.246±15.079, Episode_length: 192.700±29.316\n", ++ "Rollout 2191/9766, Reward: 258.032±43.579, Episode_length: 342.700±329.029\n", ++ "Rollout 2192/9766, Reward: 247.424±60.857, Episode_length: 427.200±375.593\n", ++ "Rollout 2193/9766, Reward: 262.565±41.184, Episode_length: 311.000±271.057\n", ++ "Rollout 2194/9766, Reward: 232.299±60.030, Episode_length: 685.500±279.596\n", ++ "Rollout 2195/9766, Reward: 170.324±57.002, Episode_length: 866.500±269.126\n", ++ "Rollout 2196/9766, Reward: 154.340±52.609, Episode_length: 927.500±217.500\n", ++ "Rollout 2197/9766, Reward: 158.558±65.947, Episode_length: 770.700±351.312\n", ++ "Rollout 2198/9766, Reward: 183.251±42.206, Episode_length: 907.000±242.809\n", ++ "Rollout 2199/9766, Reward: 240.143±53.126, Episode_length: 510.500±363.947\n", ++ "Rollout 2200/9766, Reward: 272.650±31.958, Episode_length: 276.300±246.500\n", ++ "Rollout 2201/9766, Reward: 251.632±48.363, Episode_length: 381.500±339.577\n", ++ "Rollout 2202/9766, Reward: 227.840±44.466, Episode_length: 684.700±325.311\n", ++ "Rollout 2203/9766, Reward: 209.250±62.817, Episode_length: 775.500±299.024\n", ++ "Rollout 2204/9766, Reward: 219.843±60.267, Episode_length: 645.000±379.022\n", ++ "Rollout 2205/9766, Reward: 192.772±57.799, Episode_length: 765.100±358.838\n", ++ "Rollout 2206/9766, Reward: 164.559±35.464, Episode_length: 916.500±250.500\n", ++ "Rollout 2207/9766, Reward: 169.865±58.673, Episode_length: 754.300±375.818\n", ++ "Rollout 2208/9766, Reward: 208.501±71.234, Episode_length: 603.600±398.021\n", ++ "Rollout 2209/9766, Reward: 192.989±80.221, Episode_length: 530.900±384.796\n", ++ "Rollout 2210/9766, Reward: 174.946±57.614, Episode_length: 841.600±316.832\n", ++ "Rollout 2211/9766, Reward: 164.703±71.337, Episode_length: 754.400±375.702\n", ++ "Rollout 2212/9766, Reward: 200.259±72.425, Episode_length: 669.200±395.674\n", ++ "Rollout 2213/9766, Reward: 225.576±50.733, Episode_length: 665.800±406.260\n", ++ "Rollout 2214/9766, Reward: 234.820±57.231, Episode_length: 544.700±379.964\n", ++ "Rollout 2215/9766, Reward: 295.453±12.503, Episode_length: 181.200±18.983\n", ++ "Rollout 2216/9766, Reward: 270.296±49.007, Episode_length: 351.200±325.555\n", ++ "Rollout 2217/9766, Reward: 267.409±52.559, Episode_length: 352.800±323.771\n", ++ "Rollout 2218/9766, Reward: 286.865±12.136, Episode_length: 185.600±17.806\n", ++ "Rollout 2219/9766, Reward: 292.395±18.673, Episode_length: 186.800±26.111\n", ++ "Rollout 2220/9766, Reward: 279.931±14.263, Episode_length: 181.600±23.170\n", ++ "Rollout 2221/9766, Reward: 280.263±18.140, Episode_length: 224.700±165.959\n", ++ "Rollout 2222/9766, Reward: 263.069±44.930, Episode_length: 406.600±340.217\n", ++ "Rollout 2223/9766, Reward: 281.938±18.249, Episode_length: 254.400±209.814\n", ++ "Rollout 2224/9766, Reward: 264.561±31.225, Episode_length: 309.900±299.891\n", ++ "Rollout 2225/9766, Reward: 263.874±40.652, Episode_length: 325.400±288.347\n", ++ "Rollout 2226/9766, Reward: 224.374±173.090, Episode_length: 176.200±19.554\n", ++ "Rollout 2227/9766, Reward: 279.221±13.516, Episode_length: 173.900±18.047\n", ++ "Rollout 2228/9766, Reward: 271.336±34.061, Episode_length: 269.000±244.624\n", ++ "Rollout 2229/9766, Reward: 276.075±17.814, Episode_length: 162.200±19.062\n", ++ "Rollout 2230/9766, Reward: 283.484±15.809, Episode_length: 182.200±19.099\n", ++ "Rollout 2231/9766, Reward: 249.446±40.440, Episode_length: 414.900±372.987\n", ++ "Rollout 2232/9766, Reward: 275.890±16.901, Episode_length: 177.800±16.726\n", ++ "Rollout 2233/9766, Reward: 272.705±37.140, Episode_length: 265.800±245.760\n", ++ "Rollout 2234/9766, Reward: 276.885±23.367, Episode_length: 184.200±26.660\n", ++ "Rollout 2235/9766, Reward: 276.012±21.236, Episode_length: 182.900±26.418\n", ++ "Rollout 2236/9766, Reward: 277.683±11.027, Episode_length: 306.900±265.700\n", ++ "Rollout 2237/9766, Reward: 229.877±46.098, Episode_length: 592.800±407.717\n", ++ "Rollout 2238/9766, Reward: 199.280±46.360, Episode_length: 751.900±379.071\n", ++ "Rollout 2239/9766, Reward: 258.673±42.866, Episode_length: 444.900±346.814\n", ++ "Rollout 2240/9766, Reward: 261.386±46.838, Episode_length: 445.800±352.742\n", ++ "Rollout 2241/9766, Reward: 268.729±31.494, Episode_length: 259.900±247.354\n", ++ "Rollout 2242/9766, Reward: 271.689±46.604, Episode_length: 322.400±285.922\n", ++ "Rollout 2243/9766, Reward: 220.137±162.970, Episode_length: 177.800±38.070\n", ++ "Rollout 2244/9766, Reward: 243.474±44.929, Episode_length: 511.900±398.578\n", ++ "Rollout 2245/9766, Reward: 190.690±46.781, Episode_length: 908.200±214.268\n", ++ "Rollout 2246/9766, Reward: 265.835±32.782, Episode_length: 267.300±245.903\n", ++ "Rollout 2247/9766, Reward: 278.548±17.374, Episode_length: 213.800±73.909\n", ++ "Rollout 2248/9766, Reward: 283.992±12.804, Episode_length: 182.500±21.759\n", ++ "Rollout 2249/9766, Reward: 287.620±18.612, Episode_length: 187.700±19.215\n", ++ "Rollout 2250/9766, Reward: 271.403±11.548, Episode_length: 174.900±24.744\n", ++ "Rollout 2251/9766, Reward: 275.098±30.756, Episode_length: 251.500±132.367\n", ++ "Rollout 2252/9766, Reward: 293.996±16.968, Episode_length: 191.000±12.538\n", ++ "Rollout 2253/9766, Reward: 282.206±17.809, Episode_length: 181.300±19.021\n", ++ "Rollout 2254/9766, Reward: 279.633±20.960, Episode_length: 186.600±23.474\n", ++ "Rollout 2255/9766, Reward: 285.550±19.218, Episode_length: 183.700±24.706\n", ++ "Rollout 2256/9766, Reward: 221.612±150.007, Episode_length: 193.500±61.973\n", ++ "Rollout 2257/9766, Reward: 272.346±25.450, Episode_length: 198.600±82.351\n", ++ "Rollout 2258/9766, Reward: 244.138±123.695, Episode_length: 195.500±60.607\n", ++ "Rollout 2259/9766, Reward: 279.827±19.186, Episode_length: 170.300±29.069\n", ++ "Rollout 2260/9766, Reward: 255.590±50.526, Episode_length: 307.300±268.046\n", ++ "Rollout 2261/9766, Reward: 234.102±79.652, Episode_length: 263.100±198.145\n", ++ "Rollout 2262/9766, Reward: 282.748±16.214, Episode_length: 270.300±215.232\n", ++ "Rollout 2263/9766, Reward: 284.924±25.401, Episode_length: 187.500±22.308\n", ++ "Rollout 2264/9766, Reward: 269.538±30.191, Episode_length: 309.500±246.358\n", ++ "Rollout 2265/9766, Reward: 261.313±43.174, Episode_length: 335.600±312.642\n", ++ "Rollout 2266/9766, Reward: 267.204±16.634, Episode_length: 169.300±15.950\n", ++ "Rollout 2267/9766, Reward: 278.730±18.226, Episode_length: 190.000±22.136\n", ++ "Rollout 2268/9766, Reward: 263.400±48.489, Episode_length: 260.900±247.272\n", ++ "Rollout 2269/9766, Reward: 254.659±56.229, Episode_length: 272.400±243.394\n", ++ "Rollout 2270/9766, Reward: 249.038±74.065, Episode_length: 357.400±321.789\n", ++ "Rollout 2271/9766, Reward: 266.120±50.391, Episode_length: 253.400±249.519\n", ++ "Rollout 2272/9766, Reward: 276.611±17.908, Episode_length: 249.500±198.182\n", ++ "Rollout 2273/9766, Reward: 240.389±63.782, Episode_length: 354.900±323.134\n", ++ "Rollout 2274/9766, Reward: 204.317±159.526, Episode_length: 276.200±243.132\n", ++ "Rollout 2275/9766, Reward: 264.166±14.743, Episode_length: 171.900±22.340\n", ++ "Rollout 2276/9766, Reward: 254.517±53.320, Episode_length: 272.700±243.253\n", ++ "Rollout 2277/9766, Reward: 242.403±68.003, Episode_length: 356.500±322.140\n", ++ "Rollout 2278/9766, Reward: 255.083±74.599, Episode_length: 186.200±26.317\n", ++ "Rollout 2279/9766, Reward: 246.103±55.962, Episode_length: 344.800±328.706\n", ++ "Rollout 2280/9766, Reward: 274.398±11.959, Episode_length: 199.100±34.040\n", ++ "Rollout 2281/9766, Reward: 237.760±52.805, Episode_length: 369.500±318.576\n", ++ "Rollout 2282/9766, Reward: 247.011±42.580, Episode_length: 261.500±246.775\n", ++ "Rollout 2283/9766, Reward: 248.358±53.185, Episode_length: 295.400±237.832\n", ++ "Rollout 2284/9766, Reward: 270.335±17.311, Episode_length: 209.500±75.833\n", ++ "Rollout 2285/9766, Reward: 234.759±52.266, Episode_length: 406.600±251.769\n", ++ "Rollout 2286/9766, Reward: 261.111±19.538, Episode_length: 196.000±32.744\n", ++ "Rollout 2287/9766, Reward: 221.060±84.836, Episode_length: 295.200±238.505\n", ++ "Rollout 2288/9766, Reward: 238.997±24.613, Episode_length: 334.300±178.037\n", ++ "Rollout 2289/9766, Reward: 241.907±38.146, Episode_length: 353.700±204.979\n", ++ "Rollout 2290/9766, Reward: 243.167±67.479, Episode_length: 205.600±42.344\n", ++ "Rollout 2291/9766, Reward: 231.593±49.163, Episode_length: 341.600±229.653\n", ++ "Rollout 2292/9766, Reward: 179.246±198.244, Episode_length: 250.700±182.225\n", ++ "Rollout 2293/9766, Reward: 232.979±79.679, Episode_length: 222.200±61.741\n", ++ "Rollout 2294/9766, Reward: 215.267±60.247, Episode_length: 378.200±204.825\n", ++ "Rollout 2295/9766, Reward: 224.345±79.097, Episode_length: 285.800±138.014\n", ++ "Rollout 2296/9766, Reward: 244.252±34.845, Episode_length: 271.600±63.437\n", ++ "Rollout 2297/9766, Reward: 206.349±148.441, Episode_length: 259.100±100.003\n", ++ "Rollout 2298/9766, Reward: 93.752±162.705, Episode_length: 280.200±140.826\n", ++ "Rollout 2299/9766, Reward: 228.403±38.624, Episode_length: 290.000±122.437\n", ++ "Rollout 2300/9766, Reward: 214.057±46.033, Episode_length: 475.100±280.931\n", ++ "Rollout 2301/9766, Reward: 234.129±40.265, Episode_length: 304.800±142.334\n", ++ "Rollout 2302/9766, Reward: 222.794±77.318, Episode_length: 252.700±44.486\n", ++ "Rollout 2303/9766, Reward: 168.013±152.558, Episode_length: 272.000±153.170\n", ++ "Rollout 2304/9766, Reward: 221.713±25.074, Episode_length: 220.500±45.557\n", ++ "Rollout 2305/9766, Reward: 225.045±43.339, Episode_length: 376.200±294.720\n", ++ "Rollout 2306/9766, Reward: 215.483±83.271, Episode_length: 362.600±321.678\n", ++ "Rollout 2307/9766, Reward: 208.079±121.221, Episode_length: 266.400±117.268\n", ++ "Rollout 2308/9766, Reward: 247.462±20.720, Episode_length: 236.200±42.061\n", ++ "Rollout 2309/9766, Reward: 251.211±15.921, Episode_length: 226.600±39.105\n", ++ "Rollout 2310/9766, Reward: 210.397±110.440, Episode_length: 292.700±241.450\n", ++ "Rollout 2311/9766, Reward: 234.245±63.542, Episode_length: 262.800±155.860\n", ++ "Rollout 2312/9766, Reward: 216.851±90.386, Episode_length: 278.500±243.567\n", ++ "Rollout 2313/9766, Reward: 221.266±73.434, Episode_length: 298.300±237.357\n", ++ "Rollout 2314/9766, Reward: 221.575±82.210, Episode_length: 275.700±179.089\n", ++ "Rollout 2315/9766, Reward: 169.009±108.367, Episode_length: 467.300±358.706\n", ++ "Rollout 2316/9766, Reward: 267.878±26.777, Episode_length: 245.200±68.663\n", ++ "Rollout 2317/9766, Reward: 218.259±69.748, Episode_length: 401.000±302.653\n", ++ "Rollout 2318/9766, Reward: 258.084±25.100, Episode_length: 202.800±27.151\n", ++ "Rollout 2319/9766, Reward: 248.764±34.596, Episode_length: 295.800±102.185\n", ++ "Rollout 2320/9766, Reward: 249.698±26.387, Episode_length: 283.700±135.707\n", ++ "Rollout 2321/9766, Reward: 242.680±38.507, Episode_length: 254.900±105.406\n", ++ "Rollout 2322/9766, Reward: 238.542±30.237, Episode_length: 296.600±154.433\n", ++ "Rollout 2323/9766, Reward: 235.708±31.450, Episode_length: 309.500±104.950\n", ++ "Rollout 2324/9766, Reward: 236.361±33.361, Episode_length: 267.000±102.356\n", ++ "Rollout 2325/9766, Reward: 268.799±17.913, Episode_length: 238.900±62.447\n", ++ "Rollout 2326/9766, Reward: 263.269±23.697, Episode_length: 222.900±50.985\n", ++ "Rollout 2327/9766, Reward: 213.388±157.437, Episode_length: 226.200±52.000\n", ++ "Rollout 2328/9766, Reward: 225.107±152.492, Episode_length: 250.400±75.361\n", ++ "Rollout 2329/9766, Reward: 268.941±33.694, Episode_length: 253.500±75.844\n", ++ "Rollout 2330/9766, Reward: 271.481±18.299, Episode_length: 210.700±20.387\n", ++ "Rollout 2331/9766, Reward: 258.590±34.101, Episode_length: 294.700±165.530\n", ++ "Rollout 2332/9766, Reward: 248.295±49.237, Episode_length: 321.900±265.726\n", ++ "Rollout 2333/9766, Reward: 265.013±27.900, Episode_length: 210.400±76.777\n", ++ "Rollout 2334/9766, Reward: 270.076±14.246, Episode_length: 183.600±21.134\n", ++ "Rollout 2335/9766, Reward: 270.235±24.790, Episode_length: 205.500±60.470\n", ++ "Rollout 2336/9766, Reward: 279.476±14.762, Episode_length: 197.300±17.573\n", ++ "Rollout 2337/9766, Reward: 277.005±17.225, Episode_length: 192.800±21.288\n", ++ "Rollout 2338/9766, Reward: 279.247±16.708, Episode_length: 212.500±19.658\n", ++ "Rollout 2339/9766, Reward: 272.554±27.429, Episode_length: 219.900±67.635\n", ++ "Rollout 2340/9766, Reward: 274.384±16.687, Episode_length: 220.200±81.875\n", ++ "Rollout 2341/9766, Reward: 286.922±17.560, Episode_length: 199.200±11.847\n", ++ "Rollout 2342/9766, Reward: 269.433±32.517, Episode_length: 281.100±122.250\n", ++ "Rollout 2343/9766, Reward: 269.967±32.653, Episode_length: 250.200±142.758\n", ++ "Rollout 2344/9766, Reward: 277.223±20.607, Episode_length: 209.300±22.199\n", ++ "Rollout 2345/9766, Reward: 269.157±19.594, Episode_length: 199.600±24.589\n", ++ "Rollout 2346/9766, Reward: 271.881±15.308, Episode_length: 199.400±19.080\n", ++ "Rollout 2347/9766, Reward: 264.133±43.495, Episode_length: 288.400±238.251\n", ++ "Rollout 2348/9766, Reward: 284.475±22.453, Episode_length: 229.800±99.944\n", ++ "Rollout 2349/9766, Reward: 261.557±38.983, Episode_length: 351.200±300.093\n", ++ "Rollout 2350/9766, Reward: 273.185±17.306, Episode_length: 256.600±165.193\n", ++ "Rollout 2351/9766, Reward: 219.500±149.742, Episode_length: 357.200±312.538\n", ++ "Rollout 2352/9766, Reward: 297.254±17.405, Episode_length: 196.700±17.036\n", ++ "Rollout 2353/9766, Reward: 272.786±23.328, Episode_length: 241.200±78.539\n", ++ "Rollout 2354/9766, Reward: 282.798±18.150, Episode_length: 194.400±25.578\n", ++ "Rollout 2355/9766, Reward: 282.528±19.496, Episode_length: 191.100±25.956\n", ++ "Rollout 2356/9766, Reward: 281.089±20.769, Episode_length: 195.300±22.777\n", ++ "Rollout 2357/9766, Reward: 276.660±35.722, Episode_length: 297.700±239.031\n", ++ "Rollout 2358/9766, Reward: 258.101±40.674, Episode_length: 302.600±243.398\n", ++ "Rollout 2359/9766, Reward: 274.734±43.100, Episode_length: 269.900±244.006\n", ++ "Rollout 2360/9766, Reward: 278.893±37.958, Episode_length: 275.600±242.388\n", ++ "Rollout 2361/9766, Reward: 272.806±20.206, Episode_length: 195.100±23.725\n", ++ "Rollout 2362/9766, Reward: 287.339±21.962, Episode_length: 236.200±31.176\n", ++ "Rollout 2363/9766, Reward: 286.221±16.126, Episode_length: 195.700±23.933\n", ++ "Rollout 2364/9766, Reward: 284.355±16.344, Episode_length: 187.500±24.508\n", ++ "Rollout 2365/9766, Reward: 276.822±14.531, Episode_length: 191.900±26.155\n", ++ "Rollout 2366/9766, Reward: 277.346±16.477, Episode_length: 188.600±20.470\n", ++ "Rollout 2367/9766, Reward: 275.838±25.672, Episode_length: 186.200±19.405\n", ++ "Rollout 2368/9766, Reward: 274.523±20.096, Episode_length: 191.500±19.054\n", ++ "Rollout 2369/9766, Reward: 282.967±17.328, Episode_length: 190.000±30.003\n", ++ "Rollout 2370/9766, Reward: 285.859±23.457, Episode_length: 256.800±195.481\n", ++ "Rollout 2371/9766, Reward: 255.750±100.474, Episode_length: 189.200±39.789\n", ++ "Rollout 2372/9766, Reward: 277.307±16.564, Episode_length: 181.500±12.761\n", ++ "Rollout 2373/9766, Reward: 270.558±19.480, Episode_length: 192.200±44.093\n", ++ "Rollout 2374/9766, Reward: 267.552±18.474, Episode_length: 221.900±58.953\n", ++ "Rollout 2375/9766, Reward: 244.818±64.603, Episode_length: 334.300±280.807\n", ++ "Rollout 2376/9766, Reward: 234.219±84.712, Episode_length: 285.400±240.521\n", ++ "Rollout 2377/9766, Reward: 254.305±52.652, Episode_length: 364.000±319.292\n", ++ "Rollout 2378/9766, Reward: 256.116±36.671, Episode_length: 361.500±320.371\n", ++ "Rollout 2379/9766, Reward: 252.092±48.189, Episode_length: 347.800±327.141\n", ++ "Rollout 2380/9766, Reward: 279.549±19.943, Episode_length: 194.700±36.642\n", ++ "Rollout 2381/9766, Reward: 263.129±37.372, Episode_length: 262.200±248.524\n", ++ "Rollout 2382/9766, Reward: 258.990±39.716, Episode_length: 294.800±237.354\n", ++ "Rollout 2383/9766, Reward: 266.815±36.579, Episode_length: 296.300±236.986\n", ++ "Rollout 2384/9766, Reward: 286.939±20.425, Episode_length: 260.000±180.199\n", ++ "Rollout 2385/9766, Reward: 272.295±22.131, Episode_length: 194.600±32.773\n", ++ "Rollout 2386/9766, Reward: 280.096±13.225, Episode_length: 195.700±25.578\n", ++ "Rollout 2387/9766, Reward: 280.132±16.499, Episode_length: 194.900±29.211\n", ++ "Rollout 2388/9766, Reward: 277.699±13.723, Episode_length: 195.700±30.414\n", ++ "Rollout 2389/9766, Reward: 274.361±16.577, Episode_length: 197.700±23.584\n", ++ "Rollout 2390/9766, Reward: 266.762±13.900, Episode_length: 203.000±74.411\n", ++ "Rollout 2391/9766, Reward: 281.737±18.773, Episode_length: 186.400±36.538\n", ++ "Rollout 2392/9766, Reward: 268.760±18.640, Episode_length: 183.100±24.986\n", ++ "Rollout 2393/9766, Reward: 249.049±40.327, Episode_length: 352.700±324.346\n", ++ "Rollout 2394/9766, Reward: 269.704±32.808, Episode_length: 263.000±247.145\n", ++ "Rollout 2395/9766, Reward: 270.019±34.823, Episode_length: 273.300±243.880\n", ++ "Rollout 2396/9766, Reward: 260.855±42.332, Episode_length: 342.200±329.749\n", ++ "Rollout 2397/9766, Reward: 284.878±12.147, Episode_length: 187.500±27.979\n", ++ "Rollout 2398/9766, Reward: 288.510±19.909, Episode_length: 195.100±22.784\n", ++ "Rollout 2399/9766, Reward: 288.235±15.291, Episode_length: 187.900±22.634\n", ++ "Rollout 2400/9766, Reward: 258.140±73.700, Episode_length: 181.800±31.543\n", ++ "Rollout 2401/9766, Reward: 263.329±43.873, Episode_length: 351.100±325.212\n", ++ "Rollout 2402/9766, Reward: 275.116±35.679, Episode_length: 286.600±239.127\n", ++ "Rollout 2403/9766, Reward: 254.563±80.818, Episode_length: 287.500±242.800\n", ++ "Rollout 2404/9766, Reward: 280.759±18.343, Episode_length: 250.300±140.254\n", ++ "Rollout 2405/9766, Reward: 270.543±12.647, Episode_length: 192.000±28.150\n", ++ "Rollout 2406/9766, Reward: 274.291±39.907, Episode_length: 271.400±243.531\n", ++ "Rollout 2407/9766, Reward: 247.102±35.926, Episode_length: 436.900±369.830\n", ++ "Rollout 2408/9766, Reward: 271.156±17.932, Episode_length: 191.600±22.137\n", ++ "Rollout 2409/9766, Reward: 259.225±57.681, Episode_length: 364.100±319.025\n", ++ "Rollout 2410/9766, Reward: 263.510±40.271, Episode_length: 352.200±324.725\n", ++ "Rollout 2411/9766, Reward: 268.860±49.119, Episode_length: 311.600±249.777\n", ++ "Rollout 2412/9766, Reward: 279.896±13.403, Episode_length: 190.700±26.390\n", ++ "Rollout 2413/9766, Reward: 283.440±38.428, Episode_length: 352.600±293.551\n", ++ "Rollout 2414/9766, Reward: 263.393±43.216, Episode_length: 268.300±244.738\n", ++ "Rollout 2415/9766, Reward: 286.968±13.699, Episode_length: 186.600±17.130\n", ++ "Rollout 2416/9766, Reward: 184.257±52.058, Episode_length: 751.300±379.899\n", ++ "Rollout 2417/9766, Reward: 214.117±65.794, Episode_length: 593.800±406.421\n", ++ "Rollout 2418/9766, Reward: 238.800±53.321, Episode_length: 649.300±336.075\n", ++ "Rollout 2419/9766, Reward: 210.783±73.705, Episode_length: 716.500±360.118\n", ++ "Rollout 2420/9766, Reward: 223.475±53.677, Episode_length: 663.000±412.846\n", ++ "Rollout 2421/9766, Reward: 270.817±46.484, Episode_length: 254.600±249.011\n", ++ "Rollout 2422/9766, Reward: 263.509±45.228, Episode_length: 351.700±325.052\n", ++ "Rollout 2423/9766, Reward: 283.146±14.291, Episode_length: 190.600±36.467\n", ++ "Rollout 2424/9766, Reward: 285.779±19.500, Episode_length: 194.000±35.930\n", ++ "Rollout 2425/9766, Reward: 284.831±15.278, Episode_length: 191.700±44.802\n", ++ "Rollout 2426/9766, Reward: 283.154±18.287, Episode_length: 212.800±93.385\n", ++ "Rollout 2427/9766, Reward: 274.165±28.237, Episode_length: 258.200±248.633\n", ++ "Rollout 2428/9766, Reward: 276.658±35.996, Episode_length: 267.500±244.566\n", ++ "Rollout 2429/9766, Reward: 261.580±50.297, Episode_length: 346.200±327.294\n", ++ "Rollout 2430/9766, Reward: 253.899±42.384, Episode_length: 333.200±333.568\n", ++ "Rollout 2431/9766, Reward: 263.641±57.131, Episode_length: 365.100±321.108\n", ++ "Rollout 2432/9766, Reward: 284.210±17.806, Episode_length: 271.800±176.866\n", ++ "Rollout 2433/9766, Reward: 285.931±14.754, Episode_length: 188.900±25.774\n", ++ "Rollout 2434/9766, Reward: 279.267±26.063, Episode_length: 178.200±35.227\n", ++ "Rollout 2435/9766, Reward: 283.204±17.537, Episode_length: 179.700±24.327\n", ++ "Rollout 2436/9766, Reward: 264.078±34.666, Episode_length: 260.300±247.973\n", ++ "Rollout 2437/9766, Reward: 266.321±39.432, Episode_length: 271.600±243.140\n", ++ "Rollout 2438/9766, Reward: 273.842±12.072, Episode_length: 186.900±24.922\n", ++ "Rollout 2439/9766, Reward: 274.287±15.533, Episode_length: 219.300±130.138\n", ++ "Rollout 2440/9766, Reward: 229.215±155.465, Episode_length: 197.200±52.646\n", ++ "Rollout 2441/9766, Reward: 250.613±44.709, Episode_length: 274.600±242.355\n", ++ "Rollout 2442/9766, Reward: 232.725±140.811, Episode_length: 232.900±134.406\n", ++ "Rollout 2443/9766, Reward: 281.623±18.711, Episode_length: 194.100±26.021\n", ++ "Rollout 2444/9766, Reward: 277.438±21.484, Episode_length: 213.800±43.504\n", ++ "Rollout 2445/9766, Reward: 285.314±23.917, Episode_length: 242.200±146.022\n", ++ "Rollout 2446/9766, Reward: 275.281±15.649, Episode_length: 190.500±26.748\n", ++ "Rollout 2447/9766, Reward: 285.400±12.162, Episode_length: 212.800±63.047\n", ++ "Rollout 2448/9766, Reward: 288.114±13.875, Episode_length: 194.900±22.858\n", ++ "Rollout 2449/9766, Reward: 278.654±13.840, Episode_length: 180.200±18.734\n", ++ "Rollout 2450/9766, Reward: 283.488±18.045, Episode_length: 203.400±32.166\n", ++ "Rollout 2451/9766, Reward: 283.989±21.588, Episode_length: 188.100±28.981\n", ++ "Rollout 2452/9766, Reward: 289.775±12.747, Episode_length: 192.200±34.632\n", ++ "Rollout 2453/9766, Reward: 291.871±15.571, Episode_length: 203.100±18.876\n", ++ "Rollout 2454/9766, Reward: 285.325±21.313, Episode_length: 189.900±21.557\n", ++ "Rollout 2455/9766, Reward: 280.734±21.545, Episode_length: 202.600±19.936\n", ++ "Rollout 2456/9766, Reward: 279.438±11.142, Episode_length: 202.800±22.243\n", ++ "Rollout 2457/9766, Reward: 268.074±16.012, Episode_length: 191.400±38.658\n", ++ "Rollout 2458/9766, Reward: 292.280±16.688, Episode_length: 217.300±51.445\n", ++ "Rollout 2459/9766, Reward: 271.484±18.717, Episode_length: 206.100±25.782\n", ++ "Rollout 2460/9766, Reward: 294.447±18.006, Episode_length: 209.400±26.740\n", ++ "Rollout 2461/9766, Reward: 282.566±17.069, Episode_length: 203.200±36.780\n", ++ "Rollout 2462/9766, Reward: 270.242±14.817, Episode_length: 194.200±8.280\n", ++ "Rollout 2463/9766, Reward: 277.834±13.961, Episode_length: 180.800±12.090\n", ++ "Rollout 2464/9766, Reward: 271.283±26.285, Episode_length: 220.400±27.493\n", ++ "Rollout 2465/9766, Reward: 287.571±14.534, Episode_length: 211.900±40.081\n", ++ "Rollout 2466/9766, Reward: 289.404±16.086, Episode_length: 228.300±30.282\n", ++ "Rollout 2467/9766, Reward: 283.553±19.307, Episode_length: 199.400±23.265\n", ++ "Rollout 2468/9766, Reward: 290.969±16.802, Episode_length: 212.700±34.745\n", ++ "Rollout 2469/9766, Reward: 256.279±44.101, Episode_length: 283.800±239.973\n", ++ "Rollout 2470/9766, Reward: 281.057±15.724, Episode_length: 189.100±9.772\n", ++ "Rollout 2471/9766, Reward: 282.412±14.161, Episode_length: 186.200±24.404\n", ++ "Rollout 2472/9766, Reward: 260.295±77.019, Episode_length: 194.000±27.350\n", ++ "Rollout 2473/9766, Reward: 288.161±22.372, Episode_length: 203.900±19.690\n", ++ "Rollout 2474/9766, Reward: 289.117±16.003, Episode_length: 192.500±30.160\n", ++ "Rollout 2475/9766, Reward: 280.184±13.543, Episode_length: 177.500±23.118\n", ++ "Rollout 2476/9766, Reward: 276.472±17.166, Episode_length: 172.100±14.432\n", ++ "Rollout 2477/9766, Reward: 286.048±17.145, Episode_length: 204.100±34.870\n", ++ "Rollout 2478/9766, Reward: 275.812±16.654, Episode_length: 177.700±20.323\n", ++ "Rollout 2479/9766, Reward: 283.988±14.395, Episode_length: 189.400±15.970\n", ++ "Rollout 2480/9766, Reward: 274.813±16.396, Episode_length: 188.800±22.471\n", ++ "Rollout 2481/9766, Reward: 270.893±23.402, Episode_length: 180.100±18.442\n", ++ "Rollout 2482/9766, Reward: 242.663±51.655, Episode_length: 348.600±326.943\n", ++ "Rollout 2483/9766, Reward: 252.293±60.548, Episode_length: 183.800±21.391\n", ++ "Rollout 2484/9766, Reward: 279.608±18.294, Episode_length: 207.700±41.156\n", ++ "Rollout 2485/9766, Reward: 277.726±25.678, Episode_length: 247.300±156.242\n", ++ "Rollout 2486/9766, Reward: 290.806±14.432, Episode_length: 182.500±16.458\n", ++ "Rollout 2487/9766, Reward: 287.403±14.048, Episode_length: 196.200±29.526\n", ++ "Rollout 2488/9766, Reward: 286.083±12.717, Episode_length: 186.100±14.970\n", ++ "Rollout 2489/9766, Reward: 272.161±24.334, Episode_length: 256.200±216.369\n", ++ "Rollout 2490/9766, Reward: 277.977±14.727, Episode_length: 181.400±21.648\n", ++ "Rollout 2491/9766, Reward: 278.751±16.277, Episode_length: 184.000±23.744\n", ++ "Rollout 2492/9766, Reward: 268.574±35.631, Episode_length: 262.000±246.673\n", ++ "Rollout 2493/9766, Reward: 275.572±14.030, Episode_length: 181.600±27.872\n", ++ "Rollout 2494/9766, Reward: 283.088±16.487, Episode_length: 186.300±24.112\n", ++ "Rollout 2495/9766, Reward: 284.735±14.428, Episode_length: 230.700±116.386\n", ++ "Rollout 2496/9766, Reward: 280.834±15.649, Episode_length: 183.500±20.505\n", ++ "Rollout 2497/9766, Reward: 283.543±19.105, Episode_length: 200.900±30.283\n", ++ "Rollout 2498/9766, Reward: 287.665±10.037, Episode_length: 186.200±22.542\n", ++ "Rollout 2499/9766, Reward: 280.761±12.254, Episode_length: 189.200±27.224\n", ++ "Rollout 2500/9766, Reward: 269.327±35.990, Episode_length: 278.900±244.043\n", ++ "Rollout 2501/9766, Reward: 293.918±23.823, Episode_length: 199.600±38.552\n", ++ "Rollout 2502/9766, Reward: 288.248±18.677, Episode_length: 211.800±67.409\n", ++ "Rollout 2503/9766, Reward: 283.954±12.608, Episode_length: 240.100±181.705\n", ++ "Rollout 2504/9766, Reward: 282.731±29.805, Episode_length: 280.800±242.085\n", ++ "Rollout 2505/9766, Reward: 201.602±114.062, Episode_length: 509.800±350.404\n", ++ "Rollout 2506/9766, Reward: 240.917±47.198, Episode_length: 732.400±319.219\n", ++ "Rollout 2507/9766, Reward: 178.026±40.622, Episode_length: 906.800±236.644\n", ++ "Rollout 2508/9766, Reward: 229.318±140.976, Episode_length: 325.600±273.319\n", ++ "Rollout 2509/9766, Reward: 267.206±20.750, Episode_length: 424.100±272.195\n", ++ "Rollout 2510/9766, Reward: 273.134±42.138, Episode_length: 285.900±240.290\n", ++ "Rollout 2511/9766, Reward: 243.330±52.783, Episode_length: 446.900±365.886\n", ++ "Rollout 2512/9766, Reward: 263.749±47.871, Episode_length: 357.800±324.118\n", ++ "Rollout 2513/9766, Reward: 265.910±45.912, Episode_length: 272.600±243.642\n", ++ "Rollout 2514/9766, Reward: 269.449±27.674, Episode_length: 292.100±214.588\n", ++ "Rollout 2515/9766, Reward: 274.963±28.121, Episode_length: 253.700±171.646\n", ++ "Rollout 2516/9766, Reward: 270.374±34.431, Episode_length: 224.000±84.438\n", ++ "Rollout 2517/9766, Reward: 249.956±55.158, Episode_length: 279.000±243.565\n", ++ "Rollout 2518/9766, Reward: 268.178±31.525, Episode_length: 230.600±102.952\n", ++ "Rollout 2519/9766, Reward: 277.023±18.667, Episode_length: 255.200±105.286\n", ++ "Rollout 2520/9766, Reward: 264.614±16.498, Episode_length: 238.800±93.651\n", ++ "Rollout 2521/9766, Reward: 220.250±136.487, Episode_length: 350.100±314.806\n", ++ "Rollout 2522/9766, Reward: 211.992±75.176, Episode_length: 497.100±359.996\n", ++ "Rollout 2523/9766, Reward: 278.793±17.712, Episode_length: 235.300±61.338\n", ++ "Rollout 2524/9766, Reward: 173.823±132.181, Episode_length: 543.100±381.558\n", ++ "Rollout 2525/9766, Reward: 235.538±48.723, Episode_length: 686.500±331.373\n", ++ "Rollout 2526/9766, Reward: 267.371±18.037, Episode_length: 261.900±60.819\n", ++ "Rollout 2527/9766, Reward: 219.800±62.076, Episode_length: 554.800±287.043\n", ++ "Rollout 2528/9766, Reward: 160.272±126.284, Episode_length: 382.500±292.441\n", ++ "Rollout 2529/9766, Reward: 213.937±71.411, Episode_length: 373.300±255.548\n", ++ "Rollout 2530/9766, Reward: 247.811±30.265, Episode_length: 431.300±319.609\n", ++ "Rollout 2531/9766, Reward: 278.778±18.590, Episode_length: 212.200±69.659\n", ++ "Rollout 2532/9766, Reward: 274.621±20.937, Episode_length: 234.000±142.165\n", ++ "Rollout 2533/9766, Reward: 282.652±31.811, Episode_length: 318.200±247.631\n", ++ "Rollout 2534/9766, Reward: 266.842±39.572, Episode_length: 316.200±263.554\n", ++ "Rollout 2535/9766, Reward: 286.066±21.568, Episode_length: 206.000±28.358\n", ++ "Rollout 2536/9766, Reward: 280.324±17.211, Episode_length: 197.600±27.750\n", ++ "Rollout 2537/9766, Reward: 236.357±136.201, Episode_length: 186.500±22.800\n", ++ "Rollout 2538/9766, Reward: 283.223±10.431, Episode_length: 189.900±26.606\n", ++ "Rollout 2539/9766, Reward: 285.935±16.803, Episode_length: 205.200±40.454\n", ++ "Rollout 2540/9766, Reward: 270.174±46.909, Episode_length: 275.600±242.791\n", ++ "Rollout 2541/9766, Reward: 240.411±62.857, Episode_length: 488.700±346.791\n", ++ "Rollout 2542/9766, Reward: 245.104±55.221, Episode_length: 352.400±324.948\n", ++ "Rollout 2543/9766, Reward: 263.337±42.174, Episode_length: 283.100±244.121\n", ++ "Rollout 2544/9766, Reward: 254.354±48.205, Episode_length: 413.900±332.262\n", ++ "Rollout 2545/9766, Reward: 261.627±46.214, Episode_length: 257.600±248.555\n", ++ "Rollout 2546/9766, Reward: 276.181±16.559, Episode_length: 191.000±14.007\n", ++ "Rollout 2547/9766, Reward: 283.020±13.705, Episode_length: 219.000±79.061\n", ++ "Rollout 2548/9766, Reward: 284.307±21.428, Episode_length: 202.200±19.513\n", ++ "Rollout 2549/9766, Reward: 273.403±12.519, Episode_length: 182.400±25.993\n", ++ "Rollout 2550/9766, Reward: 283.746±14.292, Episode_length: 192.600±31.190\n", ++ "Rollout 2551/9766, Reward: 282.175±25.329, Episode_length: 196.200±32.908\n", ++ "Rollout 2552/9766, Reward: 249.999±51.584, Episode_length: 324.100±263.307\n", ++ "Rollout 2553/9766, Reward: 277.979±31.576, Episode_length: 252.700±176.321\n", ++ "Rollout 2554/9766, Reward: 260.548±23.464, Episode_length: 247.600±179.856\n", ++ "Rollout 2555/9766, Reward: 278.734±20.995, Episode_length: 202.900±36.303\n", ++ "Rollout 2556/9766, Reward: 267.224±20.556, Episode_length: 181.200±23.819\n", ++ "Rollout 2557/9766, Reward: 250.436±61.455, Episode_length: 225.200±79.685\n", ++ "Rollout 2558/9766, Reward: 274.120±26.929, Episode_length: 363.500±308.037\n", ++ "Rollout 2559/9766, Reward: 266.358±17.260, Episode_length: 198.200±28.600\n", ++ "Rollout 2560/9766, Reward: 269.406±35.486, Episode_length: 384.800±257.563\n", ++ "Rollout 2561/9766, Reward: 262.345±51.439, Episode_length: 348.200±287.015\n", ++ "Rollout 2562/9766, Reward: 274.469±23.929, Episode_length: 217.800±52.450\n", ++ "Rollout 2563/9766, Reward: 230.327±79.840, Episode_length: 392.300±314.008\n", ++ "Rollout 2564/9766, Reward: 256.610±48.895, Episode_length: 361.400±321.182\n", ++ "Rollout 2565/9766, Reward: 251.671±43.154, Episode_length: 405.000±283.048\n", ++ "Rollout 2566/9766, Reward: 233.384±53.729, Episode_length: 411.100±295.535\n", ++ "Rollout 2567/9766, Reward: 218.596±76.839, Episode_length: 353.000±160.522\n", ++ "Rollout 2568/9766, Reward: 255.480±38.144, Episode_length: 327.200±268.296\n", ++ "Rollout 2569/9766, Reward: 260.273±37.045, Episode_length: 254.900±127.477\n", ++ "Rollout 2570/9766, Reward: 252.523±32.040, Episode_length: 319.900±287.850\n", ++ "Rollout 2571/9766, Reward: 280.410±10.139, Episode_length: 245.500±62.763\n", ++ "Rollout 2572/9766, Reward: 239.032±67.318, Episode_length: 201.700±40.020\n", ++ "Rollout 2573/9766, Reward: 228.376±92.395, Episode_length: 213.100±41.249\n", ++ "Rollout 2574/9766, Reward: 222.867±78.794, Episode_length: 315.200±257.713\n", ++ "Rollout 2575/9766, Reward: 252.051±73.546, Episode_length: 241.100±75.551\n", ++ "Rollout 2576/9766, Reward: 269.931±23.315, Episode_length: 202.200±33.775\n", ++ "Rollout 2577/9766, Reward: 270.853±48.881, Episode_length: 284.200±241.283\n", ++ "Rollout 2578/9766, Reward: 247.588±76.577, Episode_length: 276.400±161.606\n", ++ "Rollout 2579/9766, Reward: 284.263±9.053, Episode_length: 208.000±24.593\n", ++ "Rollout 2580/9766, Reward: 268.849±24.312, Episode_length: 305.200±236.463\n", ++ "Rollout 2581/9766, Reward: 268.149±24.029, Episode_length: 267.000±236.398\n", ++ "Rollout 2582/9766, Reward: 224.502±54.720, Episode_length: 671.300±365.608\n", ++ "Rollout 2583/9766, Reward: 272.208±16.743, Episode_length: 244.600±106.381\n", ++ "Rollout 2584/9766, Reward: 253.197±44.317, Episode_length: 282.300±241.249\n", ++ "Rollout 2585/9766, Reward: 223.641±80.737, Episode_length: 347.900±271.062\n", ++ "Rollout 2586/9766, Reward: 250.697±69.385, Episode_length: 194.900±31.970\n", ++ "Rollout 2587/9766, Reward: 215.393±76.065, Episode_length: 386.200±309.400\n", ++ "Rollout 2588/9766, Reward: 246.985±47.579, Episode_length: 413.300±361.661\n", ++ "Rollout 2589/9766, Reward: 228.535±62.733, Episode_length: 443.500±365.936\n", ++ "Rollout 2590/9766, Reward: 240.366��52.093, Episode_length: 361.500±320.850\n", ++ "Rollout 2591/9766, Reward: 244.155±39.278, Episode_length: 330.700±242.464\n", ++ "Rollout 2592/9766, Reward: 226.786±66.710, Episode_length: 580.100±380.789\n", ++ "Rollout 2593/9766, Reward: 241.947±56.954, Episode_length: 432.800±337.258\n", ++ "Rollout 2594/9766, Reward: 269.646±28.202, Episode_length: 257.300±160.633\n", ++ "Rollout 2595/9766, Reward: 259.169±36.508, Episode_length: 278.000±241.925\n", ++ "Rollout 2596/9766, Reward: 262.865±18.797, Episode_length: 207.100±65.064\n", ++ "Rollout 2597/9766, Reward: 244.025±61.163, Episode_length: 360.000±321.356\n", ++ "Rollout 2598/9766, Reward: 257.598±57.522, Episode_length: 560.600±367.695\n", ++ "Rollout 2599/9766, Reward: 228.457±63.355, Episode_length: 286.600±34.926\n", ++ "Rollout 2600/9766, Reward: 232.645±40.385, Episode_length: 493.500±336.776\n", ++ "Rollout 2601/9766, Reward: 234.222±73.302, Episode_length: 269.300±224.362\n", ++ "Rollout 2602/9766, Reward: 220.553±84.948, Episode_length: 286.900±183.922\n", ++ "Rollout 2603/9766, Reward: 231.479±83.116, Episode_length: 297.900±199.740\n", ++ "Rollout 2604/9766, Reward: 221.677±76.814, Episode_length: 265.200±83.499\n", ++ "Rollout 2605/9766, Reward: 214.173±89.817, Episode_length: 335.500±198.157\n", ++ "Rollout 2606/9766, Reward: 205.948±83.340, Episode_length: 395.100±304.353\n", ++ "Rollout 2607/9766, Reward: 228.151±77.938, Episode_length: 368.500±209.083\n", ++ "Rollout 2608/9766, Reward: 230.159±72.191, Episode_length: 291.400±218.511\n", ++ "Rollout 2609/9766, Reward: 209.678±78.672, Episode_length: 459.600±321.403\n", ++ "Rollout 2610/9766, Reward: 166.233±106.687, Episode_length: 468.000±338.953\n", ++ "Rollout 2611/9766, Reward: 229.067±79.802, Episode_length: 300.000±239.136\n", ++ "Rollout 2612/9766, Reward: 184.179±99.526, Episode_length: 292.000±238.131\n", ++ "Rollout 2613/9766, Reward: 165.723±124.276, Episode_length: 355.900±322.538\n", ++ "Rollout 2614/9766, Reward: 196.825±97.642, Episode_length: 474.800±330.329\n", ++ "Rollout 2615/9766, Reward: 224.270±82.133, Episode_length: 295.600±238.575\n", ++ "Rollout 2616/9766, Reward: 192.675±104.884, Episode_length: 318.700±257.462\n", ++ "Rollout 2617/9766, Reward: 231.384±41.170, Episode_length: 317.100±238.563\n", ++ "Rollout 2618/9766, Reward: 224.269±87.905, Episode_length: 308.900±236.053\n", ++ "Rollout 2619/9766, Reward: 152.190±119.790, Episode_length: 320.500±242.530\n", ++ "Rollout 2620/9766, Reward: 215.557±76.520, Episode_length: 303.000±234.473\n", ++ "Rollout 2621/9766, Reward: 235.771±77.235, Episode_length: 366.600±285.795\n", ++ "Rollout 2622/9766, Reward: 219.979±99.443, Episode_length: 199.900±37.007\n", ++ "Rollout 2623/9766, Reward: 188.678±96.409, Episode_length: 413.900±303.846\n", ++ "Rollout 2624/9766, Reward: 200.246±95.743, Episode_length: 384.900±313.796\n", ++ "Rollout 2625/9766, Reward: 211.228±78.752, Episode_length: 372.500±316.022\n", ++ "Rollout 2626/9766, Reward: 247.872±40.352, Episode_length: 294.800±238.439\n", ++ "Rollout 2627/9766, Reward: 220.352±59.404, Episode_length: 688.500±328.321\n", ++ "Rollout 2628/9766, Reward: 252.274±58.588, Episode_length: 388.800±309.576\n", ++ "Rollout 2629/9766, Reward: 241.037±61.822, Episode_length: 427.600±332.196\n", ++ "Rollout 2630/9766, Reward: 251.871±43.056, Episode_length: 325.300±241.147\n", ++ "Rollout 2631/9766, Reward: 231.598±42.989, Episode_length: 527.500±277.670\n", ++ "Rollout 2632/9766, Reward: 245.469±36.804, Episode_length: 632.600±371.397\n", ++ "Rollout 2633/9766, Reward: 263.436±21.304, Episode_length: 253.000±224.084\n", ++ "Rollout 2634/9766, Reward: 284.610±25.953, Episode_length: 197.400±13.771\n", ++ "Rollout 2635/9766, Reward: 248.676±32.705, Episode_length: 253.700±79.725\n", ++ "Rollout 2636/9766, Reward: 264.518±13.577, Episode_length: 227.600±74.310\n", ++ "Rollout 2637/9766, Reward: 241.992±53.213, Episode_length: 519.800±342.043\n", ++ "Rollout 2638/9766, Reward: 253.026±58.603, Episode_length: 366.500±318.213\n", ++ "Rollout 2639/9766, Reward: 248.320±87.406, Episode_length: 242.300±75.911\n", ++ "Rollout 2640/9766, Reward: 250.803±45.840, Episode_length: 507.600±337.756\n", ++ "Rollout 2641/9766, Reward: 271.800±23.580, Episode_length: 277.000±199.988\n", ++ "Rollout 2642/9766, Reward: 243.364±44.912, Episode_length: 304.700±234.172\n", ++ "Rollout 2643/9766, Reward: 257.884±35.515, Episode_length: 303.500±237.753\n", ++ "Rollout 2644/9766, Reward: 259.897±29.706, Episode_length: 337.100±272.259\n", ++ "Rollout 2645/9766, Reward: 218.016±86.506, Episode_length: 487.900±325.868\n", ++ "Rollout 2646/9766, Reward: 240.686±56.110, Episode_length: 382.900±311.515\n", ++ "Rollout 2647/9766, Reward: 268.494±17.869, Episode_length: 227.000±39.606\n", ++ "Rollout 2648/9766, Reward: 218.155±112.363, Episode_length: 290.500±241.571\n", ++ "Rollout 2649/9766, Reward: 202.500±92.907, Episode_length: 418.600±293.817\n", ++ "Rollout 2650/9766, Reward: 230.519±58.903, Episode_length: 337.200±265.872\n", ++ "Rollout 2651/9766, Reward: 240.922±22.246, Episode_length: 332.800±188.378\n", ++ "Rollout 2652/9766, Reward: 233.323±46.843, Episode_length: 307.900±190.023\n", ++ "Rollout 2653/9766, Reward: 219.550±47.686, Episode_length: 594.400±320.287\n", ++ "Rollout 2654/9766, Reward: 243.072±59.674, Episode_length: 401.300±309.762\n", ++ "Rollout 2655/9766, Reward: 247.399±54.980, Episode_length: 370.000±317.930\n", ++ "Rollout 2656/9766, Reward: 244.136±45.237, Episode_length: 326.400±242.794\n", ++ "Rollout 2657/9766, Reward: 219.430±45.122, Episode_length: 583.100±369.716\n", ++ "Rollout 2658/9766, Reward: 251.159±26.026, Episode_length: 304.700±157.635\n", ++ "Rollout 2659/9766, Reward: 218.806±54.983, Episode_length: 472.400±347.714\n", ++ "Rollout 2660/9766, Reward: 259.268±42.480, Episode_length: 310.100±232.973\n", ++ "Rollout 2661/9766, Reward: 193.443±128.712, Episode_length: 423.800±316.381\n", ++ "Rollout 2662/9766, Reward: 231.011±59.360, Episode_length: 397.500±311.168\n", ++ "Rollout 2663/9766, Reward: 230.556±75.936, Episode_length: 461.200±353.548\n", ++ "Rollout 2664/9766, Reward: 235.553±51.603, Episode_length: 370.000±318.291\n", ++ "Rollout 2665/9766, Reward: 252.740±48.985, Episode_length: 314.800±237.459\n", ++ "Rollout 2666/9766, Reward: 251.977±35.562, Episode_length: 410.900±270.195\n", ++ "Rollout 2667/9766, Reward: 255.167±25.085, Episode_length: 259.800±34.490\n", ++ "Rollout 2668/9766, Reward: 233.835±46.796, Episode_length: 405.700±300.255\n", ++ "Rollout 2669/9766, Reward: 228.990±43.270, Episode_length: 520.400±329.051\n", ++ "Rollout 2670/9766, Reward: 244.068±38.575, Episode_length: 321.600±238.485\n", ++ "Rollout 2671/9766, Reward: 236.292±55.796, Episode_length: 488.800±370.046\n", ++ "Rollout 2672/9766, Reward: 191.165±61.413, Episode_length: 678.200±394.236\n", ++ "Rollout 2673/9766, Reward: 227.278±48.521, Episode_length: 452.800±361.248\n", ++ "Rollout 2674/9766, Reward: 226.960±39.766, Episode_length: 558.000±381.469\n", ++ "Rollout 2675/9766, Reward: 209.059±50.371, Episode_length: 542.500±374.746\n", ++ "Rollout 2676/9766, Reward: 234.638±45.493, Episode_length: 404.900±259.401\n", ++ "Rollout 2677/9766, Reward: 223.521±58.448, Episode_length: 596.900±349.195\n", ++ "Rollout 2678/9766, Reward: 188.607±58.604, Episode_length: 753.400±376.963\n", ++ "Rollout 2679/9766, Reward: 197.109±71.063, Episode_length: 724.700±345.369\n", ++ "Rollout 2680/9766, Reward: 213.429±55.526, Episode_length: 616.200±384.742\n", ++ "Rollout 2681/9766, Reward: 170.990±96.190, Episode_length: 640.000±372.554\n", ++ "Rollout 2682/9766, Reward: 231.835±41.297, Episode_length: 715.300±202.938\n", ++ "Rollout 2683/9766, Reward: 221.049±60.694, Episode_length: 578.700±352.301\n", ++ "Rollout 2684/9766, Reward: 207.280±56.596, Episode_length: 671.500±296.247\n", ++ "Rollout 2685/9766, Reward: 206.743±57.209, Episode_length: 574.200±365.749\n", ++ "Rollout 2686/9766, Reward: 208.972±65.800, Episode_length: 597.500±383.132\n", ++ "Rollout 2687/9766, Reward: 193.291±62.949, Episode_length: 610.500±389.719\n", ++ "Rollout 2688/9766, Reward: 192.602±60.236, Episode_length: 749.900±337.755\n", ++ "Rollout 2689/9766, Reward: 165.205±144.491, Episode_length: 527.200±326.350\n", ++ "Rollout 2690/9766, Reward: 186.009±56.418, Episode_length: 792.100±323.666\n", ++ "Rollout 2691/9766, Reward: 177.630±85.687, Episode_length: 655.000±370.235\n", ++ "Rollout 2692/9766, Reward: 163.430±54.438, Episode_length: 913.900±243.986\n", ++ "Rollout 2693/9766, Reward: 202.437±61.232, Episode_length: 704.300±313.637\n", ++ "Rollout 2694/9766, Reward: 278.359±22.032, Episode_length: 221.900±48.492\n", ++ "Rollout 2695/9766, Reward: 264.238±26.532, Episode_length: 357.000±226.667\n", ++ "Rollout 2696/9766, Reward: 284.595±10.016, Episode_length: 255.100±165.210\n", ++ "Rollout 2697/9766, Reward: 238.173±55.219, Episode_length: 351.000±325.268\n", ++ "Rollout 2698/9766, Reward: 280.828±12.092, Episode_length: 245.700±101.634\n", ++ "Rollout 2699/9766, Reward: 282.642±13.930, Episode_length: 197.400±34.731\n", ++ "Rollout 2700/9766, Reward: 276.383±19.337, Episode_length: 203.500±37.641\n", ++ "Rollout 2701/9766, Reward: 284.512±20.403, Episode_length: 195.900±27.894\n", ++ "Rollout 2702/9766, Reward: 214.167±100.004, Episode_length: 191.300±27.964\n", ++ "Rollout 2703/9766, Reward: 236.044±53.850, Episode_length: 666.900±380.012\n", ++ "Rollout 2704/9766, Reward: 258.399±49.710, Episode_length: 512.500±390.565\n", ++ "Rollout 2705/9766, Reward: 278.033±16.499, Episode_length: 178.300±15.736\n", ++ "Rollout 2706/9766, Reward: 280.507±14.647, Episode_length: 219.600±71.662\n", ++ "Rollout 2707/9766, Reward: 284.796±11.953, Episode_length: 212.700±43.463\n", ++ "Rollout 2708/9766, Reward: 287.362±14.550, Episode_length: 204.400±29.176\n", ++ "Rollout 2709/9766, Reward: 263.777±32.933, Episode_length: 313.200±256.440\n", ++ "Rollout 2710/9766, Reward: 245.931±52.733, Episode_length: 583.800±336.087\n", ++ "Rollout 2711/9766, Reward: 268.395±46.651, Episode_length: 321.300±290.860\n", ++ "Rollout 2712/9766, Reward: 205.260±45.669, Episode_length: 853.400±211.561\n", ++ "Rollout 2713/9766, Reward: 244.948±41.505, Episode_length: 750.900±253.795\n", ++ "Rollout 2714/9766, Reward: 188.861±42.793, Episode_length: 840.400±319.261\n", ++ "Rollout 2715/9766, Reward: 182.149±73.420, Episode_length: 686.100±386.384\n", ++ "Rollout 2716/9766, Reward: 224.047±63.425, Episode_length: 591.200±408.931\n", ++ "Rollout 2717/9766, Reward: 259.934±38.027, Episode_length: 407.700±216.014\n", ++ "Rollout 2718/9766, Reward: 169.830±42.423, Episode_length: 949.600±151.200\n", ++ "Rollout 2719/9766, Reward: 255.750±38.612, Episode_length: 468.100±327.388\n", ++ "Rollout 2720/9766, Reward: 243.673±56.538, Episode_length: 584.500±360.015\n", ++ "Rollout 2721/9766, Reward: 261.088±10.504, Episode_length: 271.500±135.665\n", ++ "Rollout 2722/9766, Reward: 245.586±45.341, Episode_length: 515.300±345.150\n", ++ "Rollout 2723/9766, Reward: 255.413±45.679, Episode_length: 557.900±300.907\n", ++ "Rollout 2724/9766, Reward: 248.240±43.129, Episode_length: 474.100±359.506\n", ++ "Rollout 2725/9766, Reward: 263.125±23.822, Episode_length: 265.300±114.982\n", ++ "Rollout 2726/9766, Reward: 268.849±16.682, Episode_length: 207.900±50.968\n", ++ "Rollout 2727/9766, Reward: 248.604±42.279, Episode_length: 334.200±237.455\n", ++ "Rollout 2728/9766, Reward: 248.259±32.618, Episode_length: 406.700±304.272\n", ++ "Rollout 2729/9766, Reward: 235.279±47.774, Episode_length: 351.100±299.888\n", ++ "Rollout 2730/9766, Reward: 239.913±81.305, Episode_length: 363.700±293.158\n", ++ "Rollout 2731/9766, Reward: 227.302±94.265, Episode_length: 268.800±103.335\n", ++ "Rollout 2732/9766, Reward: 248.212±39.710, Episode_length: 338.900±239.294\n", ++ "Rollout 2733/9766, Reward: 231.102±73.243, Episode_length: 385.300±275.880\n", ++ "Rollout 2734/9766, Reward: 249.777±30.017, Episode_length: 235.300±124.216\n", ++ "Rollout 2735/9766, Reward: 185.504±94.065, Episode_length: 530.500±333.102\n", ++ "Rollout 2736/9766, Reward: 246.900±26.107, Episode_length: 238.400±70.742\n", ++ "Rollout 2737/9766, Reward: 244.642±47.320, Episode_length: 359.900±220.911\n", ++ "Rollout 2738/9766, Reward: 186.192±108.302, Episode_length: 374.400±245.635\n", ++ "Rollout 2739/9766, Reward: 228.989±57.074, Episode_length: 447.000±362.567\n", ++ "Rollout 2740/9766, Reward: 227.219±47.634, Episode_length: 344.900±239.691\n", ++ "Rollout 2741/9766, Reward: 263.935±28.481, Episode_length: 255.600±180.942\n", ++ "Rollout 2742/9766, Reward: 233.214±46.817, Episode_length: 399.600±282.244\n", ++ "Rollout 2743/9766, Reward: 263.188±44.228, Episode_length: 309.800±233.884\n", ++ "Rollout 2744/9766, Reward: 245.232±37.763, Episode_length: 247.400±100.778\n", ++ "Rollout 2745/9766, Reward: 278.556±20.036, Episode_length: 222.200±27.125\n", ++ "Rollout 2746/9766, Reward: 248.543±48.882, Episode_length: 377.700±314.151\n", ++ "Rollout 2747/9766, Reward: 258.526±23.390, Episode_length: 316.500±218.370\n", ++ "Rollout 2748/9766, Reward: 246.442±54.630, Episode_length: 310.900±236.616\n", ++ "Rollout 2749/9766, Reward: 257.269±47.942, Episode_length: 361.400±286.384\n", ++ "Rollout 2750/9766, Reward: 244.235±48.718, Episode_length: 342.700±245.287\n", ++ "Rollout 2751/9766, Reward: 246.507±59.027, Episode_length: 348.400±268.086\n", ++ "Rollout 2752/9766, Reward: 235.826±37.054, Episode_length: 375.400±218.945\n", ++ "Rollout 2753/9766, Reward: 218.482±56.088, Episode_length: 473.600±294.953\n", ++ "Rollout 2754/9766, Reward: 232.034±51.567, Episode_length: 340.000±268.891\n", ++ "Rollout 2755/9766, Reward: 230.587±57.719, Episode_length: 417.200±231.012\n", ++ "Rollout 2756/9766, Reward: 234.546±52.515, Episode_length: 369.300±235.024\n", ++ "Rollout 2757/9766, Reward: 198.428±110.368, Episode_length: 333.000±236.395\n", ++ "Rollout 2758/9766, Reward: 242.280±49.381, Episode_length: 322.500±229.108\n", ++ "Rollout 2759/9766, Reward: 207.590±53.553, Episode_length: 443.400±223.718\n", ++ "Rollout 2760/9766, Reward: 242.555±28.951, Episode_length: 280.100±179.040\n", ++ "Rollout 2761/9766, Reward: 204.118±63.302, Episode_length: 556.600±355.274\n", ++ "Rollout 2762/9766, Reward: 220.433±75.228, Episode_length: 526.500±367.219\n", ++ "Rollout 2763/9766, Reward: 231.869±66.672, Episode_length: 374.400±315.061\n", ++ "Rollout 2764/9766, Reward: 236.133±43.641, Episode_length: 368.400±241.943\n", ++ "Rollout 2765/9766, Reward: 243.826±49.102, Episode_length: 382.800±295.783\n", ++ "Rollout 2766/9766, Reward: 257.332±17.211, Episode_length: 206.400±16.335\n", ++ "Rollout 2767/9766, Reward: 237.009±57.680, Episode_length: 371.900±315.323\n", ++ "Rollout 2768/9766, Reward: 254.024±46.204, Episode_length: 318.700±232.823\n", ++ "Rollout 2769/9766, Reward: 196.979±122.527, Episode_length: 199.400±47.767\n", ++ "Rollout 2770/9766, Reward: 185.500±135.636, Episode_length: 446.000±294.807\n", ++ "Rollout 2771/9766, Reward: 235.809±47.917, Episode_length: 320.400±230.032\n", ++ "Rollout 2772/9766, Reward: 211.782±66.905, Episode_length: 450.200±360.288\n", ++ "Rollout 2773/9766, Reward: 241.165±53.610, Episode_length: 371.300±223.679\n", ++ "Rollout 2774/9766, Reward: 244.202±45.635, Episode_length: 372.800±221.767\n", ++ "Rollout 2775/9766, Reward: 183.258±84.743, Episode_length: 506.700±332.515\n", ++ "Rollout 2776/9766, Reward: 236.842±44.723, Episode_length: 312.500±233.727\n", ++ "Rollout 2777/9766, Reward: 185.525±96.671, Episode_length: 486.900±302.146\n", ++ "Rollout 2778/9766, Reward: 242.862±29.759, Episode_length: 253.200±44.830\n", ++ "Rollout 2779/9766, Reward: 221.564±40.826, Episode_length: 324.800±228.636\n", ++ "Rollout 2780/9766, Reward: 229.059±44.065, Episode_length: 350.000±239.130\n", ++ "Rollout 2781/9766, Reward: 220.758±57.081, Episode_length: 405.800±298.685\n", ++ "Rollout 2782/9766, Reward: 237.999±39.199, Episode_length: 316.100±229.868\n", ++ "Rollout 2783/9766, Reward: 228.781±82.597, Episode_length: 323.500±234.711\n", ++ "Rollout 2784/9766, Reward: 258.036±46.376, Episode_length: 293.600±235.995\n", ++ "Rollout 2785/9766, Reward: 235.185±59.915, Episode_length: 384.100±308.251\n", ++ "Rollout 2786/9766, Reward: 250.592±39.820, Episode_length: 317.300±235.310\n", ++ "Rollout 2787/9766, Reward: 239.623±46.987, Episode_length: 487.400±293.334\n", ++ "Rollout 2788/9766, Reward: 221.150±69.396, Episode_length: 441.800±365.938\n", ++ "Rollout 2789/9766, Reward: 266.296±18.887, Episode_length: 231.600±51.463\n", ++ "Rollout 2790/9766, Reward: 259.307±37.271, Episode_length: 293.000±236.275\n", ++ "Rollout 2791/9766, Reward: 250.664±56.250, Episode_length: 277.600±242.271\n", ++ "Rollout 2792/9766, Reward: 248.718±60.453, Episode_length: 366.900±317.194\n", ++ "Rollout 2793/9766, Reward: 262.730±32.758, Episode_length: 299.300±238.696\n", ++ "Rollout 2794/9766, Reward: 207.818±141.879, Episode_length: 364.500±318.441\n", ++ "Rollout 2795/9766, Reward: 271.269±21.742, Episode_length: 192.200±17.040\n", ++ "Rollout 2796/9766, Reward: 266.152±13.334, Episode_length: 183.000±18.221\n", ++ "Rollout 2797/9766, Reward: 276.786±16.828, Episode_length: 200.600±24.703\n", ++ "Rollout 2798/9766, Reward: 266.272±20.678, Episode_length: 206.000±43.394\n", ++ "Rollout 2799/9766, Reward: 249.440±47.582, Episode_length: 385.500±308.339\n", ++ "Rollout 2800/9766, Reward: 261.767±34.203, Episode_length: 296.100±237.303\n", ++ "Rollout 2801/9766, Reward: 222.499±144.850, Episode_length: 191.500±36.277\n", ++ "Rollout 2802/9766, Reward: 257.854±36.643, Episode_length: 340.900±277.706\n", ++ "Rollout 2803/9766, Reward: 228.780±53.684, Episode_length: 364.800±318.291\n", ++ "Rollout 2804/9766, Reward: 261.269±38.433, Episode_length: 289.000±239.185\n", ++ "Rollout 2805/9766, Reward: 274.881±12.633, Episode_length: 197.300±16.007\n", ++ "Rollout 2806/9766, Reward: 220.642±108.913, Episode_length: 354.100±324.207\n", ++ "Rollout 2807/9766, Reward: 270.800±26.911, Episode_length: 205.300±23.900\n", ++ "Rollout 2808/9766, Reward: 274.264±33.355, Episode_length: 289.500±237.636\n", ++ "Rollout 2809/9766, Reward: 272.370±15.034, Episode_length: 181.800±15.689\n", ++ "Rollout 2810/9766, Reward: 278.115±16.775, Episode_length: 189.700±14.724\n", ++ "Rollout 2811/9766, Reward: 282.930±8.416, Episode_length: 191.000±21.503\n", ++ "Rollout 2812/9766, Reward: 281.694±17.533, Episode_length: 189.600±8.535\n", ++ "Rollout 2813/9766, Reward: 290.220±18.971, Episode_length: 208.400±21.667\n", ++ "Rollout 2814/9766, Reward: 276.836±18.858, Episode_length: 193.200±19.702\n", ++ "Rollout 2815/9766, Reward: 278.638±20.104, Episode_length: 192.900±19.414\n", ++ "Rollout 2816/9766, Reward: 278.695±19.419, Episode_length: 195.200±19.266\n", ++ "Rollout 2817/9766, Reward: 286.290±16.293, Episode_length: 194.800±19.104\n", ++ "Rollout 2818/9766, Reward: 291.228±17.429, Episode_length: 191.300±25.172\n", ++ "Rollout 2819/9766, Reward: 286.868±16.454, Episode_length: 191.700±19.779\n", ++ "Rollout 2820/9766, Reward: 273.599±21.481, Episode_length: 195.700±29.404\n", ++ "Rollout 2821/9766, Reward: 288.755±19.030, Episode_length: 199.300±22.199\n", ++ "Rollout 2822/9766, Reward: 291.050±17.318, Episode_length: 190.800±23.558\n", ++ "Rollout 2823/9766, Reward: 280.526±17.056, Episode_length: 181.300±19.622\n", ++ "Rollout 2824/9766, Reward: 279.866±16.511, Episode_length: 196.800±18.546\n", ++ "Rollout 2825/9766, Reward: 292.522±18.845, Episode_length: 200.500±24.043\n", ++ "Rollout 2826/9766, Reward: 270.309±17.493, Episode_length: 190.800±17.657\n", ++ "Rollout 2827/9766, Reward: 272.483±14.512, Episode_length: 194.700±21.340\n", ++ "Rollout 2828/9766, Reward: 280.183±13.641, Episode_length: 198.400±12.886\n", ++ "Rollout 2829/9766, Reward: 280.805±20.711, Episode_length: 193.500±22.105\n", ++ "Rollout 2830/9766, Reward: 283.204±18.613, Episode_length: 183.400±22.173\n", ++ "Rollout 2831/9766, Reward: 288.483±18.646, Episode_length: 193.700±15.369\n", ++ "Rollout 2832/9766, Reward: 288.718±17.833, Episode_length: 192.400±27.840\n", ++ "Rollout 2833/9766, Reward: 290.074±13.877, Episode_length: 199.700±22.909\n", ++ "Rollout 2834/9766, Reward: 289.456±16.794, Episode_length: 191.200±20.542\n", ++ "Rollout 2835/9766, Reward: 280.737±8.393, Episode_length: 185.200±13.797\n", ++ "Rollout 2836/9766, Reward: 284.494±13.499, Episode_length: 193.000±26.533\n", ++ "Rollout 2837/9766, Reward: 280.698±20.847, Episode_length: 192.200±35.411\n", ++ "Rollout 2838/9766, Reward: 291.468±21.456, Episode_length: 199.200±14.972\n", ++ "Rollout 2839/9766, Reward: 289.786±18.277, Episode_length: 198.300±17.556\n", ++ "Rollout 2840/9766, Reward: 288.560±13.680, Episode_length: 195.700±26.511\n", ++ "Rollout 2841/9766, Reward: 287.198±20.597, Episode_length: 182.200±24.244\n", ++ "Rollout 2842/9766, Reward: 272.569±15.799, Episode_length: 172.900±10.034\n", ++ "Rollout 2843/9766, Reward: 296.498±17.394, Episode_length: 199.500±27.119\n", ++ "Rollout 2844/9766, Reward: 293.304±20.719, Episode_length: 203.700±21.941\n", ++ "Rollout 2845/9766, Reward: 284.789±19.554, Episode_length: 192.600±14.228\n", ++ "Rollout 2846/9766, Reward: 280.797±24.164, Episode_length: 177.500±20.733\n", ++ "Rollout 2847/9766, Reward: 266.102±75.982, Episode_length: 183.500±26.466\n", ++ "Rollout 2848/9766, Reward: 275.812±16.252, Episode_length: 181.000±26.038\n", ++ "Rollout 2849/9766, Reward: 283.398±16.119, Episode_length: 179.400±18.288\n", ++ "Rollout 2850/9766, Reward: 280.278±12.291, Episode_length: 171.500±19.760\n", ++ "Rollout 2851/9766, Reward: 283.409±18.570, Episode_length: 176.700±18.510\n", ++ "Rollout 2852/9766, Reward: 274.753±21.069, Episode_length: 183.500±14.603\n", ++ "Rollout 2853/9766, Reward: 282.765±13.567, Episode_length: 200.100±21.874\n", ++ "Rollout 2854/9766, Reward: 286.619±16.996, Episode_length: 211.300±23.520\n", ++ "Rollout 2855/9766, Reward: 288.376±19.166, Episode_length: 197.000±22.834\n", ++ "Rollout 2856/9766, Reward: 280.686±20.772, Episode_length: 194.700±26.777\n", ++ "Rollout 2857/9766, Reward: 290.588±17.777, Episode_length: 204.200±14.892\n", ++ "Rollout 2858/9766, Reward: 281.059±19.978, Episode_length: 185.500±16.536\n", ++ "Rollout 2859/9766, Reward: 284.890±17.432, Episode_length: 204.600±20.353\n", ++ "Rollout 2860/9766, Reward: 278.387±18.193, Episode_length: 200.300±26.672\n", ++ "Rollout 2861/9766, Reward: 290.387±13.182, Episode_length: 202.900±22.598\n", ++ "Rollout 2862/9766, Reward: 291.283±15.773, Episode_length: 220.600±16.758\n", ++ "Rollout 2863/9766, Reward: 279.323±20.289, Episode_length: 204.800±24.429\n", ++ "Rollout 2864/9766, Reward: 282.320±10.539, Episode_length: 201.300±18.094\n", ++ "Rollout 2865/9766, Reward: 277.314±18.527, Episode_length: 207.900±22.612\n", ++ "Rollout 2866/9766, Reward: 284.487±16.100, Episode_length: 205.600±23.144\n", ++ "Rollout 2867/9766, Reward: 277.469±23.211, Episode_length: 206.700±11.270\n", ++ "Rollout 2868/9766, Reward: 287.253±18.014, Episode_length: 209.200±19.737\n", ++ "Rollout 2869/9766, Reward: 278.537±19.272, Episode_length: 202.400±20.051\n", ++ "Rollout 2870/9766, Reward: 288.680±19.907, Episode_length: 200.500±27.376\n", ++ "Rollout 2871/9766, Reward: 288.051±17.178, Episode_length: 194.500±26.246\n", ++ "Rollout 2872/9766, Reward: 287.459±17.004, Episode_length: 194.600±17.631\n", ++ "Rollout 2873/9766, Reward: 292.525±15.641, Episode_length: 195.800±24.819\n", ++ "Rollout 2874/9766, Reward: 287.126±16.036, Episode_length: 200.000±15.317\n", ++ "Rollout 2875/9766, Reward: 288.475±11.557, Episode_length: 180.100±12.405\n", ++ "Rollout 2876/9766, Reward: 292.060±12.386, Episode_length: 193.300±19.647\n", ++ "Rollout 2877/9766, Reward: 299.237±15.519, Episode_length: 213.400±26.729\n", ++ "Rollout 2878/9766, Reward: 290.528±18.184, Episode_length: 183.300±16.853\n", ++ "Rollout 2879/9766, Reward: 288.528±15.948, Episode_length: 192.000±15.053\n", ++ "Rollout 2880/9766, Reward: 279.540±24.380, Episode_length: 195.100±28.077\n", ++ "Rollout 2881/9766, Reward: 281.330±19.159, Episode_length: 190.700±15.786\n", ++ "Rollout 2882/9766, Reward: 282.996±14.492, Episode_length: 181.800±21.803\n", ++ "Rollout 2883/9766, Reward: 269.195±21.288, Episode_length: 185.000±16.492\n", ++ "Rollout 2884/9766, Reward: 283.250±13.386, Episode_length: 181.700±18.287\n", ++ "Rollout 2885/9766, Reward: 248.920±30.234, Episode_length: 258.100±247.688\n", ++ "Rollout 2886/9766, Reward: 260.906±43.606, Episode_length: 259.800±247.402\n", ++ "Rollout 2887/9766, Reward: 262.973±44.935, Episode_length: 263.400±246.267\n", ++ "Rollout 2888/9766, Reward: 283.080±15.345, Episode_length: 192.500±20.284\n", ++ "Rollout 2889/9766, Reward: 278.638±24.743, Episode_length: 188.800±21.535\n", ++ "Rollout 2890/9766, Reward: 278.755±13.096, Episode_length: 182.600±20.776\n", ++ "Rollout 2891/9766, Reward: 262.870±46.408, Episode_length: 262.300±246.367\n", ++ "Rollout 2892/9766, Reward: 271.041±18.458, Episode_length: 170.400±14.807\n", ++ "Rollout 2893/9766, Reward: 262.411±49.158, Episode_length: 298.600±243.436\n", ++ "Rollout 2894/9766, Reward: 250.752±37.938, Episode_length: 251.500±249.782\n", ++ "Rollout 2895/9766, Reward: 246.531±55.351, Episode_length: 354.500±323.320\n", ++ "Rollout 2896/9766, Reward: 255.294±46.215, Episode_length: 327.300±263.003\n", ++ "Rollout 2897/9766, Reward: 278.949±22.707, Episode_length: 240.600±68.678\n", ++ "Rollout 2898/9766, Reward: 250.293±45.949, Episode_length: 351.200±327.150\n", ++ "Rollout 2899/9766, Reward: 267.855±21.088, Episode_length: 246.800±73.435\n", ++ "Rollout 2900/9766, Reward: 248.477±48.071, Episode_length: 362.100±321.321\n", ++ "Rollout 2901/9766, Reward: 249.522±37.237, Episode_length: 280.200±242.214\n", ++ "Rollout 2902/9766, Reward: 259.688±59.483, Episode_length: 382.600±311.515\n", ++ "Rollout 2903/9766, Reward: 251.168±50.290, Episode_length: 457.000±353.038\n", ++ "Rollout 2904/9766, Reward: 266.125±38.667, Episode_length: 352.700±260.409\n", ++ "Rollout 2905/9766, Reward: 260.300±41.774, Episode_length: 306.400±240.072\n", ++ "Rollout 2906/9766, Reward: 254.206±48.009, Episode_length: 391.700±315.150\n", ++ "Rollout 2907/9766, Reward: 279.340±13.864, Episode_length: 211.700±27.225\n", ++ "Rollout 2908/9766, Reward: 272.203±16.819, Episode_length: 186.800±24.911\n", ++ "Rollout 2909/9766, Reward: 263.665±48.774, Episode_length: 284.200±240.127\n", ++ "Rollout 2910/9766, Reward: 284.728±15.157, Episode_length: 198.500±27.270\n", ++ "Rollout 2911/9766, Reward: 264.298±33.703, Episode_length: 273.600±243.417\n", ++ "Rollout 2912/9766, Reward: 284.721±20.258, Episode_length: 203.200±29.434\n", ++ "Rollout 2913/9766, Reward: 274.129±19.178, Episode_length: 196.900±11.528\n", ++ "Rollout 2914/9766, Reward: 286.161±16.422, Episode_length: 202.200±24.264\n", ++ "Rollout 2915/9766, Reward: 274.666±15.960, Episode_length: 182.300±20.095\n", ++ "Rollout 2916/9766, Reward: 269.004±19.167, Episode_length: 186.200±22.613\n", ++ "Rollout 2917/9766, Reward: 120.244±477.722, Episode_length: 204.800±32.860\n", ++ "Rollout 2918/9766, Reward: 284.080±17.666, Episode_length: 196.500±21.978\n", ++ "Rollout 2919/9766, Reward: 287.128±17.739, Episode_length: 199.100±17.740\n", ++ "Rollout 2920/9766, Reward: 286.905±17.745, Episode_length: 177.700±20.249\n", ++ "Rollout 2921/9766, Reward: 283.218±14.540, Episode_length: 174.100±24.403\n", ++ "Rollout 2922/9766, Reward: 146.078±394.173, Episode_length: 183.000±39.472\n", ++ "Rollout 2923/9766, Reward: 267.729±40.163, Episode_length: 265.800±246.925\n", ++ "Rollout 2924/9766, Reward: 275.507±19.325, Episode_length: 168.800±18.148\n", ++ "Rollout 2925/9766, Reward: 291.671±14.325, Episode_length: 192.900±34.619\n", ++ "Rollout 2926/9766, Reward: 278.015±20.330, Episode_length: 184.200±20.390\n", ++ "Rollout 2927/9766, Reward: 284.069±18.870, Episode_length: 171.700±21.661\n", ++ "Rollout 2928/9766, Reward: 289.011±16.140, Episode_length: 181.200±19.697\n", ++ "Rollout 2929/9766, Reward: 287.386±17.191, Episode_length: 182.900±21.598\n", ++ "Rollout 2930/9766, Reward: 287.524±18.725, Episode_length: 177.600±19.033\n", ++ "Rollout 2931/9766, Reward: 282.256±19.621, Episode_length: 172.000±17.692\n", ++ "Rollout 2932/9766, Reward: 284.025±14.568, Episode_length: 179.600±22.813\n", ++ "Rollout 2933/9766, Reward: 278.241±22.448, Episode_length: 185.500±24.225\n", ++ "Rollout 2934/9766, Reward: 281.463±23.233, Episode_length: 191.400±25.512\n", ++ "Rollout 2935/9766, Reward: 288.742±16.969, Episode_length: 181.200±26.784\n", ++ "Rollout 2936/9766, Reward: 292.613±17.816, Episode_length: 194.600±32.592\n", ++ "Rollout 2937/9766, Reward: 277.455±17.972, Episode_length: 176.700±23.148\n", ++ "Rollout 2938/9766, Reward: 291.442±18.678, Episode_length: 183.600±27.721\n", ++ "Rollout 2939/9766, Reward: 277.557±18.597, Episode_length: 183.700±26.019\n", ++ "Rollout 2940/9766, Reward: 270.750±20.354, Episode_length: 175.000±21.808\n", ++ "Rollout 2941/9766, Reward: 286.782±11.182, Episode_length: 170.500±23.771\n", ++ "Rollout 2942/9766, Reward: 280.971±18.819, Episode_length: 184.900±34.469\n", ++ "Rollout 2943/9766, Reward: 290.516±13.163, Episode_length: 200.000±28.691\n", ++ "Rollout 2944/9766, Reward: 285.316±20.165, Episode_length: 193.300±22.392\n", ++ "Rollout 2945/9766, Reward: 290.546±15.155, Episode_length: 192.800±28.760\n", ++ "Rollout 2946/9766, Reward: 278.834±13.554, Episode_length: 177.700±20.040\n", ++ "Rollout 2947/9766, Reward: 277.518±15.940, Episode_length: 191.800±26.324\n", ++ "Rollout 2948/9766, Reward: 289.792±14.934, Episode_length: 193.500±16.366\n", ++ "Rollout 2949/9766, Reward: 256.595±85.287, Episode_length: 176.500±36.555\n", ++ "Rollout 2950/9766, Reward: 292.533±9.599, Episode_length: 197.900±17.392\n", ++ "Rollout 2951/9766, Reward: 285.493±22.631, Episode_length: 205.700±33.918\n", ++ "Rollout 2952/9766, Reward: 284.499±12.009, Episode_length: 194.000±31.718\n", ++ "Rollout 2953/9766, Reward: 280.413±16.899, Episode_length: 183.300±19.152\n", ++ "Rollout 2954/9766, Reward: 284.952±24.722, Episode_length: 181.700±18.050\n", ++ "Rollout 2955/9766, Reward: 285.608±16.265, Episode_length: 182.300±25.632\n", ++ "Rollout 2956/9766, Reward: 273.769±20.657, Episode_length: 183.600±26.882\n", ++ "Rollout 2957/9766, Reward: 281.746±17.322, Episode_length: 182.500±20.786\n", ++ "Rollout 2958/9766, Reward: 279.348±16.511, Episode_length: 184.600±31.919\n", ++ "Rollout 2959/9766, Reward: 296.978±10.745, Episode_length: 208.000±32.072\n", ++ "Rollout 2960/9766, Reward: 284.999±14.983, Episode_length: 188.700±29.278\n", ++ "Rollout 2961/9766, Reward: 279.010±20.184, Episode_length: 184.500±26.960\n", ++ "Rollout 2962/9766, Reward: 288.664±16.523, Episode_length: 201.200±42.776\n", ++ "Rollout 2963/9766, Reward: 285.067±19.905, Episode_length: 189.800±29.684\n", ++ "Rollout 2964/9766, Reward: 270.946±14.716, Episode_length: 174.800±15.670\n", ++ "Rollout 2965/9766, Reward: 273.102±44.813, Episode_length: 273.600±244.408\n", ++ "Rollout 2966/9766, Reward: 284.064±19.564, Episode_length: 183.800±23.836\n", ++ "Rollout 2967/9766, Reward: 286.225±17.280, Episode_length: 183.100±18.245\n", ++ "Rollout 2968/9766, Reward: 293.673±7.590, Episode_length: 183.200±31.438\n", ++ "Rollout 2969/9766, Reward: 268.009±15.191, Episode_length: 179.900±24.184\n", ++ "Rollout 2970/9766, Reward: 259.990±37.670, Episode_length: 325.000±277.223\n", ++ "Rollout 2971/9766, Reward: 277.344±38.628, Episode_length: 277.500±242.230\n", ++ "Rollout 2972/9766, Reward: 266.473±36.932, Episode_length: 258.200±247.358\n", ++ "Rollout 2973/9766, Reward: 283.658±9.303, Episode_length: 183.900±26.838\n", ++ "Rollout 2974/9766, Reward: 290.490±13.679, Episode_length: 186.500±22.366\n", ++ "Rollout 2975/9766, Reward: 287.784±17.670, Episode_length: 192.000±24.884\n", ++ "Rollout 2976/9766, Reward: 286.668±20.142, Episode_length: 187.900±34.532\n", ++ "Rollout 2977/9766, Reward: 272.176±42.254, Episode_length: 266.800±246.179\n", ++ "Rollout 2978/9766, Reward: 283.721±20.444, Episode_length: 169.800±19.451\n", ++ "Rollout 2979/9766, Reward: 272.156±12.849, Episode_length: 165.000±13.513\n", ++ "Rollout 2980/9766, Reward: 286.088±20.218, Episode_length: 203.400±30.621\n", ++ "Rollout 2981/9766, Reward: 289.570±15.922, Episode_length: 204.700±43.126\n", ++ "Rollout 2982/9766, Reward: 273.834±18.803, Episode_length: 174.200±11.125\n", ++ "Rollout 2983/9766, Reward: 273.558±37.931, Episode_length: 276.300±244.715\n", ++ "Rollout 2984/9766, Reward: 280.522±13.115, Episode_length: 205.400±33.554\n", ++ "Rollout 2985/9766, Reward: 289.256±17.241, Episode_length: 209.100±23.881\n", ++ "Rollout 2986/9766, Reward: 278.686±16.458, Episode_length: 192.100±27.050\n", ++ "Rollout 2987/9766, Reward: 282.025±20.066, Episode_length: 191.300±25.620\n", ++ "Rollout 2988/9766, Reward: 281.345±19.792, Episode_length: 230.500±42.264\n", ++ "Rollout 2989/9766, Reward: 288.278±16.830, Episode_length: 192.000±23.614\n", ++ "Rollout 2990/9766, Reward: 286.069±13.174, Episode_length: 201.000±30.295\n", ++ "Rollout 2991/9766, Reward: 286.660±16.152, Episode_length: 194.700±26.104\n", ++ "Rollout 2992/9766, Reward: 271.429±20.043, Episode_length: 183.100±27.263\n", ++ "Rollout 2993/9766, Reward: 288.718±17.112, Episode_length: 185.000±33.496\n", ++ "Rollout 2994/9766, Reward: 262.986±21.300, Episode_length: 255.000±52.729\n", ++ "Rollout 2995/9766, Reward: 229.411±57.346, Episode_length: 485.300±348.191\n", ++ "Rollout 2996/9766, Reward: 255.508±32.000, Episode_length: 318.100±228.417\n", ++ "Rollout 2997/9766, Reward: 280.516±14.954, Episode_length: 237.600±24.225\n", ++ "Rollout 2998/9766, Reward: 285.072±19.766, Episode_length: 215.700±33.088\n", ++ "Rollout 2999/9766, Reward: 270.558±27.049, Episode_length: 248.400±30.871\n", ++ "Rollout 3000/9766, Reward: 267.001±18.974, Episode_length: 282.800±96.788\n", ++ "Rollout 3001/9766, Reward: 252.067±39.420, Episode_length: 301.300±235.660\n", ++ "Rollout 3002/9766, Reward: 286.374±19.322, Episode_length: 183.700±24.824\n", ++ "Rollout 3003/9766, Reward: 277.950±28.011, Episode_length: 174.000±23.152\n", ++ "Rollout 3004/9766, Reward: 282.308±11.061, Episode_length: 176.000±20.847\n", ++ "Rollout 3005/9766, Reward: 282.348±12.730, Episode_length: 183.900±23.973\n", ++ "Rollout 3006/9766, Reward: 282.721±19.887, Episode_length: 199.400±27.649\n", ++ "Rollout 3007/9766, Reward: 277.286±14.013, Episode_length: 167.100±19.583\n", ++ "Rollout 3008/9766, Reward: 263.592±53.266, Episode_length: 261.600±246.943\n", ++ "Rollout 3009/9766, Reward: 291.974±21.196, Episode_length: 179.600±24.088\n", ++ "Rollout 3010/9766, Reward: 288.462±13.702, Episode_length: 186.300±19.422\n", ++ "Rollout 3011/9766, Reward: 265.774±34.404, Episode_length: 223.000±125.294\n", ++ "Rollout 3012/9766, Reward: 280.664±20.594, Episode_length: 187.800±23.021\n", ++ "Rollout 3013/9766, Reward: 281.715±18.833, Episode_length: 176.500±31.810\n", ++ "Rollout 3014/9766, Reward: 276.320±35.817, Episode_length: 236.700±167.574\n", ++ "Rollout 3015/9766, Reward: 266.985±23.538, Episode_length: 200.300±90.134\n", ++ "Rollout 3016/9766, Reward: 289.449±13.920, Episode_length: 182.800±20.899\n", ++ "Rollout 3017/9766, Reward: 273.573±15.544, Episode_length: 173.100±21.806\n", ++ "Rollout 3018/9766, Reward: 286.775±21.439, Episode_length: 182.500±19.117\n", ++ "Rollout 3019/9766, Reward: 292.874±16.509, Episode_length: 200.000±31.559\n", ++ "Rollout 3020/9766, Reward: 272.831±35.379, Episode_length: 253.100±249.386\n", ++ "Rollout 3021/9766, Reward: 286.187±17.209, Episode_length: 194.300±25.788\n", ++ "Rollout 3022/9766, Reward: 279.539±17.831, Episode_length: 189.200±37.757\n", ++ "Rollout 3023/9766, Reward: 291.017±18.038, Episode_length: 191.600±25.267\n", ++ "Rollout 3024/9766, Reward: 286.459±17.797, Episode_length: 191.900±38.059\n", ++ "Rollout 3025/9766, Reward: 289.078±18.903, Episode_length: 190.200±26.999\n", ++ "Rollout 3026/9766, Reward: 283.429±22.039, Episode_length: 180.100±22.832\n", ++ "Rollout 3027/9766, Reward: 289.679±17.482, Episode_length: 193.400±27.814\n", ++ "Rollout 3028/9766, Reward: 264.220±43.858, Episode_length: 265.800±247.100\n", ++ "Rollout 3029/9766, Reward: 245.676±137.384, Episode_length: 241.300±139.174\n", ++ "Rollout 3030/9766, Reward: 284.053±13.704, Episode_length: 172.800±23.916\n", ++ "Rollout 3031/9766, Reward: 283.320±17.680, Episode_length: 193.500±25.279\n", ++ "Rollout 3032/9766, Reward: 291.750±9.738, Episode_length: 182.000±25.570\n", ++ "Rollout 3033/9766, Reward: 272.341±23.240, Episode_length: 185.900±21.187\n", ++ "Rollout 3034/9766, Reward: 270.966±23.992, Episode_length: 192.300±83.633\n", ++ "Rollout 3035/9766, Reward: 243.855±79.948, Episode_length: 221.100±158.242\n", ++ "Rollout 3036/9766, Reward: 278.209±24.900, Episode_length: 233.200±130.678\n", ++ "Rollout 3037/9766, Reward: 273.596±19.333, Episode_length: 175.800±20.610\n", ++ "Rollout 3038/9766, Reward: 284.166±20.588, Episode_length: 175.600±24.695\n", ++ "Rollout 3039/9766, Reward: 266.266±53.459, Episode_length: 272.000±243.848\n", ++ "Rollout 3040/9766, Reward: 290.819±18.033, Episode_length: 179.300±21.601\n", ++ "Rollout 3041/9766, Reward: 290.383±12.128, Episode_length: 191.400±24.864\n", ++ "Rollout 3042/9766, Reward: 288.999±15.767, Episode_length: 206.600±30.240\n", ++ "Rollout 3043/9766, Reward: 287.641±13.984, Episode_length: 193.900±28.423\n", ++ "Rollout 3044/9766, Reward: 298.625±9.897, Episode_length: 222.900±25.473\n", ++ "Rollout 3045/9766, Reward: 292.276±11.824, Episode_length: 211.400±34.837\n", ++ "Rollout 3046/9766, Reward: 292.806±12.136, Episode_length: 202.600±21.261\n", ++ "Rollout 3047/9766, Reward: 272.980±9.327, Episode_length: 179.200±28.174\n", ++ "Rollout 3048/9766, Reward: 281.537±18.344, Episode_length: 203.900±34.512\n", ++ "Rollout 3049/9766, Reward: 277.676±18.591, Episode_length: 183.000±26.948\n", ++ "Rollout 3050/9766, Reward: 276.935±21.650, Episode_length: 197.200±29.580\n", ++ "Rollout 3051/9766, Reward: 281.068±12.560, Episode_length: 186.300±34.156\n", ++ "Rollout 3052/9766, Reward: 289.431±18.235, Episode_length: 203.600±27.321\n", ++ "Rollout 3053/9766, Reward: 272.923±19.051, Episode_length: 179.200±19.240\n", ++ "Rollout 3054/9766, Reward: 291.169±18.881, Episode_length: 214.400±28.970\n", ++ "Rollout 3055/9766, Reward: 286.309±24.826, Episode_length: 195.400±26.215\n", ++ "Rollout 3056/9766, Reward: 284.855±15.061, Episode_length: 196.800±14.490\n", ++ "Rollout 3057/9766, Reward: 276.818±17.415, Episode_length: 189.600±25.687\n", ++ "Rollout 3058/9766, Reward: 292.410±22.066, Episode_length: 205.600±30.536\n", ++ "Rollout 3059/9766, Reward: 276.200±17.925, Episode_length: 197.700±39.451\n", ++ "Rollout 3060/9766, Reward: 288.964±13.075, Episode_length: 191.200±17.389\n", ++ "Rollout 3061/9766, Reward: 284.231±21.301, Episode_length: 190.200±15.791\n", ++ "Rollout 3062/9766, Reward: 283.024±22.500, Episode_length: 191.300±26.035\n", ++ "Rollout 3063/9766, Reward: 286.821±16.460, Episode_length: 192.700±29.739\n", ++ "Rollout 3064/9766, Reward: 276.358±14.598, Episode_length: 185.300±32.168\n", ++ "Rollout 3065/9766, Reward: 273.528±22.912, Episode_length: 182.900±26.737\n", ++ "Rollout 3066/9766, Reward: 276.157±19.549, Episode_length: 189.200±24.012\n", ++ "Rollout 3067/9766, Reward: 290.424±19.105, Episode_length: 189.700±23.979\n", ++ "Rollout 3068/9766, Reward: 281.503±22.194, Episode_length: 189.200±21.715\n", ++ "Rollout 3069/9766, Reward: 273.890±32.592, Episode_length: 245.500±132.096\n", ++ "Rollout 3070/9766, Reward: 289.243±18.479, Episode_length: 201.800±17.256\n", ++ "Rollout 3071/9766, Reward: 281.406±19.012, Episode_length: 193.600±27.325\n", ++ "Rollout 3072/9766, Reward: 283.691±20.744, Episode_length: 192.400±29.114\n", ++ "Rollout 3073/9766, Reward: 283.843±18.009, Episode_length: 181.000±29.448\n", ++ "Rollout 3074/9766, Reward: 288.140±14.200, Episode_length: 184.300±18.270\n", ++ "Rollout 3075/9766, Reward: 281.454±17.489, Episode_length: 191.700±23.039\n", ++ "Rollout 3076/9766, Reward: 278.765±10.036, Episode_length: 179.700±22.415\n", ++ "Rollout 3077/9766, Reward: 285.104±20.182, Episode_length: 229.400±84.206\n", ++ "Rollout 3078/9766, Reward: 291.474±11.923, Episode_length: 197.800±18.088\n", ++ "Rollout 3079/9766, Reward: 270.539±22.115, Episode_length: 233.600±101.014\n", ++ "Rollout 3080/9766, Reward: 281.430±15.380, Episode_length: 202.200±16.744\n", ++ "Rollout 3081/9766, Reward: 285.516±16.308, Episode_length: 181.500±19.096\n", ++ "Rollout 3082/9766, Reward: 282.697±16.429, Episode_length: 181.700±26.253\n", ++ "Rollout 3083/9766, Reward: 285.818±14.117, Episode_length: 186.500±22.420\n", ++ "Rollout 3084/9766, Reward: 280.818±21.293, Episode_length: 187.900±27.384\n", ++ "Rollout 3085/9766, Reward: 281.104±16.529, Episode_length: 178.800±24.037\n", ++ "Rollout 3086/9766, Reward: 290.763±13.966, Episode_length: 179.400±20.200\n", ++ "Rollout 3087/9766, Reward: 269.164±32.615, Episode_length: 269.700±244.468\n", ++ "Rollout 3088/9766, Reward: 243.169±83.571, Episode_length: 182.000±45.385\n", ++ "Rollout 3089/9766, Reward: 280.189±22.687, Episode_length: 182.200±21.372\n", ++ "Rollout 3090/9766, Reward: 281.211±18.641, Episode_length: 260.900±221.410\n", ++ "Rollout 3091/9766, Reward: 286.117±11.915, Episode_length: 196.500±18.699\n", ++ "Rollout 3092/9766, Reward: 279.820±18.859, Episode_length: 180.300±22.468\n", ++ "Rollout 3093/9766, Reward: 252.700±85.755, Episode_length: 271.300±244.967\n", ++ "Rollout 3094/9766, Reward: 288.541±13.729, Episode_length: 188.700±32.035\n", ++ "Rollout 3095/9766, Reward: 271.302±37.402, Episode_length: 264.100±246.810\n", ++ "Rollout 3096/9766, Reward: 279.815±17.753, Episode_length: 183.400±30.447\n", ++ "Rollout 3097/9766, Reward: 285.250±18.417, Episode_length: 187.600±20.524\n", ++ "Rollout 3098/9766, Reward: 264.765±77.142, Episode_length: 188.500±22.313\n", ++ "Rollout 3099/9766, Reward: 282.103±19.755, Episode_length: 177.600±17.235\n", ++ "Rollout 3100/9766, Reward: 269.077±21.328, Episode_length: 244.400±168.769\n", ++ "Rollout 3101/9766, Reward: 278.063±16.089, Episode_length: 177.600±15.628\n", ++ "Rollout 3102/9766, Reward: 286.313±8.574, Episode_length: 184.600±17.834\n", ++ "Rollout 3103/9766, Reward: 282.517±17.117, Episode_length: 198.000±20.489\n", ++ "Rollout 3104/9766, Reward: 284.835±17.524, Episode_length: 181.000±21.349\n", ++ "Rollout 3105/9766, Reward: 291.376±18.181, Episode_length: 196.700±16.125\n", ++ "Rollout 3106/9766, Reward: 283.525±17.257, Episode_length: 184.200±17.520\n", ++ "Rollout 3107/9766, Reward: 288.878±19.247, Episode_length: 203.400±25.966\n", ++ "Rollout 3108/9766, Reward: 270.172±49.211, Episode_length: 271.400±243.746\n", ++ "Rollout 3109/9766, Reward: 277.731±17.857, Episode_length: 192.700±26.131\n", ++ "Rollout 3110/9766, Reward: 273.627±19.792, Episode_length: 181.200±19.317\n", ++ "Rollout 3111/9766, Reward: 283.672±16.979, Episode_length: 200.100±18.593\n", ++ "Rollout 3112/9766, Reward: 277.577±18.886, Episode_length: 175.300±14.554\n", ++ "Rollout 3113/9766, Reward: 287.355±21.971, Episode_length: 198.100±18.251\n", ++ "Rollout 3114/9766, Reward: 287.483±16.407, Episode_length: 194.000±27.306\n", ++ "Rollout 3115/9766, Reward: 286.987±12.991, Episode_length: 186.600±26.192\n", ++ "Rollout 3116/9766, Reward: 282.754±21.404, Episode_length: 173.600±22.446\n", ++ "Rollout 3117/9766, Reward: 272.598±20.125, Episode_length: 188.700±22.694\n", ++ "Rollout 3118/9766, Reward: 283.774±17.063, Episode_length: 193.000±29.927\n", ++ "Rollout 3119/9766, Reward: 273.623±17.706, Episode_length: 182.400±23.436\n", ++ "Rollout 3120/9766, Reward: 239.452±120.395, Episode_length: 195.600±20.578\n", ++ "Rollout 3121/9766, Reward: 278.035±24.191, Episode_length: 240.000±122.535\n", ++ "Rollout 3122/9766, Reward: 259.054±41.740, Episode_length: 302.100±264.635\n", ++ "Rollout 3123/9766, Reward: 289.426±16.795, Episode_length: 184.400±15.819\n", ++ "Rollout 3124/9766, Reward: 290.902±15.231, Episode_length: 187.900±24.255\n", ++ "Rollout 3125/9766, Reward: 294.913±14.395, Episode_length: 188.300±22.334\n", ++ "Rollout 3126/9766, Reward: 271.628±31.041, Episode_length: 206.500±110.579\n", ++ "Rollout 3127/9766, Reward: 276.294±29.364, Episode_length: 202.000±86.265\n", ++ "Rollout 3128/9766, Reward: 284.669±20.572, Episode_length: 185.900±24.044\n", ++ "Rollout 3129/9766, Reward: 294.200±16.261, Episode_length: 185.600±22.092\n", ++ "Rollout 3130/9766, Reward: 285.637±17.893, Episode_length: 244.100±160.924\n", ++ "Rollout 3131/9766, Reward: 285.644±20.094, Episode_length: 181.100±14.943\n", ++ "Rollout 3132/9766, Reward: 278.454±10.146, Episode_length: 177.800±15.497\n", ++ "Rollout 3133/9766, Reward: 295.286±17.330, Episode_length: 198.300±35.660\n", ++ "Rollout 3134/9766, Reward: 291.217±27.308, Episode_length: 238.600±142.573\n", ++ "Rollout 3135/9766, Reward: 282.327±12.178, Episode_length: 190.000±21.014\n", ++ "Rollout 3136/9766, Reward: 297.771±13.160, Episode_length: 179.900±26.410\n", ++ "Rollout 3137/9766, Reward: 281.799±21.114, Episode_length: 190.300±17.989\n", ++ "Rollout 3138/9766, Reward: 281.509±19.376, Episode_length: 190.300±22.654\n", ++ "Rollout 3139/9766, Reward: 273.323±23.065, Episode_length: 185.400±17.878\n", ++ "Rollout 3140/9766, Reward: 289.779±11.820, Episode_length: 229.100±58.731\n", ++ "Rollout 3141/9766, Reward: 279.689±13.959, Episode_length: 183.300±31.267\n", ++ "Rollout 3142/9766, Reward: 276.464±18.919, Episode_length: 187.800±22.618\n", ++ "Rollout 3143/9766, Reward: 281.298±17.099, Episode_length: 189.100±19.279\n", ++ "Rollout 3144/9766, Reward: 265.562±44.844, Episode_length: 271.200±243.652\n", ++ "Rollout 3145/9766, Reward: 283.284±16.255, Episode_length: 187.000±29.230\n", ++ "Rollout 3146/9766, Reward: 263.088±38.536, Episode_length: 278.700±241.665\n", ++ "Rollout 3147/9766, Reward: 284.761±12.306, Episode_length: 186.100±23.985\n", ++ "Rollout 3148/9766, Reward: 277.844±18.084, Episode_length: 181.900±19.552\n", ++ "Rollout 3149/9766, Reward: 282.250±24.622, Episode_length: 180.900±18.801\n", ++ "Rollout 3150/9766, Reward: 281.127±19.216, Episode_length: 188.600±20.665\n", ++ "Rollout 3151/9766, Reward: 269.660±15.910, Episode_length: 187.100±18.414\n", ++ "Rollout 3152/9766, Reward: 278.569±15.556, Episode_length: 181.600±22.495\n", ++ "Rollout 3153/9766, Reward: 284.671±16.797, Episode_length: 204.000±28.014\n", ++ "Rollout 3154/9766, Reward: 285.547±20.021, Episode_length: 178.600±13.771\n", ++ "Rollout 3155/9766, Reward: 274.532±54.140, Episode_length: 276.900±241.753\n", ++ "Rollout 3156/9766, Reward: 279.429±19.521, Episode_length: 188.400±21.606\n", ++ "Rollout 3157/9766, Reward: 285.738±15.928, Episode_length: 186.500±20.641\n", ++ "Rollout 3158/9766, Reward: 262.109±42.139, Episode_length: 349.200±325.760\n", ++ "Rollout 3159/9766, Reward: 291.083±15.336, Episode_length: 192.200±16.600\n", ++ "Rollout 3160/9766, Reward: 288.923±22.112, Episode_length: 192.600±20.358\n", ++ "Rollout 3161/9766, Reward: 264.202±67.691, Episode_length: 187.600±17.979\n", ++ "Rollout 3162/9766, Reward: 285.082±17.476, Episode_length: 207.000±22.009\n", ++ "Rollout 3163/9766, Reward: 272.379±13.470, Episode_length: 249.300±204.873\n", ++ "Rollout 3164/9766, Reward: 269.725±43.955, Episode_length: 271.600±242.998\n", ++ "Rollout 3165/9766, Reward: 277.355±18.834, Episode_length: 188.300±25.187\n", ++ "Rollout 3166/9766, Reward: 282.025±14.445, Episode_length: 199.200±20.942\n", ++ "Rollout 3167/9766, Reward: 275.228±32.916, Episode_length: 275.900±242.005\n", ++ "Rollout 3168/9766, Reward: 291.849±15.294, Episode_length: 195.300±15.499\n", ++ "Rollout 3169/9766, Reward: 285.720±18.152, Episode_length: 189.200±19.219\n", ++ "Rollout 3170/9766, Reward: 290.823±18.028, Episode_length: 206.300±19.473\n", ++ "Rollout 3171/9766, Reward: 294.453±15.984, Episode_length: 206.300±16.589\n", ++ "Rollout 3172/9766, Reward: 283.316±17.913, Episode_length: 193.200±29.253\n", ++ "Rollout 3173/9766, Reward: 286.435±16.196, Episode_length: 204.200±23.332\n", ++ "Rollout 3174/9766, Reward: 284.019±18.013, Episode_length: 193.300±18.574\n", ++ "Rollout 3175/9766, Reward: 291.988±16.495, Episode_length: 197.900±23.364\n", ++ "Rollout 3176/9766, Reward: 288.862±18.962, Episode_length: 199.300±24.413\n", ++ "Rollout 3177/9766, Reward: 279.474±20.088, Episode_length: 183.400±25.001\n", ++ "Rollout 3178/9766, Reward: 282.727±23.454, Episode_length: 254.500±178.425\n", ++ "Rollout 3179/9766, Reward: 292.558±12.893, Episode_length: 195.600±30.256\n", ++ "Rollout 3180/9766, Reward: 281.893±15.425, Episode_length: 181.600±25.711\n", ++ "Rollout 3181/9766, Reward: 273.638±19.362, Episode_length: 241.900±197.254\n", ++ "Rollout 3182/9766, Reward: 259.969±51.239, Episode_length: 348.500±326.407\n", ++ "Rollout 3183/9766, Reward: 289.998±14.184, Episode_length: 201.000±19.225\n", ++ "Rollout 3184/9766, Reward: 287.803±17.936, Episode_length: 180.300±12.915\n", ++ "Rollout 3185/9766, Reward: 271.860±36.190, Episode_length: 261.000±246.944\n", ++ "Rollout 3186/9766, Reward: 205.143±55.241, Episode_length: 747.800±385.251\n", ++ "Rollout 3187/9766, Reward: 287.801±19.709, Episode_length: 179.600±20.373\n", ++ "Rollout 3188/9766, Reward: 303.162±10.716, Episode_length: 184.400±15.920\n", ++ "Rollout 3189/9766, Reward: 282.252±13.046, Episode_length: 181.400±20.848\n", ++ "Rollout 3190/9766, Reward: 287.714±22.363, Episode_length: 195.000±23.728\n", ++ "Rollout 3191/9766, Reward: 283.242±20.111, Episode_length: 184.400±22.069\n", ++ "Rollout 3192/9766, Reward: 277.703±16.847, Episode_length: 190.100±28.073\n", ++ "Rollout 3193/9766, Reward: 283.120±22.703, Episode_length: 179.700±16.853\n", ++ "Rollout 3194/9766, Reward: 290.148±19.455, Episode_length: 198.100±29.565\n", ++ "Rollout 3195/9766, Reward: 277.945±13.936, Episode_length: 177.000±23.173\n", ++ "Rollout 3196/9766, Reward: 260.095±43.958, Episode_length: 522.100±376.639\n", ++ "Rollout 3197/9766, Reward: 242.958±52.936, Episode_length: 490.900±396.103\n", ++ "Rollout 3198/9766, Reward: 260.624±29.837, Episode_length: 253.200±249.326\n", ++ "Rollout 3199/9766, Reward: 258.088±31.821, Episode_length: 431.800±330.357\n", ++ "Rollout 3200/9766, Reward: 276.749±36.365, Episode_length: 269.400±245.049\n", ++ "Rollout 3201/9766, Reward: 284.660±16.491, Episode_length: 179.700±21.471\n", ++ "Rollout 3202/9766, Reward: 238.205±48.268, Episode_length: 507.200±402.423\n", ++ "Rollout 3203/9766, Reward: 252.812±53.570, Episode_length: 432.000±373.173\n", ++ "Rollout 3204/9766, Reward: 203.204±52.732, Episode_length: 754.500±375.128\n", ++ "Rollout 3205/9766, Reward: 268.034±18.526, Episode_length: 321.900±60.356\n", ++ "Rollout 3206/9766, Reward: 227.373±58.703, Episode_length: 709.900±349.498\n", ++ "Rollout 3207/9766, Reward: 211.799±60.526, Episode_length: 651.100±386.447\n", ++ "Rollout 3208/9766, Reward: 215.380±61.178, Episode_length: 603.100±397.057\n", ++ "Rollout 3209/9766, Reward: 258.811±30.579, Episode_length: 261.700±247.566\n", ++ "Rollout 3210/9766, Reward: 211.039±49.232, Episode_length: 766.000±357.502\n", ++ "Rollout 3211/9766, Reward: 277.724±30.592, Episode_length: 269.600±244.598\n", ++ "Rollout 3212/9766, Reward: 261.718±39.570, Episode_length: 355.700±322.499\n", ++ "Rollout 3213/9766, Reward: 234.452±55.060, Episode_length: 428.900±374.062\n", ++ "Rollout 3214/9766, Reward: 281.180±21.484, Episode_length: 207.300±58.210\n", ++ "Rollout 3215/9766, Reward: 281.370±13.537, Episode_length: 327.000±301.697\n", ++ "Rollout 3216/9766, Reward: 265.627±38.940, Episode_length: 355.200±323.295\n", ++ "Rollout 3217/9766, Reward: 255.008±37.652, Episode_length: 365.800±318.243\n", ++ "Rollout 3218/9766, Reward: 263.521±43.050, Episode_length: 284.900±239.925\n", ++ "Rollout 3219/9766, Reward: 270.348±38.560, Episode_length: 330.400±295.866\n", ++ "Rollout 3220/9766, Reward: 263.701±37.297, Episode_length: 445.700±343.808\n", ++ "Rollout 3221/9766, Reward: 255.465±52.105, Episode_length: 359.800±320.374\n", ++ "Rollout 3222/9766, Reward: 233.094±80.704, Episode_length: 356.900±322.738\n", ++ "Rollout 3223/9766, Reward: 272.001±37.645, Episode_length: 294.300±238.397\n", ++ "Rollout 3224/9766, Reward: 244.332±58.617, Episode_length: 432.000±372.859\n", ++ "Rollout 3225/9766, Reward: 270.663±28.700, Episode_length: 274.500±242.888\n", ++ "Rollout 3226/9766, Reward: 285.241±14.087, Episode_length: 200.000±25.694\n", ++ "Rollout 3227/9766, Reward: 284.092±12.473, Episode_length: 221.900±36.209\n", ++ "Rollout 3228/9766, Reward: 244.136±64.996, Episode_length: 351.500±324.913\n", ++ "Rollout 3229/9766, Reward: 277.467±18.018, Episode_length: 189.200±19.114\n", ++ "Rollout 3230/9766, Reward: 279.370±20.366, Episode_length: 199.900±16.640\n", ++ "Rollout 3231/9766, Reward: 219.474±137.462, Episode_length: 223.100±135.208\n", ++ "Rollout 3232/9766, Reward: 261.144±27.680, Episode_length: 261.100±246.938\n", ++ "Rollout 3233/9766, Reward: 261.549±36.830, Episode_length: 263.600±246.366\n", ++ "Rollout 3234/9766, Reward: 279.746±18.128, Episode_length: 176.600±25.299\n", ++ "Rollout 3235/9766, Reward: 268.119±38.276, Episode_length: 231.800±132.474\n", ++ "Rollout 3236/9766, Reward: 237.815±70.460, Episode_length: 202.000±80.776\n", ++ "Rollout 3237/9766, Reward: 243.979±47.526, Episode_length: 510.200±400.229\n", ++ "Rollout 3238/9766, Reward: 227.894±58.899, Episode_length: 597.300±403.331\n", ++ "Rollout 3239/9766, Reward: 274.804±18.475, Episode_length: 194.700±42.266\n", ++ "Rollout 3240/9766, Reward: 282.502±16.115, Episode_length: 174.600±16.883\n", ++ "Rollout 3241/9766, Reward: 272.846±24.122, Episode_length: 184.400±27.204\n", ++ "Rollout 3242/9766, Reward: 277.936±20.547, Episode_length: 180.700±28.436\n", ++ "Rollout 3243/9766, Reward: 281.893±19.078, Episode_length: 182.000±23.152\n", ++ "Rollout 3244/9766, Reward: 280.118±34.236, Episode_length: 267.200±246.261\n", ++ "Rollout 3245/9766, Reward: 282.605±18.584, Episode_length: 189.200±19.041\n", ++ "Rollout 3246/9766, Reward: 213.251±63.018, Episode_length: 670.700±396.191\n", ++ "Rollout 3247/9766, Reward: 251.247±48.638, Episode_length: 344.300±328.208\n", ++ "Rollout 3248/9766, Reward: 267.688±54.364, Episode_length: 347.300±326.847\n", ++ "Rollout 3249/9766, Reward: 272.445±27.550, Episode_length: 181.400±55.173\n", ++ "Rollout 3250/9766, Reward: 247.995±41.388, Episode_length: 338.600±330.929\n", ++ "Rollout 3251/9766, Reward: 211.696±71.599, Episode_length: 683.600±388.524\n", ++ "Rollout 3252/9766, Reward: 149.055±237.050, Episode_length: 277.000±264.869\n", ++ "Rollout 3253/9766, Reward: -76.230±238.750, Episode_length: 286.700±361.149\n", ++ "Rollout 3254/9766, Reward: 127.557±203.582, Episode_length: 493.400±416.674\n", ++ "Rollout 3255/9766, Reward: 72.784±177.369, Episode_length: 563.200±439.407\n", ++ "Rollout 3256/9766, Reward: 144.735±156.840, Episode_length: 399.900±395.300\n", ++ "Rollout 3257/9766, Reward: 64.394±210.999, Episode_length: 134.700±67.411\n", ++ "Rollout 3258/9766, Reward: 69.251±132.672, Episode_length: 640.000±442.276\n", ++ "Rollout 3259/9766, Reward: 26.950±161.131, Episode_length: 373.500±412.781\n", ++ "Rollout 3260/9766, Reward: 17.158±197.606, Episode_length: 208.500±267.932\n", ++ "Rollout 3261/9766, Reward: 123.573±188.282, Episode_length: 289.100±304.711\n", ++ "Rollout 3262/9766, Reward: 192.700±125.988, Episode_length: 313.100±320.473\n", ++ "Rollout 3263/9766, Reward: -14.659±183.456, Episode_length: 280.000±362.412\n", ++ "Rollout 3264/9766, Reward: 198.237±158.833, Episode_length: 154.400±48.401\n", ++ "Rollout 3265/9766, Reward: 124.542±197.279, Episode_length: 143.400±66.363\n", ++ "Rollout 3266/9766, Reward: 197.118±165.882, Episode_length: 161.500±51.346\n", ++ "Rollout 3267/9766, Reward: 157.829±192.836, Episode_length: 143.900±44.928\n", ++ "Rollout 3268/9766, Reward: 155.388±184.091, Episode_length: 145.200±55.021\n", ++ "Rollout 3269/9766, Reward: 246.446±118.510, Episode_length: 179.800±44.425\n", ++ "Rollout 3270/9766, Reward: 187.515±167.067, Episode_length: 153.700±47.653\n", ++ "Rollout 3271/9766, Reward: 103.491±220.310, Episode_length: 143.600±59.817\n", ++ "Rollout 3272/9766, Reward: 166.759±194.842, Episode_length: 166.700±59.185\n", ++ "Rollout 3273/9766, Reward: 203.761±139.011, Episode_length: 324.000±338.800\n", ++ "Rollout 3274/9766, Reward: 86.916±216.844, Episode_length: 220.400±265.498\n", ++ "Rollout 3275/9766, Reward: 173.478±172.249, Episode_length: 238.900±257.032\n", ++ "Rollout 3276/9766, Reward: 179.780±129.672, Episode_length: 506.000±405.674\n", ++ "Rollout 3277/9766, Reward: 169.508±148.549, Episode_length: 350.200±331.550\n", ++ "Rollout 3278/9766, Reward: 78.028±210.381, Episode_length: 486.500±422.529\n", ++ "Rollout 3279/9766, Reward: 85.790±151.586, Episode_length: 559.700±441.776\n", ++ "Rollout 3280/9766, Reward: 220.975±102.532, Episode_length: 342.200±331.746\n", ++ "Rollout 3281/9766, Reward: 142.241±180.677, Episode_length: 223.000±263.653\n", ++ "Rollout 3282/9766, Reward: 221.826±123.351, Episode_length: 252.800±252.270\n", ++ "Rollout 3283/9766, Reward: 244.187±129.502, Episode_length: 177.900±42.810\n", ++ "Rollout 3284/9766, Reward: 234.529±112.206, Episode_length: 161.600±31.734\n", ++ "Rollout 3285/9766, Reward: 262.672±50.069, Episode_length: 348.600±326.336\n", ++ "Rollout 3286/9766, Reward: 262.917±28.133, Episode_length: 393.000±337.749\n", ++ "Rollout 3287/9766, Reward: 222.837±56.253, Episode_length: 699.400±371.452\n", ++ "Rollout 3288/9766, Reward: 246.453±46.003, Episode_length: 334.800±332.908\n", ++ "Rollout 3289/9766, Reward: 223.366±54.081, Episode_length: 536.500±390.640\n", ++ "Rollout 3290/9766, Reward: 210.852±66.660, Episode_length: 728.800±346.061\n", ++ "Rollout 3291/9766, Reward: 266.076±21.421, Episode_length: 235.200±40.987\n", ++ "Rollout 3292/9766, Reward: 222.987±57.937, Episode_length: 572.300±396.564\n", ++ "Rollout 3293/9766, Reward: 277.943±20.997, Episode_length: 306.000±104.319\n", ++ "Rollout 3294/9766, Reward: 251.468±48.238, Episode_length: 453.500±351.307\n", ++ "Rollout 3295/9766, Reward: 287.418±17.422, Episode_length: 199.200±29.212\n", ++ "Rollout 3296/9766, Reward: 293.611±11.513, Episode_length: 191.700±19.131\n", ++ "Rollout 3297/9766, Reward: 275.532±22.576, Episode_length: 302.400±254.613\n", ++ "Rollout 3298/9766, Reward: 281.385±21.501, Episode_length: 181.700±17.567\n", ++ "Rollout 3299/9766, Reward: 282.449±35.149, Episode_length: 266.800±245.107\n", ++ "Rollout 3300/9766, Reward: 281.340±19.984, Episode_length: 186.700±32.044\n", ++ "Rollout 3301/9766, Reward: 279.792±15.940, Episode_length: 181.200±27.763\n", ++ "Rollout 3302/9766, Reward: 286.675±16.347, Episode_length: 191.000±19.550\n", ++ "Rollout 3303/9766, Reward: 276.392±21.101, Episode_length: 176.900±15.070\n", ++ "Rollout 3304/9766, Reward: 46.284±683.098, Episode_length: 187.500±36.310\n", ++ "Rollout 3305/9766, Reward: 253.944±78.617, Episode_length: 261.700±246.878\n", ++ "Rollout 3306/9766, Reward: 278.508±20.560, Episode_length: 189.700±19.288\n", ++ "Rollout 3307/9766, Reward: 272.685±15.811, Episode_length: 169.900±16.646\n", ++ "Rollout 3308/9766, Reward: 263.481±21.728, Episode_length: 180.000±20.381\n", ++ "Rollout 3309/9766, Reward: 281.675±17.296, Episode_length: 199.000±28.093\n", ++ "Rollout 3310/9766, Reward: 288.789±23.639, Episode_length: 192.500±37.052\n", ++ "Rollout 3311/9766, Reward: 274.506±39.105, Episode_length: 262.700±120.681\n", ++ "Rollout 3312/9766, Reward: 276.006±19.550, Episode_length: 190.700±18.100\n", ++ "Rollout 3313/9766, Reward: 266.779±32.310, Episode_length: 230.500±108.153\n", ++ "Rollout 3314/9766, Reward: 281.927±16.028, Episode_length: 189.500±16.391\n", ++ "Rollout 3315/9766, Reward: 271.805±20.239, Episode_length: 186.900±19.614\n", ++ "Rollout 3316/9766, Reward: 266.978±19.313, Episode_length: 177.300±17.350\n", ++ "Rollout 3317/9766, Reward: 294.154±13.231, Episode_length: 223.800±30.721\n", ++ "Rollout 3318/9766, Reward: 267.243±17.655, Episode_length: 187.800±16.503\n", ++ "Rollout 3319/9766, Reward: 276.693±35.232, Episode_length: 285.400±239.137\n", ++ "Rollout 3320/9766, Reward: 282.559±10.227, Episode_length: 192.100±29.262\n", ++ "Rollout 3321/9766, Reward: 269.648±37.371, Episode_length: 302.100±239.745\n", ++ "Rollout 3322/9766, Reward: 225.732±54.354, Episode_length: 674.000±394.818\n", ++ "Rollout 3323/9766, Reward: 273.893±36.491, Episode_length: 354.700±293.541\n", ++ "Rollout 3324/9766, Reward: 277.316±49.762, Episode_length: 363.300±306.409\n", ++ "Rollout 3325/9766, Reward: 210.326±59.854, Episode_length: 782.100±322.278\n", ++ "Rollout 3326/9766, Reward: 189.996±60.933, Episode_length: 848.500±303.019\n", ++ "Rollout 3327/9766, Reward: 258.680±24.562, Episode_length: 492.000±98.484\n", ++ "Rollout 3328/9766, Reward: 169.801±14.126, Episode_length: 1000.000±0.000\n", ++ "Rollout 3329/9766, Reward: 168.217±11.513, Episode_length: 1000.000±0.000\n", ++ "Rollout 3330/9766, Reward: 162.823±19.393, Episode_length: 1000.000±0.000\n", ++ "Rollout 3331/9766, Reward: 269.288±37.111, Episode_length: 266.200±245.719\n", ++ "Rollout 3332/9766, Reward: 238.656±46.414, Episode_length: 527.900±370.255\n", ++ "Rollout 3333/9766, Reward: 277.208±33.257, Episode_length: 593.000±353.484\n", ++ "Rollout 3334/9766, Reward: 244.502±50.204, Episode_length: 572.200±397.507\n", ++ "Rollout 3335/9766, Reward: 236.875±47.754, Episode_length: 505.500±403.943\n", ++ "Rollout 3336/9766, Reward: 282.712±14.158, Episode_length: 311.000±265.191\n", ++ "Rollout 3337/9766, Reward: 252.831±52.302, Episode_length: 336.200±332.173\n", ++ "Rollout 3338/9766, Reward: 208.975±63.050, Episode_length: 753.100±371.765\n", ++ "Rollout 3339/9766, Reward: 257.647±45.037, Episode_length: 340.300±330.648\n", ++ "Rollout 3340/9766, Reward: 284.719±20.750, Episode_length: 195.900±58.021\n", ++ "Rollout 3341/9766, Reward: 280.998±17.837, Episode_length: 163.000±11.773\n", ++ "Rollout 3342/9766, Reward: 288.578±10.356, Episode_length: 172.400±18.473\n", ++ "Rollout 3343/9766, Reward: 229.420±148.208, Episode_length: 199.900±97.710\n", ++ "Rollout 3344/9766, Reward: 284.278±16.523, Episode_length: 175.200±12.528\n", ++ "Rollout 3345/9766, Reward: 289.410±19.120, Episode_length: 227.200±160.953\n", ++ "Rollout 3346/9766, Reward: 282.338±24.244, Episode_length: 168.600±23.196\n", ++ "Rollout 3347/9766, Reward: 285.857±16.734, Episode_length: 178.600±20.631\n", ++ "Rollout 3348/9766, Reward: 253.835±48.028, Episode_length: 338.500±331.162\n", ++ "Rollout 3349/9766, Reward: 278.538±43.577, Episode_length: 274.000±243.521\n", ++ "Rollout 3350/9766, Reward: 267.578±47.033, Episode_length: 257.000±248.833\n", ++ "Rollout 3351/9766, Reward: 243.212±62.569, Episode_length: 501.900±407.007\n", ++ "Rollout 3352/9766, Reward: 182.865±38.805, Episode_length: 915.300±254.100\n", ++ "Rollout 3353/9766, Reward: 243.879±55.798, Episode_length: 701.800±358.315\n", ++ "Rollout 3354/9766, Reward: 248.697±55.792, Episode_length: 491.100±379.073\n", ++ "Rollout 3355/9766, Reward: 245.687±58.283, Episode_length: 488.200±399.352\n", ++ "Rollout 3356/9766, Reward: 211.250±57.217, Episode_length: 667.900±406.756\n", ++ "Rollout 3357/9766, Reward: 242.916±53.789, Episode_length: 591.200±394.588\n", ++ "Rollout 3358/9766, Reward: 251.597±50.424, Episode_length: 604.500±362.703\n", ++ "Rollout 3359/9766, Reward: 232.347±61.280, Episode_length: 632.900±393.690\n", ++ "Rollout 3360/9766, Reward: 255.629±52.786, Episode_length: 421.000±379.604\n", ++ "Rollout 3361/9766, Reward: 253.904±52.903, Episode_length: 417.700±381.411\n", ++ "Rollout 3362/9766, Reward: 280.250±16.784, Episode_length: 243.000±213.508\n", ++ "Rollout 3363/9766, Reward: 284.521±16.495, Episode_length: 179.200±21.632\n", ++ "Rollout 3364/9766, Reward: 261.659±62.232, Episode_length: 432.900±371.391\n", ++ "Rollout 3365/9766, Reward: 256.646±50.801, Episode_length: 386.700±345.824\n", ++ "Rollout 3366/9766, Reward: 276.819±28.471, Episode_length: 259.400±247.648\n", ++ "Rollout 3367/9766, Reward: 276.623±46.374, Episode_length: 263.900±246.399\n", ++ "Rollout 3368/9766, Reward: 279.246±14.377, Episode_length: 238.600±202.192\n", ++ "Rollout 3369/9766, Reward: 288.737±10.773, Episode_length: 236.500±184.507\n", ++ "Rollout 3370/9766, Reward: 282.229±16.915, Episode_length: 175.900±37.927\n", ++ "Rollout 3371/9766, Reward: 284.698±27.794, Episode_length: 332.500±334.580\n", ++ "Rollout 3372/9766, Reward: 273.262±39.040, Episode_length: 352.600±324.002\n", ++ "Rollout 3373/9766, Reward: 238.289±55.340, Episode_length: 666.400±408.402\n", ++ "Rollout 3374/9766, Reward: 249.485±56.559, Episode_length: 528.500±381.037\n", ++ "Rollout 3375/9766, Reward: 269.260±38.946, Episode_length: 484.900±378.717\n", ++ "Rollout 3376/9766, Reward: 265.293±25.390, Episode_length: 301.100±283.068\n", ++ "Rollout 3377/9766, Reward: 202.609±55.299, Episode_length: 826.800±320.751\n", ++ "Rollout 3378/9766, Reward: 233.876±62.250, Episode_length: 823.200±301.529\n", ++ "Rollout 3379/9766, Reward: 221.333±65.268, Episode_length: 696.400±361.720\n", ++ "Rollout 3380/9766, Reward: 282.366±14.262, Episode_length: 179.800±15.873\n", ++ "Rollout 3381/9766, Reward: 278.002±35.465, Episode_length: 263.200±246.563\n", ++ "Rollout 3382/9766, Reward: 278.790±15.699, Episode_length: 184.500±20.076\n", ++ "Rollout 3383/9766, Reward: 280.947±19.534, Episode_length: 174.800±12.278\n", ++ "Rollout 3384/9766, Reward: 284.156±21.176, Episode_length: 183.600±26.908\n", ++ "Rollout 3385/9766, Reward: 288.046±17.409, Episode_length: 176.700±11.376\n", ++ "Rollout 3386/9766, Reward: 284.918±12.457, Episode_length: 177.300±17.234\n", ++ "Rollout 3387/9766, Reward: 290.634±16.031, Episode_length: 194.800±22.319\n", ++ "Rollout 3388/9766, Reward: 286.720±10.784, Episode_length: 196.000±26.138\n", ++ "Rollout 3389/9766, Reward: 270.996±15.079, Episode_length: 186.100±24.869\n", ++ "Rollout 3390/9766, Reward: 278.356±16.757, Episode_length: 177.100±27.844\n", ++ "Rollout 3391/9766, Reward: 283.754±22.918, Episode_length: 165.400±17.727\n", ++ "Rollout 3392/9766, Reward: 223.509±55.149, Episode_length: 591.900±408.264\n", ++ "Rollout 3393/9766, Reward: 256.600±46.773, Episode_length: 492.800±386.854\n", ++ "Rollout 3394/9766, Reward: 278.908±22.697, Episode_length: 300.700±244.757\n", ++ "Rollout 3395/9766, Reward: 263.022±41.955, Episode_length: 410.900±342.689\n", ++ "Rollout 3396/9766, Reward: 277.678±18.454, Episode_length: 246.000±177.688\n", ++ "Rollout 3397/9766, Reward: 286.231±14.724, Episode_length: 184.700±26.982\n", ++ "Rollout 3398/9766, Reward: 283.435±11.817, Episode_length: 186.000±21.772\n", ++ "Rollout 3399/9766, Reward: 254.284±37.446, Episode_length: 250.800±250.295\n", ++ "Rollout 3400/9766, Reward: 251.028±54.266, Episode_length: 347.100±326.811\n", ++ "Rollout 3401/9766, Reward: 277.725±20.109, Episode_length: 182.000±25.072\n", ++ "Rollout 3402/9766, Reward: 270.634±15.745, Episode_length: 168.600±21.818\n", ++ "Rollout 3403/9766, Reward: 262.544±37.018, Episode_length: 262.600±247.220\n", ++ "Rollout 3404/9766, Reward: 238.512±82.589, Episode_length: 222.300±119.512\n", ++ "Rollout 3405/9766, Reward: 225.250±89.066, Episode_length: 264.600±248.152\n", ++ "Rollout 3406/9766, Reward: 281.349±17.051, Episode_length: 175.800±17.781\n", ++ "Rollout 3407/9766, Reward: 269.982±17.780, Episode_length: 205.800±50.825\n", ++ "Rollout 3408/9766, Reward: 259.084±46.888, Episode_length: 272.100±243.735\n", ++ "Rollout 3409/9766, Reward: 279.258±25.198, Episode_length: 201.600±37.977\n", ++ "Rollout 3410/9766, Reward: 275.413±22.199, Episode_length: 234.600±159.280\n", ++ "Rollout 3411/9766, Reward: 282.566±17.271, Episode_length: 206.300±44.068\n", ++ "Rollout 3412/9766, Reward: 281.109±15.939, Episode_length: 184.400±24.561\n", ++ "Rollout 3413/9766, Reward: 278.344±17.406, Episode_length: 192.000±29.230\n", ++ "Rollout 3414/9766, Reward: 272.977±35.127, Episode_length: 312.200±270.689\n", ++ "Rollout 3415/9766, Reward: 233.483±86.731, Episode_length: 255.400±250.187\n", ++ "Rollout 3416/9766, Reward: 248.729±85.681, Episode_length: 179.100±36.292\n", ++ "Rollout 3417/9766, Reward: 275.273±25.170, Episode_length: 269.900±221.719\n", ++ "Rollout 3418/9766, Reward: 273.039±39.817, Episode_length: 270.200±245.035\n", ++ "Rollout 3419/9766, Reward: 277.207±20.090, Episode_length: 183.600±20.470\n", ++ "Rollout 3420/9766, Reward: 274.686±35.642, Episode_length: 270.000±244.214\n", ++ "Rollout 3421/9766, Reward: 243.760±54.069, Episode_length: 358.800±322.812\n", ++ "Rollout 3422/9766, Reward: 269.100±18.680, Episode_length: 189.700±25.108\n", ++ "Rollout 3423/9766, Reward: 248.598±39.054, Episode_length: 310.300±284.884\n", ++ "Rollout 3424/9766, Reward: 221.223±60.967, Episode_length: 550.900±375.944\n", ++ "Rollout 3425/9766, Reward: 227.618±57.577, Episode_length: 460.400±363.095\n", ++ "Rollout 3426/9766, Reward: 267.313±47.971, Episode_length: 289.200±238.729\n", ++ "Rollout 3427/9766, Reward: 224.773±42.608, Episode_length: 450.700±300.384\n", ++ "Rollout 3428/9766, Reward: 213.321±56.494, Episode_length: 504.800±372.959\n", ++ "Rollout 3429/9766, Reward: 222.482±48.324, Episode_length: 496.300±275.247\n", ++ "Rollout 3430/9766, Reward: 224.491±36.819, Episode_length: 531.800±231.282\n", ++ "Rollout 3431/9766, Reward: 225.253±50.106, Episode_length: 477.300±215.193\n", ++ "Rollout 3432/9766, Reward: 192.609±65.289, Episode_length: 738.100±349.714\n", ++ "Rollout 3433/9766, Reward: 216.218±52.900, Episode_length: 660.100±299.952\n", ++ "Rollout 3434/9766, Reward: 243.976±26.475, Episode_length: 453.400±215.154\n", ++ "Rollout 3435/9766, Reward: 205.748±63.791, Episode_length: 539.500±360.277\n", ++ "Rollout 3436/9766, Reward: 246.304±24.206, Episode_length: 334.200±148.732\n", ++ "Rollout 3437/9766, Reward: 210.954±72.799, Episode_length: 489.600±349.208\n", ++ "Rollout 3438/9766, Reward: 229.420±78.705, Episode_length: 440.500±367.442\n", ++ "Rollout 3439/9766, Reward: 259.139±51.551, Episode_length: 289.100±242.526\n", ++ "Rollout 3440/9766, Reward: 239.394±55.179, Episode_length: 406.100±276.053\n", ++ "Rollout 3441/9766, Reward: 261.816±11.786, Episode_length: 193.900±27.837\n", ++ "Rollout 3442/9766, Reward: 222.820±57.980, Episode_length: 409.800±310.704\n", ++ "Rollout 3443/9766, Reward: 247.358±77.881, Episode_length: 412.400±307.990\n", ++ "Rollout 3444/9766, Reward: 232.254±46.009, Episode_length: 405.900±247.421\n", ++ "Rollout 3445/9766, Reward: 222.547±74.342, Episode_length: 494.600±380.462\n", ++ "Rollout 3446/9766, Reward: 212.399±51.455, Episode_length: 531.800±333.499\n", ++ "Rollout 3447/9766, Reward: 211.111±72.425, Episode_length: 555.300±376.327\n", ++ "Rollout 3448/9766, Reward: 194.887±58.790, Episode_length: 664.400±299.471\n", ++ "Rollout 3449/9766, Reward: 223.492±55.659, Episode_length: 556.100±345.494\n", ++ "Rollout 3450/9766, Reward: 204.045±60.351, Episode_length: 654.800±358.244\n", ++ "Rollout 3451/9766, Reward: 214.711±47.714, Episode_length: 584.800±365.199\n", ++ "Rollout 3452/9766, Reward: 227.201±53.696, Episode_length: 438.300±322.269\n", ++ "Rollout 3453/9766, Reward: 231.883±35.782, Episode_length: 451.600±245.307\n", ++ "Rollout 3454/9766, Reward: 228.424±57.706, Episode_length: 421.800±335.452\n", ++ "Rollout 3455/9766, Reward: 212.965±63.038, Episode_length: 655.800±359.626\n", ++ "Rollout 3456/9766, Reward: 216.700±57.751, Episode_length: 552.300±342.986\n", ++ "Rollout 3457/9766, Reward: 229.654±55.463, Episode_length: 668.400±297.707\n", ++ "Rollout 3458/9766, Reward: 222.755±52.392, Episode_length: 473.500±353.164\n", ++ "Rollout 3459/9766, Reward: 225.106±50.133, Episode_length: 581.400±294.218\n", ++ "Rollout 3460/9766, Reward: 197.549±60.202, Episode_length: 578.200±284.811\n", ++ "Rollout 3461/9766, Reward: 197.473±75.891, Episode_length: 481.300±308.546\n", ++ "Rollout 3462/9766, Reward: 189.516±81.814, Episode_length: 560.400±356.627\n", ++ "Rollout 3463/9766, Reward: 217.674±45.749, Episode_length: 561.200±356.230\n", ++ "Rollout 3464/9766, Reward: 203.902±98.870, Episode_length: 523.900±299.682\n", ++ "Rollout 3465/9766, Reward: 195.371±129.129, Episode_length: 344.800±253.857\n", ++ "Rollout 3466/9766, Reward: 211.600±57.692, Episode_length: 570.400±357.764\n", ++ "Rollout 3467/9766, Reward: 205.625±40.537, Episode_length: 550.800±367.867\n", ++ "Rollout 3468/9766, Reward: 167.983±104.709, Episode_length: 496.700±344.710\n", ++ "Rollout 3469/9766, Reward: 229.269±61.285, Episode_length: 484.000±316.043\n", ++ "Rollout 3470/9766, Reward: 218.570±73.721, Episode_length: 446.900±326.618\n", ++ "Rollout 3471/9766, Reward: 210.285±68.483, Episode_length: 459.400±355.733\n", ++ "Rollout 3472/9766, Reward: 228.544±83.463, Episode_length: 398.500±303.606\n", ++ "Rollout 3473/9766, Reward: 218.303±59.547, Episode_length: 420.400±258.121\n", ++ "Rollout 3474/9766, Reward: 240.332±37.467, Episode_length: 449.300±248.061\n", ++ "Rollout 3475/9766, Reward: 222.711±59.658, Episode_length: 552.600±311.264\n", ++ "Rollout 3476/9766, Reward: 199.953±81.137, Episode_length: 529.600±361.974\n", ++ "Rollout 3477/9766, Reward: 209.828±60.371, Episode_length: 488.900±303.204\n", ++ "Rollout 3478/9766, Reward: 166.607±114.970, Episode_length: 580.600±307.411\n", ++ "Rollout 3479/9766, Reward: 228.762±27.200, Episode_length: 338.300±144.868\n", ++ "Rollout 3480/9766, Reward: 189.484±47.950, Episode_length: 589.300±231.715\n", ++ "Rollout 3481/9766, Reward: 169.417±71.105, Episode_length: 752.700±320.770\n", ++ "Rollout 3482/9766, Reward: 194.835±47.620, Episode_length: 738.300±245.561\n", ++ "Rollout 3483/9766, Reward: 221.933±54.974, Episode_length: 538.400±335.573\n", ++ "Rollout 3484/9766, Reward: 222.906±41.669, Episode_length: 579.300±311.749\n", ++ "Rollout 3485/9766, Reward: 200.233±58.579, Episode_length: 584.300±348.720\n", ++ "Rollout 3486/9766, Reward: 218.709±51.746, Episode_length: 495.900±351.381\n", ++ "Rollout 3487/9766, Reward: 233.691±53.067, Episode_length: 570.100±362.826\n", ++ "Rollout 3488/9766, Reward: 206.637±66.793, Episode_length: 588.300±319.372\n", ++ "Rollout 3489/9766, Reward: 276.264±20.526, Episode_length: 249.700±104.037\n", ++ "Rollout 3490/9766, Reward: 249.977±28.126, Episode_length: 446.300±225.189\n", ++ "Rollout 3491/9766, Reward: 248.232±45.302, Episode_length: 369.800±237.998\n", ++ "Rollout 3492/9766, Reward: 173.687±64.156, Episode_length: 824.200±299.228\n", ++ "Rollout 3493/9766, Reward: 256.997±22.254, Episode_length: 374.100±255.466\n", ++ "Rollout 3494/9766, Reward: 110.955±123.643, Episode_length: 789.100±275.082\n", ++ "Rollout 3495/9766, Reward: 228.748±71.798, Episode_length: 434.900±370.100\n", ++ "Rollout 3496/9766, Reward: 182.027±175.493, Episode_length: 269.500±130.995\n", ++ "Rollout 3497/9766, Reward: 181.668±111.361, Episode_length: 693.700±324.534\n", ++ "Rollout 3498/9766, Reward: 180.810±87.535, Episode_length: 538.800±382.825\n", ++ "Rollout 3499/9766, Reward: 253.604±34.957, Episode_length: 336.600±260.499\n", ++ "Rollout 3500/9766, Reward: 234.959±39.696, Episode_length: 415.600±273.795\n", ++ "Rollout 3501/9766, Reward: 216.766±62.674, Episode_length: 531.500±378.802\n", ++ "Rollout 3502/9766, Reward: 251.684±38.314, Episode_length: 357.800±223.296\n", ++ "Rollout 3503/9766, Reward: 183.025±56.807, Episode_length: 707.000±273.085\n", ++ "Rollout 3504/9766, Reward: 223.795±73.633, Episode_length: 355.800±299.290\n", ++ "Rollout 3505/9766, Reward: 184.452±81.548, Episode_length: 566.100±246.648\n", ++ "Rollout 3506/9766, Reward: 210.081±43.972, Episode_length: 599.000±289.525\n", ++ "Rollout 3507/9766, Reward: 211.752±77.321, Episode_length: 404.900±291.055\n", ++ "Rollout 3508/9766, Reward: 244.243±81.962, Episode_length: 340.500±252.738\n", ++ "Rollout 3509/9766, Reward: 269.913±41.301, Episode_length: 313.300±215.284\n", ++ "Rollout 3510/9766, Reward: 243.594±77.569, Episode_length: 259.600±233.395\n", ++ "Rollout 3511/9766, Reward: 279.342±14.809, Episode_length: 194.200±23.638\n", ++ "Rollout 3512/9766, Reward: 260.541±35.318, Episode_length: 333.800±207.357\n", ++ "Rollout 3513/9766, Reward: 240.241±38.136, Episode_length: 346.000±248.636\n", ++ "Rollout 3514/9766, Reward: 248.613±34.521, Episode_length: 276.300±121.338\n", ++ "Rollout 3515/9766, Reward: 247.675±48.727, Episode_length: 291.400±241.841\n", ++ "Rollout 3516/9766, Reward: 234.380±31.507, Episode_length: 263.500±105.915\n", ++ "Rollout 3517/9766, Reward: 253.514±29.914, Episode_length: 245.400±66.245\n", ++ "Rollout 3518/9766, Reward: 237.933±26.574, Episode_length: 331.800±130.881\n", ++ "Rollout 3519/9766, Reward: 240.571±31.188, Episode_length: 249.500±94.936\n", ++ "Rollout 3520/9766, Reward: 190.496±69.931, Episode_length: 574.800±286.542\n", ++ "Rollout 3521/9766, Reward: 175.640±47.486, Episode_length: 681.200±286.461\n", ++ "Rollout 3522/9766, Reward: 208.598±39.326, Episode_length: 623.800±323.584\n", ++ "Rollout 3523/9766, Reward: 217.909±71.206, Episode_length: 374.500±248.886\n", ++ "Rollout 3524/9766, Reward: 167.948±119.876, Episode_length: 387.500±313.730\n", ++ "Rollout 3525/9766, Reward: 243.958±19.042, Episode_length: 256.700±106.531\n", ++ "Rollout 3526/9766, Reward: 179.101±128.602, Episode_length: 480.100±277.451\n", ++ "Rollout 3527/9766, Reward: 231.741±27.971, Episode_length: 270.400±81.544\n", ++ "Rollout 3528/9766, Reward: 158.879±136.623, Episode_length: 371.700±236.385\n", ++ "Rollout 3529/9766, Reward: 232.110±69.600, Episode_length: 224.400±56.890\n", ++ "Rollout 3530/9766, Reward: 238.423±28.082, Episode_length: 266.600±205.920\n", ++ "Rollout 3531/9766, Reward: 231.327±44.103, Episode_length: 412.100±306.978\n", ++ "Rollout 3532/9766, Reward: 230.812±28.391, Episode_length: 287.700±122.981\n", ++ "Rollout 3533/9766, Reward: 255.784±29.469, Episode_length: 264.700±96.415\n", ++ "Rollout 3534/9766, Reward: 169.492±169.261, Episode_length: 234.200±51.266\n", ++ "Rollout 3535/9766, Reward: 235.098±73.576, Episode_length: 227.700±51.954\n", ++ "Rollout 3536/9766, Reward: 185.955±162.325, Episode_length: 373.100±247.495\n", ++ "Rollout 3537/9766, Reward: 200.561±178.261, Episode_length: 277.800±59.563\n", ++ "Rollout 3538/9766, Reward: 205.142±127.026, Episode_length: 334.000±230.406\n", ++ "Rollout 3539/9766, Reward: 197.593±131.116, Episode_length: 277.600±97.686\n", ++ "Rollout 3540/9766, Reward: 219.157±28.116, Episode_length: 314.400±106.672\n", ++ "Rollout 3541/9766, Reward: 222.151±61.284, Episode_length: 244.900±54.477\n", ++ "Rollout 3542/9766, Reward: 192.172±103.004, Episode_length: 319.800±235.750\n", ++ "Rollout 3543/9766, Reward: 177.789±121.641, Episode_length: 448.200±276.826\n", ++ "Rollout 3544/9766, Reward: 243.219±22.572, Episode_length: 257.200±75.178\n", ++ "Rollout 3545/9766, Reward: 241.513±48.480, Episode_length: 350.600±238.584\n", ++ "Rollout 3546/9766, Reward: 230.571±35.294, Episode_length: 270.600±68.838\n", ++ "Rollout 3547/9766, Reward: 231.367±29.221, Episode_length: 330.200±152.261\n", ++ "Rollout 3548/9766, Reward: 190.475±85.052, Episode_length: 439.500±288.853\n", ++ "Rollout 3549/9766, Reward: 227.304±33.187, Episode_length: 269.200±51.271\n", ++ "Rollout 3550/9766, Reward: 212.397±67.099, Episode_length: 275.000±144.669\n", ++ "Rollout 3551/9766, Reward: 224.204±31.872, Episode_length: 305.900±161.689\n", ++ "Rollout 3552/9766, Reward: 249.618±21.895, Episode_length: 266.900±90.373\n", ++ "Rollout 3553/9766, Reward: 247.185±28.836, Episode_length: 287.500±72.770\n", ++ "Rollout 3554/9766, Reward: 231.157±66.772, Episode_length: 238.800±174.052\n", ++ "Rollout 3555/9766, Reward: 238.723±42.986, Episode_length: 335.200±139.688\n", ++ "Rollout 3556/9766, Reward: 245.201±35.829, Episode_length: 261.500±111.911\n", ++ "Rollout 3557/9766, Reward: 238.640±25.994, Episode_length: 240.300±75.806\n", ++ "Rollout 3558/9766, Reward: 198.270±145.823, Episode_length: 383.000±305.699\n", ++ "Rollout 3559/9766, Reward: 234.129±25.625, Episode_length: 327.500±111.142\n", ++ "Rollout 3560/9766, Reward: 248.298±39.824, Episode_length: 346.100±199.549\n", ++ "Rollout 3561/9766, Reward: 241.163±38.314, Episode_length: 301.800±155.216\n", ++ "Rollout 3562/9766, Reward: 253.440±30.267, Episode_length: 285.400±110.087\n", ++ "Rollout 3563/9766, Reward: 230.482±54.622, Episode_length: 346.600±251.496\n", ++ "Rollout 3564/9766, Reward: 257.386±30.418, Episode_length: 286.800±133.176\n", ++ "Rollout 3565/9766, Reward: 273.193±23.454, Episode_length: 230.100±49.543\n", ++ "Rollout 3566/9766, Reward: 261.947±85.187, Episode_length: 215.200±25.031\n", ++ "Rollout 3567/9766, Reward: 263.868±21.284, Episode_length: 194.900±18.398\n", ++ "Rollout 3568/9766, Reward: 260.191±19.298, Episode_length: 205.900±51.255\n", ++ "Rollout 3569/9766, Reward: 273.065±14.152, Episode_length: 195.800±19.549\n", ++ "Rollout 3570/9766, Reward: 264.172±17.299, Episode_length: 240.600±77.491\n", ++ "Rollout 3571/9766, Reward: 277.524±12.279, Episode_length: 212.200±24.343\n", ++ "Rollout 3572/9766, Reward: 275.093±15.261, Episode_length: 211.000±23.749\n", ++ "Rollout 3573/9766, Reward: 280.382±11.903, Episode_length: 200.600±24.155\n", ++ "Rollout 3574/9766, Reward: 268.693±16.344, Episode_length: 203.500±13.246\n", ++ "Rollout 3575/9766, Reward: 247.737±83.633, Episode_length: 215.800±46.482\n", ++ "Rollout 3576/9766, Reward: 280.842±11.267, Episode_length: 213.100±24.366\n", ++ "Rollout 3577/9766, Reward: 167.143±241.880, Episode_length: 180.500±47.907\n", ++ "Rollout 3578/9766, Reward: 283.926±17.984, Episode_length: 218.200±28.851\n", ++ "Rollout 3579/9766, Reward: 276.604±17.486, Episode_length: 202.400±21.058\n", ++ "Rollout 3580/9766, Reward: 278.461±16.231, Episode_length: 196.500±17.693\n", ++ "Rollout 3581/9766, Reward: 282.650±10.616, Episode_length: 211.600±24.126\n", ++ "Rollout 3582/9766, Reward: 280.398±19.612, Episode_length: 200.500±25.378\n", ++ "Rollout 3583/9766, Reward: 281.001±16.849, Episode_length: 215.200±32.329\n", ++ "Rollout 3584/9766, Reward: 263.765±44.957, Episode_length: 289.300±237.618\n", ++ "Rollout 3585/9766, Reward: 258.118±37.394, Episode_length: 293.100±238.678\n", ++ "Rollout 3586/9766, Reward: 261.132±18.014, Episode_length: 208.600±14.705\n", ++ "Rollout 3587/9766, Reward: 261.303±43.710, Episode_length: 289.900±237.316\n", ++ "Rollout 3588/9766, Reward: 268.837±18.924, Episode_length: 205.700±22.606\n", ++ "Rollout 3589/9766, Reward: 270.100±10.196, Episode_length: 213.900±25.634\n", ++ "Rollout 3590/9766, Reward: 262.032±22.722, Episode_length: 196.800±23.112\n", ++ "Rollout 3591/9766, Reward: 245.744±37.635, Episode_length: 296.100±235.478\n", ++ "Rollout 3592/9766, Reward: 275.355±14.489, Episode_length: 221.000±24.261\n", ++ "Rollout 3593/9766, Reward: 239.964±51.999, Episode_length: 381.600±311.095\n", ++ "Rollout 3594/9766, Reward: 265.326±14.610, Episode_length: 203.000±26.544\n", ++ "Rollout 3595/9766, Reward: 249.522±23.655, Episode_length: 225.300±60.620\n", ++ "Rollout 3596/9766, Reward: 247.330±51.999, Episode_length: 320.600±232.122\n", ++ "Rollout 3597/9766, Reward: 254.947±71.372, Episode_length: 204.800±29.079\n", ++ "Rollout 3598/9766, Reward: 252.526±37.932, Episode_length: 293.700±237.663\n", ++ "Rollout 3599/9766, Reward: 231.280±68.633, Episode_length: 275.000±243.380\n", ++ "Rollout 3600/9766, Reward: 275.137±20.899, Episode_length: 237.300±58.208\n", ++ "Rollout 3601/9766, Reward: 263.453±21.106, Episode_length: 211.200±39.731\n", ++ "Rollout 3602/9766, Reward: 246.679±76.138, Episode_length: 282.800±240.049\n", ++ "Rollout 3603/9766, Reward: 255.321±44.440, Episode_length: 296.200±237.448\n", ++ "Rollout 3604/9766, Reward: 266.580±47.249, Episode_length: 346.400±253.244\n", ++ "Rollout 3605/9766, Reward: 258.551±37.059, Episode_length: 296.800±238.903\n", ++ "Rollout 3606/9766, Reward: 258.297±46.462, Episode_length: 409.100±330.874\n", ++ "Rollout 3607/9766, Reward: 261.686±47.269, Episode_length: 358.100±322.886\n", ++ "Rollout 3608/9766, Reward: 197.307±46.608, Episode_length: 692.000±377.606\n", ++ "Rollout 3609/9766, Reward: 192.040±59.314, Episode_length: 691.400±378.662\n", ++ "Rollout 3610/9766, Reward: 170.469±81.647, Episode_length: 538.600±378.547\n", ++ "Rollout 3611/9766, Reward: 180.845±50.584, Episode_length: 804.100±313.653\n", ++ "Rollout 3612/9766, Reward: 205.995±53.090, Episode_length: 648.200±354.827\n", ++ "Rollout 3613/9766, Reward: 238.164±43.344, Episode_length: 520.700±391.933\n", ++ "Rollout 3614/9766, Reward: 65.339±257.646, Episode_length: 658.000±420.039\n", ++ "Rollout 3615/9766, Reward: 169.991±246.342, Episode_length: 247.000±253.042\n", ++ "Rollout 3616/9766, Reward: 281.762±18.183, Episode_length: 200.000±35.302\n", ++ "Rollout 3617/9766, Reward: 275.083±8.554, Episode_length: 206.100±58.630\n", ++ "Rollout 3618/9766, Reward: 198.830±63.901, Episode_length: 755.400±373.760\n", ++ "Rollout 3619/9766, Reward: 266.630±51.589, Episode_length: 360.000±320.721\n", ++ "Rollout 3620/9766, Reward: 278.978±14.758, Episode_length: 199.800±43.002\n", ++ "Rollout 3621/9766, Reward: 236.145±51.209, Episode_length: 583.200±389.534\n", ++ "Rollout 3622/9766, Reward: 204.959±48.351, Episode_length: 706.600±364.100\n", ++ "Rollout 3623/9766, Reward: 193.631±59.551, Episode_length: 769.300±353.050\n", ++ "Rollout 3624/9766, Reward: 220.491±66.607, Episode_length: 620.200±380.070\n", ++ "Rollout 3625/9766, Reward: 280.739±13.027, Episode_length: 199.200±62.435\n", ++ "Rollout 3626/9766, Reward: 230.352±76.392, Episode_length: 365.500±321.082\n", ++ "Rollout 3627/9766, Reward: 179.924±38.837, Episode_length: 919.500±241.500\n", ++ "Rollout 3628/9766, Reward: 155.489±42.909, Episode_length: 918.400±244.800\n", ++ "Rollout 3629/9766, Reward: 247.723±37.682, Episode_length: 596.500±206.022\n", ++ "Rollout 3630/9766, Reward: 271.676±12.524, Episode_length: 382.800±29.434\n", ++ "Rollout 3631/9766, Reward: 226.775±67.728, Episode_length: 431.000±208.832\n", ++ "Rollout 3632/9766, Reward: 163.988±23.703, Episode_length: 1000.000±0.000\n", ++ "Rollout 3633/9766, Reward: 200.724±56.712, Episode_length: 593.100±407.103\n", ++ "Rollout 3634/9766, Reward: 257.541±14.799, Episode_length: 375.600±131.835\n", ++ "Rollout 3635/9766, Reward: 190.857±68.215, Episode_length: 683.600±388.022\n", ++ "Rollout 3636/9766, Reward: 228.602±49.598, Episode_length: 725.500±313.761\n", ++ "Rollout 3637/9766, Reward: 219.644±92.075, Episode_length: 281.700±240.998\n", ++ "Rollout 3638/9766, Reward: 277.196±17.327, Episode_length: 303.600±232.008\n", ++ "Rollout 3639/9766, Reward: 243.467±41.952, Episode_length: 354.900±322.830\n", ++ "Rollout 3640/9766, Reward: 277.392±15.777, Episode_length: 200.500±19.054\n", ++ "Rollout 3641/9766, Reward: 276.475±17.832, Episode_length: 243.700±127.275\n", ++ "Rollout 3642/9766, Reward: 268.950±31.211, Episode_length: 269.900±244.784\n", ++ "Rollout 3643/9766, Reward: 265.520±64.973, Episode_length: 204.400±26.032\n", ++ "Rollout 3644/9766, Reward: 281.399±17.526, Episode_length: 210.000±25.503\n", ++ "Rollout 3645/9766, Reward: 279.714±14.978, Episode_length: 203.200±29.116\n", ++ "Rollout 3646/9766, Reward: 284.910±19.654, Episode_length: 203.800±30.036\n", ++ "Rollout 3647/9766, Reward: 272.437±22.508, Episode_length: 231.600±106.800\n", ++ "Rollout 3648/9766, Reward: 268.139±68.556, Episode_length: 206.300±28.948\n", ++ "Rollout 3649/9766, Reward: 234.301±90.224, Episode_length: 194.800±23.447\n", ++ "Rollout 3650/9766, Reward: 279.056±19.693, Episode_length: 202.300±18.778\n", ++ "Rollout 3651/9766, Reward: 279.248±20.133, Episode_length: 213.100±21.314\n", ++ "Rollout 3652/9766, Reward: 283.812±14.571, Episode_length: 194.600±25.457\n", ++ "Rollout 3653/9766, Reward: 261.140±73.340, Episode_length: 195.900±20.216\n", ++ "Rollout 3654/9766, Reward: 273.929±31.253, Episode_length: 227.500±48.322\n", ++ "Rollout 3655/9766, Reward: 285.769±15.398, Episode_length: 204.400±32.188\n", ++ "Rollout 3656/9766, Reward: 282.316±14.768, Episode_length: 202.700±32.539\n", ++ "Rollout 3657/9766, Reward: 277.836±17.366, Episode_length: 182.300±17.193\n", ++ "Rollout 3658/9766, Reward: 251.201±73.513, Episode_length: 188.800±23.596\n", ++ "Rollout 3659/9766, Reward: 282.962±13.948, Episode_length: 186.800±19.245\n", ++ "Rollout 3660/9766, Reward: 257.267±76.371, Episode_length: 176.800±18.280\n", ++ "Rollout 3661/9766, Reward: 276.983±24.739, Episode_length: 192.600±15.480\n", ++ "Rollout 3662/9766, Reward: 278.160±17.888, Episode_length: 194.500±25.656\n", ++ "Rollout 3663/9766, Reward: 282.345±19.229, Episode_length: 194.300±15.060\n", ++ "Rollout 3664/9766, Reward: 285.990±23.187, Episode_length: 201.500±20.949\n", ++ "Rollout 3665/9766, Reward: 269.176±23.349, Episode_length: 236.200±81.414\n", ++ "Rollout 3666/9766, Reward: 279.303±22.208, Episode_length: 195.700±30.974\n", ++ "Rollout 3667/9766, Reward: 272.990±22.330, Episode_length: 212.800±29.188\n", ++ "Rollout 3668/9766, Reward: 281.215±17.934, Episode_length: 212.000±22.441\n", ++ "Rollout 3669/9766, Reward: 272.042±17.063, Episode_length: 191.900±28.183\n", ++ "Rollout 3670/9766, Reward: 277.027±18.957, Episode_length: 206.400±26.997\n", ++ "Rollout 3671/9766, Reward: 270.468±18.269, Episode_length: 182.400±17.545\n", ++ "Rollout 3672/9766, Reward: 277.906±16.549, Episode_length: 203.800±23.254\n", ++ "Rollout 3673/9766, Reward: 282.315±21.287, Episode_length: 197.900±19.310\n", ++ "Rollout 3674/9766, Reward: 268.345±43.065, Episode_length: 263.700±246.148\n", ++ "Rollout 3675/9766, Reward: 267.015±32.069, Episode_length: 214.400±67.515\n", ++ "Rollout 3676/9766, Reward: 277.453±18.956, Episode_length: 193.000±30.942\n", ++ "Rollout 3677/9766, Reward: 256.805±22.594, Episode_length: 218.900±106.623\n", ++ "Rollout 3678/9766, Reward: 242.316±58.369, Episode_length: 470.300±293.691\n", ++ "Rollout 3679/9766, Reward: 246.179±29.948, Episode_length: 370.700±156.046\n", ++ "Rollout 3680/9766, Reward: 245.793±38.403, Episode_length: 379.800±174.396\n", ++ "Rollout 3681/9766, Reward: 249.818±35.360, Episode_length: 347.400±279.449\n", ++ "Rollout 3682/9766, Reward: 248.702±48.920, Episode_length: 385.000±313.685\n", ++ "Rollout 3683/9766, Reward: 258.867±66.874, Episode_length: 183.300±30.404\n", ++ "Rollout 3684/9766, Reward: 276.995±17.696, Episode_length: 183.700±26.454\n", ++ "Rollout 3685/9766, Reward: 244.020±64.455, Episode_length: 434.600±356.234\n", ++ "Rollout 3686/9766, Reward: 271.718±20.333, Episode_length: 173.900±15.934\n", ++ "Rollout 3687/9766, Reward: 272.358±18.467, Episode_length: 189.200±17.457\n", ++ "Rollout 3688/9766, Reward: 270.828±26.411, Episode_length: 357.000±265.368\n", ++ "Rollout 3689/9766, Reward: 251.684±41.876, Episode_length: 353.300±291.210\n", ++ "Rollout 3690/9766, Reward: 268.293±40.764, Episode_length: 293.500±244.555\n", ++ "Rollout 3691/9766, Reward: 252.613±52.999, Episode_length: 384.500±258.528\n", ++ "Rollout 3692/9766, Reward: 275.857±23.831, Episode_length: 193.900±31.354\n", ++ "Rollout 3693/9766, Reward: 231.845±46.737, Episode_length: 389.000±317.071\n", ++ "Rollout 3694/9766, Reward: 209.555±80.197, Episode_length: 352.300±325.056\n", ++ "Rollout 3695/9766, Reward: 259.040±32.669, Episode_length: 322.100±294.976\n", ++ "Rollout 3696/9766, Reward: 269.430±33.275, Episode_length: 288.100±239.764\n", ++ "Rollout 3697/9766, Reward: 257.928±35.369, Episode_length: 363.700±319.963\n", ++ "Rollout 3698/9766, Reward: 273.274±22.009, Episode_length: 187.200±20.498\n", ++ "Rollout 3699/9766, Reward: 280.333±20.897, Episode_length: 213.900±54.674\n", ++ "Rollout 3700/9766, Reward: 275.693±17.003, Episode_length: 189.400±16.157\n", ++ "Rollout 3701/9766, Reward: 269.943±23.359, Episode_length: 179.600±17.217\n", ++ "Rollout 3702/9766, Reward: 278.120±14.133, Episode_length: 189.700±24.872\n", ++ "Rollout 3703/9766, Reward: 289.234±15.200, Episode_length: 252.400±107.426\n", ++ "Rollout 3704/9766, Reward: 269.487±18.997, Episode_length: 183.300±28.366\n", ++ "Rollout 3705/9766, Reward: 279.293±10.493, Episode_length: 193.800±19.182\n", ++ "Rollout 3706/9766, Reward: 283.693±15.352, Episode_length: 203.800±16.839\n", ++ "Rollout 3707/9766, Reward: 263.875±14.753, Episode_length: 187.200±11.161\n", ++ "Rollout 3708/9766, Reward: 277.476±18.722, Episode_length: 196.100±15.030\n", ++ "Rollout 3709/9766, Reward: 278.918±15.088, Episode_length: 187.500±19.402\n", ++ "Rollout 3710/9766, Reward: 264.916±18.757, Episode_length: 263.100±165.836\n", ++ "Rollout 3711/9766, Reward: 286.776±21.644, Episode_length: 198.400±28.079\n", ++ "Rollout 3712/9766, Reward: 274.623±24.910, Episode_length: 217.200±97.580\n", ++ "Rollout 3713/9766, Reward: 285.088±16.336, Episode_length: 203.400±27.565\n", ++ "Rollout 3714/9766, Reward: 271.292±21.059, Episode_length: 186.400±19.381\n", ++ "Rollout 3715/9766, Reward: 275.380±12.995, Episode_length: 185.100±29.851\n", ++ "Rollout 3716/9766, Reward: 282.201±13.848, Episode_length: 189.500±14.361\n", ++ "Rollout 3717/9766, Reward: 282.567±18.882, Episode_length: 189.100±26.576\n", ++ "Rollout 3718/9766, Reward: 272.822±26.239, Episode_length: 214.600±87.208\n", ++ "Rollout 3719/9766, Reward: 282.530±18.884, Episode_length: 198.000±31.493\n", ++ "Rollout 3720/9766, Reward: 260.652±79.704, Episode_length: 215.500±73.028\n", ++ "Rollout 3721/9766, Reward: 270.327±19.295, Episode_length: 186.200±16.017\n", ++ "Rollout 3722/9766, Reward: 234.106±69.458, Episode_length: 206.400±78.532\n", ++ "Rollout 3723/9766, Reward: 247.598±67.922, Episode_length: 266.400±245.699\n", ++ "Rollout 3724/9766, Reward: 274.935±13.413, Episode_length: 178.200±22.969\n", ++ "Rollout 3725/9766, Reward: 271.283±41.599, Episode_length: 233.300±107.701\n", ++ "Rollout 3726/9766, Reward: 290.065±23.376, Episode_length: 216.200±70.798\n", ++ "Rollout 3727/9766, Reward: 280.864±18.563, Episode_length: 192.000±23.507\n", ++ "Rollout 3728/9766, Reward: 276.337±21.995, Episode_length: 185.300±25.745\n", ++ "Rollout 3729/9766, Reward: 283.691±18.619, Episode_length: 177.400±13.283\n", ++ "Rollout 3730/9766, Reward: 282.116±20.334, Episode_length: 180.700±13.835\n", ++ "Rollout 3731/9766, Reward: 261.056±33.194, Episode_length: 265.000±246.532\n", ++ "Rollout 3732/9766, Reward: 257.437±18.152, Episode_length: 520.900±209.904\n", ++ "Rollout 3733/9766, Reward: 271.586±36.587, Episode_length: 347.200±314.308\n", ++ "Rollout 3734/9766, Reward: 278.918±21.657, Episode_length: 178.100±30.194\n", ++ "Rollout 3735/9766, Reward: 286.402±17.987, Episode_length: 187.400±18.864\n", ++ "Rollout 3736/9766, Reward: 274.613±38.364, Episode_length: 213.900±79.037\n", ++ "Rollout 3737/9766, Reward: 291.206±16.407, Episode_length: 190.800±21.493\n", ++ "Rollout 3738/9766, Reward: 279.620±21.604, Episode_length: 199.900±31.873\n", ++ "Rollout 3739/9766, Reward: 287.684±19.827, Episode_length: 193.300±23.109\n", ++ "Rollout 3740/9766, Reward: 282.583±23.104, Episode_length: 184.900±21.774\n", ++ "Rollout 3741/9766, Reward: 282.658±14.094, Episode_length: 176.000±15.780\n", ++ "Rollout 3742/9766, Reward: 236.610±65.385, Episode_length: 540.500±376.564\n", ++ "Rollout 3743/9766, Reward: 246.603±29.158, Episode_length: 376.800±165.225\n", ++ "Rollout 3744/9766, Reward: 231.698±52.765, Episode_length: 595.300±404.779\n", ++ "Rollout 3745/9766, Reward: 291.313±14.811, Episode_length: 192.800±18.557\n", ++ "Rollout 3746/9766, Reward: 279.598±12.222, Episode_length: 182.600±14.186\n", ++ "Rollout 3747/9766, Reward: 275.214±11.296, Episode_length: 241.500±177.025\n", ++ "Rollout 3748/9766, Reward: 285.743±16.930, Episode_length: 185.000±19.173\n", ++ "Rollout 3749/9766, Reward: 288.118±18.520, Episode_length: 188.800±25.678\n", ++ "Rollout 3750/9766, Reward: 289.577±19.771, Episode_length: 188.000±22.271\n", ++ "Rollout 3751/9766, Reward: 262.862±33.920, Episode_length: 272.400±243.539\n", ++ "Rollout 3752/9766, Reward: 248.765±23.451, Episode_length: 412.100±147.508\n", ++ "Rollout 3753/9766, Reward: 232.519±25.998, Episode_length: 428.300±156.401\n", ++ "Rollout 3754/9766, Reward: 242.659±32.692, Episode_length: 378.500±226.579\n", ++ "Rollout 3755/9766, Reward: 267.707±17.272, Episode_length: 398.600±128.114\n", ++ "Rollout 3756/9766, Reward: 269.871±30.268, Episode_length: 264.100±245.626\n", ++ "Rollout 3757/9766, Reward: 245.663±44.026, Episode_length: 481.800±346.707\n", ++ "Rollout 3758/9766, Reward: 226.330±63.008, Episode_length: 583.200±393.605\n", ++ "Rollout 3759/9766, Reward: 242.015±41.983, Episode_length: 506.600±277.343\n", ++ "Rollout 3760/9766, Reward: 253.267±41.884, Episode_length: 372.100±223.631\n", ++ "Rollout 3761/9766, Reward: 274.780±20.718, Episode_length: 187.400±18.927\n", ++ "Rollout 3762/9766, Reward: 241.206±81.564, Episode_length: 208.200±72.974\n", ++ "Rollout 3763/9766, Reward: 265.875±31.730, Episode_length: 229.100±78.822\n", ++ "Rollout 3764/9766, Reward: 279.970±20.763, Episode_length: 189.900±13.831\n", ++ "Rollout 3765/9766, Reward: 269.674±15.947, Episode_length: 183.700±26.544\n", ++ "Rollout 3766/9766, Reward: 273.575±19.328, Episode_length: 186.900±23.257\n", ++ "Rollout 3767/9766, Reward: 275.686±21.027, Episode_length: 192.000±25.294\n", ++ "Rollout 3768/9766, Reward: 254.894±31.130, Episode_length: 234.300±134.057\n", ++ "Rollout 3769/9766, Reward: 238.417±45.307, Episode_length: 292.600±121.774\n", ++ "Rollout 3770/9766, Reward: 253.268±48.006, Episode_length: 238.100±81.510\n", ++ "Rollout 3771/9766, Reward: 239.993±46.831, Episode_length: 323.800±195.836\n", ++ "Rollout 3772/9766, Reward: 257.586±38.089, Episode_length: 242.600±84.207\n", ++ "Rollout 3773/9766, Reward: 272.883±21.907, Episode_length: 218.400±60.157\n", ++ "Rollout 3774/9766, Reward: 272.399±17.615, Episode_length: 223.200±99.727\n", ++ "Rollout 3775/9766, Reward: 239.804±73.707, Episode_length: 269.700±204.255\n", ++ "Rollout 3776/9766, Reward: 233.572±33.742, Episode_length: 255.400±123.671\n", ++ "Rollout 3777/9766, Reward: 204.458±129.787, Episode_length: 286.800±136.382\n", ++ "Rollout 3778/9766, Reward: 228.937±110.442, Episode_length: 285.900±240.903\n", ++ "Rollout 3779/9766, Reward: 260.799±30.710, Episode_length: 204.900±52.869\n", ++ "Rollout 3780/9766, Reward: 253.443±39.648, Episode_length: 286.400±126.040\n", ++ "Rollout 3781/9766, Reward: 265.003±21.605, Episode_length: 204.700±64.568\n", ++ "Rollout 3782/9766, Reward: 261.779±23.810, Episode_length: 199.200±65.334\n", ++ "Rollout 3783/9766, Reward: 261.591±27.054, Episode_length: 222.400±75.601\n", ++ "Rollout 3784/9766, Reward: 274.053±19.553, Episode_length: 187.900±16.343\n", ++ "Rollout 3785/9766, Reward: 246.564±40.194, Episode_length: 350.900±326.179\n", ++ "Rollout 3786/9766, Reward: 278.237±11.531, Episode_length: 219.700±55.129\n", ++ "Rollout 3787/9766, Reward: 158.142±261.128, Episode_length: 289.400±245.702\n", ++ "Rollout 3788/9766, Reward: 179.326±273.883, Episode_length: 172.200±39.122\n", ++ "Rollout 3789/9766, Reward: 220.427±107.066, Episode_length: 331.300±249.316\n", ++ "Rollout 3790/9766, Reward: 256.589±31.909, Episode_length: 212.600±78.014\n", ++ "Rollout 3791/9766, Reward: 239.262±75.113, Episode_length: 196.900±68.121\n", ++ "Rollout 3792/9766, Reward: 249.685±43.268, Episode_length: 306.500±184.323\n", ++ "Rollout 3793/9766, Reward: 262.467±37.060, Episode_length: 248.600±92.334\n", ++ "Rollout 3794/9766, Reward: 258.500±36.044, Episode_length: 247.100±69.942\n", ++ "Rollout 3795/9766, Reward: 259.139±30.134, Episode_length: 217.900±62.470\n", ++ "Rollout 3796/9766, Reward: 281.819±19.800, Episode_length: 249.600±113.954\n", ++ "Rollout 3797/9766, Reward: 274.721±19.086, Episode_length: 194.200±21.972\n", ++ "Rollout 3798/9766, Reward: 269.507±18.998, Episode_length: 214.100±33.807\n", ++ "Rollout 3799/9766, Reward: 272.486±15.633, Episode_length: 193.800±47.389\n", ++ "Rollout 3800/9766, Reward: 245.079±52.674, Episode_length: 323.700±256.837\n", ++ "Rollout 3801/9766, Reward: 264.219±48.194, Episode_length: 314.700±256.154\n", ++ "Rollout 3802/9766, Reward: 264.726±30.410, Episode_length: 246.300±111.624\n", ++ "Rollout 3803/9766, Reward: 174.677±264.914, Episode_length: 169.400±31.671\n", ++ "Rollout 3804/9766, Reward: 281.502±14.107, Episode_length: 179.300±21.490\n", ++ "Rollout 3805/9766, Reward: 286.542±21.361, Episode_length: 182.700±16.462\n", ++ "Rollout 3806/9766, Reward: 96.528±345.954, Episode_length: 159.800±44.553\n", ++ "Rollout 3807/9766, Reward: 41.843±354.527, Episode_length: 151.200±48.852\n", ++ "Rollout 3808/9766, Reward: 266.503±21.688, Episode_length: 195.400±67.952\n", ++ "Rollout 3809/9766, Reward: 273.401±18.223, Episode_length: 207.100±69.484\n", ++ "Rollout 3810/9766, Reward: 205.439±242.363, Episode_length: 188.100±60.149\n", ++ "Rollout 3811/9766, Reward: 259.307±30.315, Episode_length: 203.900±106.861\n", ++ "Rollout 3812/9766, Reward: 276.378±39.045, Episode_length: 194.400±57.361\n", ++ "Rollout 3813/9766, Reward: 106.791±331.131, Episode_length: 160.600±45.990\n", ++ "Rollout 3814/9766, Reward: 34.766±367.899, Episode_length: 149.100±43.436\n", ++ "Rollout 3815/9766, Reward: 109.397±331.736, Episode_length: 159.400±43.221\n", ++ "Rollout 3816/9766, Reward: -54.179±401.882, Episode_length: 132.300±45.275\n", ++ "Rollout 3817/9766, Reward: -68.347±425.922, Episode_length: 141.100±48.535\n", ++ "Rollout 3818/9766, Reward: 169.786±246.045, Episode_length: 224.100±126.626\n", ++ "Rollout 3819/9766, Reward: 257.974±32.206, Episode_length: 271.100±205.731\n", ++ "Rollout 3820/9766, Reward: 269.546±31.592, Episode_length: 200.000±75.041\n", ++ "Rollout 3821/9766, Reward: 87.063±364.918, Episode_length: 172.700±79.195\n", ++ "Rollout 3822/9766, Reward: 283.248±20.846, Episode_length: 177.000±24.417\n", ++ "Rollout 3823/9766, Reward: 186.135±249.329, Episode_length: 188.400±100.597\n", ++ "Rollout 3824/9766, Reward: 93.096±314.953, Episode_length: 225.700±260.236\n", ++ "Rollout 3825/9766, Reward: 13.705±393.818, Episode_length: 146.200±43.705\n", ++ "Rollout 3826/9766, Reward: 186.090±262.897, Episode_length: 155.200±25.682\n", ++ "Rollout 3827/9766, Reward: 285.316±16.038, Episode_length: 174.200±19.151\n", ++ "Rollout 3828/9766, Reward: 280.039±14.658, Episode_length: 171.700±17.000\n", ++ "Rollout 3829/9766, Reward: 280.611±16.779, Episode_length: 176.100±17.535\n", ++ "Rollout 3830/9766, Reward: 282.837±19.173, Episode_length: 170.800±20.267\n", ++ "Rollout 3831/9766, Reward: 289.000±17.996, Episode_length: 181.100±30.333\n", ++ "Rollout 3832/9766, Reward: 293.667±17.572, Episode_length: 176.100±26.402\n", ++ "Rollout 3833/9766, Reward: 278.903±16.715, Episode_length: 177.800±25.775\n", ++ "Rollout 3834/9766, Reward: 292.724±14.903, Episode_length: 183.200±13.430\n", ++ "Rollout 3835/9766, Reward: 287.590±23.708, Episode_length: 178.900±23.565\n", ++ "Rollout 3836/9766, Reward: 282.328±15.237, Episode_length: 170.300±15.570\n", ++ "Rollout 3837/9766, Reward: 278.622±15.995, Episode_length: 169.100±13.802\n", ++ "Rollout 3838/9766, Reward: 263.159±73.879, Episode_length: 164.500±32.197\n", ++ "Rollout 3839/9766, Reward: 295.033±14.328, Episode_length: 180.900±24.472\n", ++ "Rollout 3840/9766, Reward: 291.840±16.319, Episode_length: 176.300±32.088\n", ++ "Rollout 3841/9766, Reward: 283.250±13.466, Episode_length: 164.600±17.454\n", ++ "Rollout 3842/9766, Reward: 287.883±20.667, Episode_length: 176.600±18.896\n", ++ "Rollout 3843/9766, Reward: 289.856±20.150, Episode_length: 178.300±23.635\n", ++ "Rollout 3844/9766, Reward: 281.795±17.066, Episode_length: 181.200±16.515\n", ++ "Rollout 3845/9766, Reward: 280.024±12.154, Episode_length: 163.200±20.054\n", ++ "Rollout 3846/9766, Reward: 295.338±17.854, Episode_length: 187.300±24.175\n", ++ "Rollout 3847/9766, Reward: 278.833±14.793, Episode_length: 175.700±18.472\n", ++ "Rollout 3848/9766, Reward: 271.537±30.909, Episode_length: 255.400±249.131\n", ++ "Rollout 3849/9766, Reward: 283.669±15.578, Episode_length: 172.500±15.699\n", ++ "Rollout 3850/9766, Reward: 276.463±19.556, Episode_length: 165.700±16.847\n", ++ "Rollout 3851/9766, Reward: 282.108±18.640, Episode_length: 179.100±21.695\n", ++ "Rollout 3852/9766, Reward: 260.383±50.317, Episode_length: 362.300±331.051\n", ++ "Rollout 3853/9766, Reward: 276.941±22.497, Episode_length: 172.500±15.807\n", ++ "Rollout 3854/9766, Reward: 286.365±20.494, Episode_length: 178.100±22.470\n", ++ "Rollout 3855/9766, Reward: 282.162±33.409, Episode_length: 252.600±249.908\n", ++ "Rollout 3856/9766, Reward: 294.891±15.958, Episode_length: 170.300±23.833\n", ++ "Rollout 3857/9766, Reward: 266.143±47.723, Episode_length: 340.300±329.943\n", ++ "Rollout 3858/9766, Reward: 274.992±41.129, Episode_length: 254.700±249.516\n", ++ "Rollout 3859/9766, Reward: 275.939±23.409, Episode_length: 265.200±246.626\n", ++ "Rollout 3860/9766, Reward: 231.341±53.587, Episode_length: 575.500±373.269\n", ++ "Rollout 3861/9766, Reward: 230.405±57.980, Episode_length: 593.800±406.874\n", ++ "Rollout 3862/9766, Reward: 240.593±64.846, Episode_length: 515.300±396.244\n", ++ "Rollout 3863/9766, Reward: 255.046±42.632, Episode_length: 410.800±385.887\n", ++ "Rollout 3864/9766, Reward: 260.092±40.755, Episode_length: 248.300±251.393\n", ++ "Rollout 3865/9766, Reward: 291.453±14.077, Episode_length: 179.100±21.464\n", ++ "Rollout 3866/9766, Reward: 279.362±19.151, Episode_length: 170.600±17.165\n", ++ "Rollout 3867/9766, Reward: 278.090±21.727, Episode_length: 224.800±161.548\n", ++ "Rollout 3868/9766, Reward: 270.195±17.039, Episode_length: 163.200±19.255\n", ++ "Rollout 3869/9766, Reward: 259.145±44.167, Episode_length: 448.200±365.144\n", ++ "Rollout 3870/9766, Reward: 195.324±57.520, Episode_length: 760.400±366.110\n", ++ "Rollout 3871/9766, Reward: 242.643±45.592, Episode_length: 441.100±376.152\n", ++ "Rollout 3872/9766, Reward: 281.511±11.036, Episode_length: 259.100±226.570\n", ++ "Rollout 3873/9766, Reward: 287.949±16.048, Episode_length: 185.200±15.387\n", ++ "Rollout 3874/9766, Reward: 273.709±19.953, Episode_length: 191.000±75.864\n", ++ "Rollout 3875/9766, Reward: 285.718±23.740, Episode_length: 173.000±23.799\n", ++ "Rollout 3876/9766, Reward: 282.876±16.746, Episode_length: 166.400±22.513\n", ++ "Rollout 3877/9766, Reward: 281.556±15.235, Episode_length: 179.900±20.176\n", ++ "Rollout 3878/9766, Reward: 280.534±12.280, Episode_length: 175.800±20.302\n", ++ "Rollout 3879/9766, Reward: 289.254±22.089, Episode_length: 178.300±22.965\n", ++ "Rollout 3880/9766, Reward: 280.089±16.914, Episode_length: 184.700±20.557\n", ++ "Rollout 3881/9766, Reward: 279.887±26.035, Episode_length: 199.400±73.507\n", ++ "Rollout 3882/9766, Reward: 279.716±30.418, Episode_length: 206.500±80.408\n", ++ "Rollout 3883/9766, Reward: 285.217±15.414, Episode_length: 177.700±16.517\n", ++ "Rollout 3884/9766, Reward: 285.804±21.744, Episode_length: 191.500±24.997\n", ++ "Rollout 3885/9766, Reward: 276.914±17.540, Episode_length: 174.100±20.564\n", ++ "Rollout 3886/9766, Reward: 288.266±9.236, Episode_length: 172.300±26.203\n", ++ "Rollout 3887/9766, Reward: 280.575±21.557, Episode_length: 168.200±13.257\n", ++ "Rollout 3888/9766, Reward: 282.780±15.337, Episode_length: 179.700±27.448\n", ++ "Rollout 3889/9766, Reward: 284.243±18.046, Episode_length: 176.900±21.328\n", ++ "Rollout 3890/9766, Reward: 278.272±15.355, Episode_length: 177.800±20.366\n", ++ "Rollout 3891/9766, Reward: 282.444±21.690, Episode_length: 173.600±25.605\n", ++ "Rollout 3892/9766, Reward: 284.977±15.638, Episode_length: 186.100±27.479\n", ++ "Rollout 3893/9766, Reward: 288.286±17.954, Episode_length: 177.100±27.186\n", ++ "Rollout 3894/9766, Reward: 276.220±12.658, Episode_length: 179.100±7.880\n", ++ "Rollout 3895/9766, Reward: 282.560±10.792, Episode_length: 174.200±25.439\n", ++ "Rollout 3896/9766, Reward: 281.709±21.246, Episode_length: 178.100±28.236\n", ++ "Rollout 3897/9766, Reward: 281.963±21.476, Episode_length: 175.700±14.457\n", ++ "Rollout 3898/9766, Reward: 283.769±15.064, Episode_length: 174.700±18.188\n", ++ "Rollout 3899/9766, Reward: 273.455±26.000, Episode_length: 200.000±72.364\n", ++ "Rollout 3900/9766, Reward: 273.935±26.975, Episode_length: 210.800±80.253\n", ++ "Rollout 3901/9766, Reward: 273.556±24.251, Episode_length: 191.100±60.652\n", ++ "Rollout 3902/9766, Reward: 277.010±16.579, Episode_length: 190.400±27.954\n", ++ "Rollout 3903/9766, Reward: 278.519±17.683, Episode_length: 188.700±36.318\n", ++ "Rollout 3904/9766, Reward: 279.188±12.266, Episode_length: 183.200±21.132\n", ++ "Rollout 3905/9766, Reward: 253.316±76.644, Episode_length: 164.300±32.546\n", ++ "Rollout 3906/9766, Reward: 270.302±35.739, Episode_length: 228.000±134.329\n", ++ "Rollout 3907/9766, Reward: 271.906±32.042, Episode_length: 203.600±68.327\n", ++ "Rollout 3908/9766, Reward: 282.565±16.111, Episode_length: 182.900±21.059\n", ++ "Rollout 3909/9766, Reward: 296.983±15.774, Episode_length: 205.600±38.424\n", ++ "Rollout 3910/9766, Reward: 283.324±17.313, Episode_length: 189.100±26.220\n", ++ "Rollout 3911/9766, Reward: 284.061±19.653, Episode_length: 194.300±35.914\n", ++ "Rollout 3912/9766, Reward: 277.050±18.780, Episode_length: 195.300±26.575\n", ++ "Rollout 3913/9766, Reward: 288.343±14.879, Episode_length: 202.000±21.689\n", ++ "Rollout 3914/9766, Reward: 278.898±16.529, Episode_length: 201.100±24.027\n", ++ "Rollout 3915/9766, Reward: 191.329±285.437, Episode_length: 183.600±51.562\n", ++ "Rollout 3916/9766, Reward: 269.286±25.388, Episode_length: 214.400±75.548\n", ++ "Rollout 3917/9766, Reward: 287.461±11.681, Episode_length: 170.700±16.156\n", ++ "Rollout 3918/9766, Reward: 281.535±15.270, Episode_length: 199.200±25.918\n", ++ "Rollout 3919/9766, Reward: 281.742±16.160, Episode_length: 189.400±26.620\n", ++ "Rollout 3920/9766, Reward: 295.081±10.504, Episode_length: 185.200±25.063\n", ++ "Rollout 3921/9766, Reward: 290.507±8.599, Episode_length: 184.300±19.860\n", ++ "Rollout 3922/9766, Reward: 276.121±10.970, Episode_length: 178.800±21.377\n", ++ "Rollout 3923/9766, Reward: 289.271±17.663, Episode_length: 191.800±40.750\n", ++ "Rollout 3924/9766, Reward: 279.453±20.203, Episode_length: 167.700±17.059\n", ++ "Rollout 3925/9766, Reward: 289.610±14.104, Episode_length: 196.900±35.901\n", ++ "Rollout 3926/9766, Reward: 293.865±19.858, Episode_length: 190.600±24.117\n", ++ "Rollout 3927/9766, Reward: 271.022±34.883, Episode_length: 254.300±249.206\n", ++ "Rollout 3928/9766, Reward: 272.531±42.992, Episode_length: 303.200±265.384\n", ++ "Rollout 3929/9766, Reward: 284.006±11.630, Episode_length: 157.600±19.653\n", ++ "Rollout 3930/9766, Reward: 277.208±23.591, Episode_length: 170.700±20.347\n", ++ "Rollout 3931/9766, Reward: 269.595±32.276, Episode_length: 275.300±246.897\n", ++ "Rollout 3932/9766, Reward: 288.419±9.643, Episode_length: 314.200±258.141\n", ++ "Rollout 3933/9766, Reward: 283.472±18.541, Episode_length: 170.600±16.639\n", ++ "Rollout 3934/9766, Reward: 282.436±21.647, Episode_length: 201.000±91.218\n", ++ "Rollout 3935/9766, Reward: 231.362±70.171, Episode_length: 492.500±364.425\n", ++ "Rollout 3936/9766, Reward: 233.105±64.508, Episode_length: 639.100±382.815\n", ++ "Rollout 3937/9766, Reward: 195.478±57.971, Episode_length: 764.900±361.122\n", ++ "Rollout 3938/9766, Reward: 255.225±47.720, Episode_length: 396.600±330.857\n", ++ "Rollout 3939/9766, Reward: 271.866±42.073, Episode_length: 262.300±246.602\n", ++ "Rollout 3940/9766, Reward: 281.910±19.156, Episode_length: 166.300±22.526\n", ++ "Rollout 3941/9766, Reward: 229.250±54.386, Episode_length: 666.700±408.474\n", ++ "Rollout 3942/9766, Reward: 262.060±46.669, Episode_length: 283.500±248.010\n", ++ "Rollout 3943/9766, Reward: 285.700±18.542, Episode_length: 184.400±27.004\n", ++ "Rollout 3944/9766, Reward: 269.665±33.765, Episode_length: 259.600±247.211\n", ++ "Rollout 3945/9766, Reward: 270.413±15.924, Episode_length: 164.700±15.126\n", ++ "Rollout 3946/9766, Reward: 279.806±15.501, Episode_length: 181.000±15.830\n", ++ "Rollout 3947/9766, Reward: 270.434±39.918, Episode_length: 256.600±248.786\n", ++ "Rollout 3948/9766, Reward: 282.911±17.895, Episode_length: 196.400±36.371\n", ++ "Rollout 3949/9766, Reward: 291.269±13.767, Episode_length: 181.300±24.150\n", ++ "Rollout 3950/9766, Reward: 270.794±33.571, Episode_length: 270.100±244.408\n", ++ "Rollout 3951/9766, Reward: 278.194±38.965, Episode_length: 260.900±247.096\n", ++ "Rollout 3952/9766, Reward: 266.980±34.717, Episode_length: 265.700±245.450\n", ++ "Rollout 3953/9766, Reward: 274.688±35.710, Episode_length: 266.100±244.962\n", ++ "Rollout 3954/9766, Reward: 260.920±58.135, Episode_length: 348.500±326.592\n", ++ "Rollout 3955/9766, Reward: 293.493±14.714, Episode_length: 185.100±19.603\n", ++ "Rollout 3956/9766, Reward: 268.211±14.566, Episode_length: 166.900±13.553\n", ++ "Rollout 3957/9766, Reward: 272.153±29.987, Episode_length: 268.700±244.607\n", ++ "Rollout 3958/9766, Reward: 288.476±12.871, Episode_length: 186.000±32.640\n", ++ "Rollout 3959/9766, Reward: 270.375±34.314, Episode_length: 254.300±249.149\n", ++ "Rollout 3960/9766, Reward: 268.596±11.618, Episode_length: 173.100±16.694\n", ++ "Rollout 3961/9766, Reward: 283.603±16.425, Episode_length: 177.900±19.403\n", ++ "Rollout 3962/9766, Reward: 268.360±53.338, Episode_length: 345.900±327.866\n", ++ "Rollout 3963/9766, Reward: 292.241±11.800, Episode_length: 256.100±246.716\n", ++ "Rollout 3964/9766, Reward: 246.027±51.434, Episode_length: 434.400±370.581\n", ++ "Rollout 3965/9766, Reward: 282.890±11.539, Episode_length: 172.600±18.255\n", ++ "Rollout 3966/9766, Reward: 264.247±35.414, Episode_length: 252.400±249.635\n", ++ "Rollout 3967/9766, Reward: 287.316±17.953, Episode_length: 196.600±22.949\n", ++ "Rollout 3968/9766, Reward: 283.070±13.295, Episode_length: 185.800±17.221\n", ++ "Rollout 3969/9766, Reward: 290.201±14.679, Episode_length: 192.700±18.580\n", ++ "Rollout 3970/9766, Reward: 267.000±47.105, Episode_length: 263.000±246.389\n", ++ "Rollout 3971/9766, Reward: 285.340±20.715, Episode_length: 253.900±178.992\n", ++ "Rollout 3972/9766, Reward: 261.705±36.067, Episode_length: 262.500±246.483\n", ++ "Rollout 3973/9766, Reward: 261.652±36.576, Episode_length: 253.400±249.466\n", ++ "Rollout 3974/9766, Reward: 281.281±11.945, Episode_length: 177.000±19.437\n", ++ "Rollout 3975/9766, Reward: 279.797±18.891, Episode_length: 177.000±19.514\n", ++ "Rollout 3976/9766, Reward: 280.044±16.055, Episode_length: 188.500±14.087\n", ++ "Rollout 3977/9766, Reward: 275.183±22.302, Episode_length: 178.100±19.065\n", ++ "Rollout 3978/9766, Reward: 278.952±26.044, Episode_length: 221.600±125.565\n", ++ "Rollout 3979/9766, Reward: 291.961±16.032, Episode_length: 189.200±27.625\n", ++ "Rollout 3980/9766, Reward: 275.301±23.231, Episode_length: 303.000±248.331\n", ++ "Rollout 3981/9766, Reward: 279.660±17.588, Episode_length: 184.500±15.571\n", ++ "Rollout 3982/9766, Reward: 270.607±25.310, Episode_length: 225.500±134.530\n", ++ "Rollout 3983/9766, Reward: 286.966±9.197, Episode_length: 187.400±22.535\n", ++ "Rollout 3984/9766, Reward: 288.602±12.136, Episode_length: 181.000±20.494\n", ++ "Rollout 3985/9766, Reward: 273.472±40.405, Episode_length: 295.900±242.605\n", ++ "Rollout 3986/9766, Reward: 287.825±13.503, Episode_length: 169.300±17.590\n", ++ "Rollout 3987/9766, Reward: 284.899±12.178, Episode_length: 176.200±26.103\n", ++ "Rollout 3988/9766, Reward: 277.029±16.010, Episode_length: 184.500±17.391\n", ++ "Rollout 3989/9766, Reward: 273.051±24.938, Episode_length: 215.500±95.862\n", ++ "Rollout 3990/9766, Reward: 260.125±28.994, Episode_length: 256.700±248.677\n", ++ "Rollout 3991/9766, Reward: 270.314±21.550, Episode_length: 259.600±201.625\n", ++ "Rollout 3992/9766, Reward: 279.824±36.429, Episode_length: 277.100±242.406\n", ++ "Rollout 3993/9766, Reward: 273.813±39.929, Episode_length: 275.300±242.416\n", ++ "Rollout 3994/9766, Reward: 279.237±26.602, Episode_length: 206.200±64.801\n", ++ "Rollout 3995/9766, Reward: 271.149±27.605, Episode_length: 240.500±147.557\n", ++ "Rollout 3996/9766, Reward: 263.987±42.631, Episode_length: 260.800±247.157\n", ++ "Rollout 3997/9766, Reward: 286.581±11.989, Episode_length: 254.700±95.802\n", ++ "Rollout 3998/9766, Reward: 254.425±42.077, Episode_length: 453.700±336.820\n", ++ "Rollout 3999/9766, Reward: 275.198±32.459, Episode_length: 202.800±62.795\n", ++ "Rollout 4000/9766, Reward: 273.216±46.018, Episode_length: 346.300±244.142\n", ++ "Rollout 4001/9766, Reward: 266.610±59.480, Episode_length: 304.500±240.132\n", ++ "Rollout 4002/9766, Reward: 283.626±13.302, Episode_length: 189.700±30.348\n", ++ "Rollout 4003/9766, Reward: 269.684±35.295, Episode_length: 266.400±245.246\n", ++ "Rollout 4004/9766, Reward: 265.627±41.240, Episode_length: 386.200±305.386\n", ++ "Rollout 4005/9766, Reward: 255.447±50.709, Episode_length: 388.900±339.381\n", ++ "Rollout 4006/9766, Reward: 254.942±51.565, Episode_length: 356.200±322.768\n", ++ "Rollout 4007/9766, Reward: 271.207±24.721, Episode_length: 223.600±85.012\n", ++ "Rollout 4008/9766, Reward: 255.728±53.511, Episode_length: 345.700±328.550\n", ++ "Rollout 4009/9766, Reward: 271.980±19.639, Episode_length: 209.000±114.708\n", ++ "Rollout 4010/9766, Reward: 257.147±58.961, Episode_length: 362.300±322.468\n", ++ "Rollout 4011/9766, Reward: 277.484±44.538, Episode_length: 281.000±240.590\n", ++ "Rollout 4012/9766, Reward: 277.310±9.612, Episode_length: 238.100±183.219\n", ++ "Rollout 4013/9766, Reward: 286.124±18.085, Episode_length: 199.700±32.395\n", ++ "Rollout 4014/9766, Reward: 277.566±11.698, Episode_length: 180.600±25.656\n", ++ "Rollout 4015/9766, Reward: 273.934±42.953, Episode_length: 337.700±301.607\n", ++ "Rollout 4016/9766, Reward: 258.886±48.131, Episode_length: 370.000±324.200\n", ++ "Rollout 4017/9766, Reward: 273.432±22.870, Episode_length: 177.800±18.578\n", ++ "Rollout 4018/9766, Reward: 280.746±12.546, Episode_length: 175.200±15.574\n", ++ "Rollout 4019/9766, Reward: 277.381±19.163, Episode_length: 242.400±132.077\n", ++ "Rollout 4020/9766, Reward: 250.582±81.660, Episode_length: 259.200±196.798\n", ++ "Rollout 4021/9766, Reward: 284.584±17.881, Episode_length: 187.800±52.560\n", ++ "Rollout 4022/9766, Reward: 277.782±20.609, Episode_length: 216.600±75.562\n", ++ "Rollout 4023/9766, Reward: 246.716±41.960, Episode_length: 351.300±327.532\n", ++ "Rollout 4024/9766, Reward: 278.670±39.445, Episode_length: 265.800±246.399\n", ++ "Rollout 4025/9766, Reward: 275.592±12.679, Episode_length: 187.200±62.318\n", ++ "Rollout 4026/9766, Reward: 241.806±83.835, Episode_length: 280.100±251.455\n", ++ "Rollout 4027/9766, Reward: 87.829±228.321, Episode_length: 174.700±57.051\n", ++ "Rollout 4028/9766, Reward: 279.072±15.878, Episode_length: 188.100±40.295\n", ++ "Rollout 4029/9766, Reward: 191.263±243.454, Episode_length: 224.600±151.206\n", ++ "Rollout 4030/9766, Reward: -98.452±459.029, Episode_length: 146.300±46.403\n", ++ "Rollout 4031/9766, Reward: -257.133±450.196, Episode_length: 126.400±41.083\n", ++ "Rollout 4032/9766, Reward: -655.028±668.170, Episode_length: 139.900±60.333\n", ++ "Rollout 4033/9766, Reward: -405.269±1036.184, Episode_length: 157.100±62.459\n", ++ "Rollout 4034/9766, Reward: 107.161±334.201, Episode_length: 163.800±41.928\n", ++ "Rollout 4035/9766, Reward: 119.027±310.679, Episode_length: 161.700±42.622\n", ++ "Rollout 4036/9766, Reward: 91.954±364.731, Episode_length: 191.900±78.131\n", ++ "Rollout 4037/9766, Reward: 197.347±253.415, Episode_length: 179.400±41.164\n", ++ "Rollout 4038/9766, Reward: -49.330±393.975, Episode_length: 140.700±48.336\n", ++ "Rollout 4039/9766, Reward: 133.107±312.649, Episode_length: 180.000±35.140\n", ++ "Rollout 4040/9766, Reward: -298.385±486.212, Episode_length: 177.600±124.385\n", ++ "Rollout 4041/9766, Reward: -145.608±544.821, Episode_length: 154.000±39.036\n", ++ "Rollout 4042/9766, Reward: -412.274±793.151, Episode_length: 212.000±195.370\n", ++ "Rollout 4043/9766, Reward: -4.381±427.665, Episode_length: 150.300±30.568\n", ++ "Rollout 4044/9766, Reward: 111.433±316.227, Episode_length: 179.300±91.793\n", ++ "Rollout 4045/9766, Reward: 111.457±331.910, Episode_length: 155.900±41.623\n", ++ "Rollout 4046/9766, Reward: 109.987±341.761, Episode_length: 179.700±94.726\n", ++ "Rollout 4047/9766, Reward: 70.980±320.923, Episode_length: 157.100±57.911\n", ++ "Rollout 4048/9766, Reward: -0.017±412.906, Episode_length: 141.700±43.594\n", ++ "Rollout 4049/9766, Reward: 188.100±261.485, Episode_length: 163.800±30.112\n", ++ "Rollout 4050/9766, Reward: 77.166±407.797, Episode_length: 155.400±26.530\n", ++ "Rollout 4051/9766, Reward: 110.134±337.073, Episode_length: 156.600±42.195\n", ++ "Rollout 4052/9766, Reward: 279.045±15.387, Episode_length: 197.300±42.551\n", ++ "Rollout 4053/9766, Reward: 197.683±204.282, Episode_length: 262.700±249.672\n", ++ "Rollout 4054/9766, Reward: 246.782±82.563, Episode_length: 260.900±249.080\n", ++ "Rollout 4055/9766, Reward: 174.465±235.068, Episode_length: 188.000±81.896\n", ++ "Rollout 4056/9766, Reward: 287.669±17.216, Episode_length: 183.200±25.802\n", ++ "Rollout 4057/9766, Reward: 272.664±17.216, Episode_length: 192.600±31.039\n", ++ "Rollout 4058/9766, Reward: 271.807±40.400, Episode_length: 272.700±243.859\n", ++ "Rollout 4059/9766, Reward: 278.103±18.377, Episode_length: 183.100±25.982\n", ++ "Rollout 4060/9766, Reward: 286.654±12.158, Episode_length: 187.900±30.231\n", ++ "Rollout 4061/9766, Reward: 239.085±114.265, Episode_length: 206.000±90.782\n", ++ "Rollout 4062/9766, Reward: 267.420±37.362, Episode_length: 261.900±246.557\n", ++ "Rollout 4063/9766, Reward: 285.553±18.417, Episode_length: 209.000±55.258\n", ++ "Rollout 4064/9766, Reward: 279.668±16.864, Episode_length: 189.100±25.189\n", ++ "Rollout 4065/9766, Reward: 267.988±33.217, Episode_length: 283.500±244.474\n", ++ "Rollout 4066/9766, Reward: 282.088±18.650, Episode_length: 271.000±223.717\n", ++ "Rollout 4067/9766, Reward: 212.019±63.631, Episode_length: 715.300±359.307\n", ++ "Rollout 4068/9766, Reward: 188.541±53.210, Episode_length: 840.600±318.913\n", ++ "Rollout 4069/9766, Reward: 176.194±46.176, Episode_length: 853.900±294.929\n", ++ "Rollout 4070/9766, Reward: 211.268±60.286, Episode_length: 740.500±364.203\n", ++ "Rollout 4071/9766, Reward: 224.855±59.592, Episode_length: 634.700±376.683\n", ++ "Rollout 4072/9766, Reward: 200.080±62.866, Episode_length: 704.600±362.652\n", ++ "Rollout 4073/9766, Reward: 255.284±34.017, Episode_length: 257.400±248.523\n", ++ "Rollout 4074/9766, Reward: 272.775±41.493, Episode_length: 285.300±246.263\n", ++ "Rollout 4075/9766, Reward: 283.568±13.952, Episode_length: 199.100±28.971\n", ++ "Rollout 4076/9766, Reward: 257.755±44.376, Episode_length: 348.500±325.941\n", ++ "Rollout 4077/9766, Reward: 251.644±48.582, Episode_length: 342.500±329.723\n", ++ "Rollout 4078/9766, Reward: 276.286±34.997, Episode_length: 286.600±239.494\n", ++ "Rollout 4079/9766, Reward: 260.800±47.448, Episode_length: 292.000±239.461\n", ++ "Rollout 4080/9766, Reward: 244.750±52.514, Episode_length: 345.800±327.881\n", ++ "Rollout 4081/9766, Reward: 247.088±54.783, Episode_length: 363.800±319.453\n", ++ "Rollout 4082/9766, Reward: 240.448±65.201, Episode_length: 459.000±357.142\n", ++ "Rollout 4083/9766, Reward: 242.940±63.427, Episode_length: 357.300±323.957\n", ++ "Rollout 4084/9766, Reward: 234.166±53.365, Episode_length: 421.800±340.567\n", ++ "Rollout 4085/9766, Reward: 255.457±40.556, Episode_length: 268.800±244.896\n", ++ "Rollout 4086/9766, Reward: 246.393±61.588, Episode_length: 295.200±238.740\n", ++ "Rollout 4087/9766, Reward: 246.630±50.399, Episode_length: 294.500±237.983\n", ++ "Rollout 4088/9766, Reward: 256.127±26.485, Episode_length: 297.500±168.759\n", ++ "Rollout 4089/9766, Reward: 240.530±68.782, Episode_length: 289.200±242.003\n", ++ "Rollout 4090/9766, Reward: 244.103±49.220, Episode_length: 262.600±246.950\n", ++ "Rollout 4091/9766, Reward: 227.089±58.824, Episode_length: 379.000±312.593\n", ++ "Rollout 4092/9766, Reward: 246.882±19.134, Episode_length: 214.100±59.145\n", ++ "Rollout 4093/9766, Reward: 239.183±25.660, Episode_length: 276.200±242.732\n", ++ "Rollout 4094/9766, Reward: 236.581±29.751, Episode_length: 254.500±146.003\n", ++ "Rollout 4095/9766, Reward: 212.571±87.546, Episode_length: 319.400±267.568\n", ++ "Rollout 4096/9766, Reward: 197.158±108.087, Episode_length: 322.000±264.375\n", ++ "Rollout 4097/9766, Reward: 212.267±41.601, Episode_length: 418.900±320.315\n", ++ "Rollout 4098/9766, Reward: 197.542±74.008, Episode_length: 285.100±243.893\n", ++ "Rollout 4099/9766, Reward: 194.415±90.221, Episode_length: 226.800±110.137\n", ++ "Rollout 4100/9766, Reward: 111.477±220.149, Episode_length: 283.200±244.243\n", ++ "Rollout 4101/9766, Reward: 169.877±210.769, Episode_length: 312.200±239.134\n", ++ "Rollout 4102/9766, Reward: 230.573±60.759, Episode_length: 317.000±264.006\n", ++ "Rollout 4103/9766, Reward: 191.922±144.557, Episode_length: 208.500±37.146\n", ++ "Rollout 4104/9766, Reward: 214.649±61.978, Episode_length: 471.300±359.579\n", ++ "Rollout 4105/9766, Reward: 255.703±24.049, Episode_length: 284.500±204.449\n", ++ "Rollout 4106/9766, Reward: 240.620±48.683, Episode_length: 341.400±266.963\n", ++ "Rollout 4107/9766, Reward: 259.365±38.467, Episode_length: 268.800±245.400\n", ++ "Rollout 4108/9766, Reward: 267.829±16.930, Episode_length: 178.200±21.581\n", ++ "Rollout 4109/9766, Reward: 249.301±38.554, Episode_length: 278.900±232.593\n", ++ "Rollout 4110/9766, Reward: 231.054±62.127, Episode_length: 436.100±369.606\n", ++ "Rollout 4111/9766, Reward: 244.145±44.832, Episode_length: 256.100±58.509\n", ++ "Rollout 4112/9766, Reward: 236.638±84.848, Episode_length: 268.900±244.338\n", ++ "Rollout 4113/9766, Reward: 276.406±15.385, Episode_length: 184.600±27.288\n", ++ "Rollout 4114/9766, Reward: 263.132±37.185, Episode_length: 247.700±62.639\n", ++ "Rollout 4115/9766, Reward: 262.539±23.831, Episode_length: 221.600±91.749\n", ++ "Rollout 4116/9766, Reward: 269.379±34.794, Episode_length: 230.300±96.590\n", ++ "Rollout 4117/9766, Reward: 270.969±34.352, Episode_length: 273.700±164.330\n", ++ "Rollout 4118/9766, Reward: 265.768±32.570, Episode_length: 235.000±77.345\n", ++ "Rollout 4119/9766, Reward: 271.014±29.188, Episode_length: 306.000±172.157\n", ++ "Rollout 4120/9766, Reward: 275.391±18.743, Episode_length: 192.500±25.461\n", ++ "Rollout 4121/9766, Reward: 279.945±31.908, Episode_length: 232.400±77.368\n", ++ "Rollout 4122/9766, Reward: 159.116±325.015, Episode_length: 194.300±35.452\n", ++ "Rollout 4123/9766, Reward: 282.409±24.948, Episode_length: 205.700±52.263\n", ++ "Rollout 4124/9766, Reward: 273.121±19.420, Episode_length: 207.100±59.319\n", ++ "Rollout 4125/9766, Reward: 271.648±18.109, Episode_length: 216.000±56.464\n", ++ "Rollout 4126/9766, Reward: 283.708±20.158, Episode_length: 196.900±25.034\n", ++ "Rollout 4127/9766, Reward: 281.837±15.914, Episode_length: 177.600±24.739\n", ++ "Rollout 4128/9766, Reward: 282.999±16.136, Episode_length: 171.800±32.572\n", ++ "Rollout 4129/9766, Reward: 285.037±9.805, Episode_length: 205.000±58.956\n", ++ "Rollout 4130/9766, Reward: 267.810±48.854, Episode_length: 279.800±241.304\n", ++ "Rollout 4131/9766, Reward: 279.752±15.229, Episode_length: 178.100±26.482\n", ++ "Rollout 4132/9766, Reward: 289.026±14.925, Episode_length: 185.400±18.150\n", ++ "Rollout 4133/9766, Reward: 287.191±12.100, Episode_length: 183.200±26.951\n", ++ "Rollout 4134/9766, Reward: 278.074±16.255, Episode_length: 177.100±20.142\n", ++ "Rollout 4135/9766, Reward: 283.402±10.480, Episode_length: 179.200±26.065\n", ++ "Rollout 4136/9766, Reward: 281.992±16.835, Episode_length: 183.800±22.153\n", ++ "Rollout 4137/9766, Reward: 287.521±7.759, Episode_length: 181.500±25.734\n", ++ "Rollout 4138/9766, Reward: 283.998±17.633, Episode_length: 175.500±19.413\n", ++ "Rollout 4139/9766, Reward: 279.992±22.696, Episode_length: 180.000±27.651\n", ++ "Rollout 4140/9766, Reward: 277.738±23.621, Episode_length: 179.800±23.974\n", ++ "Rollout 4141/9766, Reward: 267.953±32.938, Episode_length: 231.800±158.701\n", ++ "Rollout 4142/9766, Reward: 240.261±94.799, Episode_length: 173.400±37.098\n", ++ "Rollout 4143/9766, Reward: 284.909±13.547, Episode_length: 184.100±25.458\n", ++ "Rollout 4144/9766, Reward: 282.372±18.506, Episode_length: 253.800±168.535\n", ++ "Rollout 4145/9766, Reward: 278.656±18.640, Episode_length: 182.900±16.489\n", ++ "Rollout 4146/9766, Reward: 273.173±20.365, Episode_length: 191.400±25.148\n", ++ "Rollout 4147/9766, Reward: 258.444±37.756, Episode_length: 233.200±78.105\n", ++ "Rollout 4148/9766, Reward: 285.682±20.425, Episode_length: 194.100±26.554\n", ++ "Rollout 4149/9766, Reward: 281.410±13.570, Episode_length: 190.000±19.473\n", ++ "Rollout 4150/9766, Reward: 262.373±25.906, Episode_length: 229.200±157.747\n", ++ "Rollout 4151/9766, Reward: 268.468±68.165, Episode_length: 268.900±243.960\n", ++ "Rollout 4152/9766, Reward: 251.271±42.443, Episode_length: 253.000±165.557\n", ++ "Rollout 4153/9766, Reward: 218.307±151.807, Episode_length: 209.100±67.871\n", ++ "Rollout 4154/9766, Reward: 229.474±87.973, Episode_length: 261.800±246.802\n", ++ "Rollout 4155/9766, Reward: 270.710±31.926, Episode_length: 200.800±64.764\n", ++ "Rollout 4156/9766, Reward: 255.409±44.143, Episode_length: 261.600±247.048\n", ++ "Rollout 4157/9766, Reward: 273.411±16.538, Episode_length: 177.000±24.273\n", ++ "Rollout 4158/9766, Reward: 293.296±13.581, Episode_length: 199.300±61.733\n", ++ "Rollout 4159/9766, Reward: 276.436±19.909, Episode_length: 176.000±20.293\n", ++ "Rollout 4160/9766, Reward: 282.277±24.762, Episode_length: 266.900±234.481\n", ++ "Rollout 4161/9766, Reward: 286.440±14.427, Episode_length: 194.200±12.671\n", ++ "Rollout 4162/9766, Reward: 274.147±25.200, Episode_length: 219.000±69.249\n", ++ "Rollout 4163/9766, Reward: 282.676±16.804, Episode_length: 194.100±21.682\n", ++ "Rollout 4164/9766, Reward: 291.735±14.745, Episode_length: 190.900±24.189\n", ++ "Rollout 4165/9766, Reward: 273.480±16.579, Episode_length: 235.400±171.554\n", ++ "Rollout 4166/9766, Reward: 277.019±37.119, Episode_length: 267.900±245.548\n", ++ "Rollout 4167/9766, Reward: 280.976±20.138, Episode_length: 177.600±24.864\n", ++ "Rollout 4168/9766, Reward: 289.574±19.357, Episode_length: 191.400±32.144\n", ++ "Rollout 4169/9766, Reward: 279.336±12.652, Episode_length: 185.600±17.608\n", ++ "Rollout 4170/9766, Reward: 283.432±14.637, Episode_length: 185.400±23.049\n", ++ "Rollout 4171/9766, Reward: 264.923±34.220, Episode_length: 253.600±249.360\n", ++ "Rollout 4172/9766, Reward: 289.938±20.902, Episode_length: 201.700±79.699\n", ++ "Rollout 4173/9766, Reward: 273.639±16.935, Episode_length: 197.700±102.631\n", ++ "Rollout 4174/9766, Reward: 277.844±16.023, Episode_length: 172.500±19.366\n", ++ "Rollout 4175/9766, Reward: 271.772±18.307, Episode_length: 169.900±22.088\n", ++ "Rollout 4176/9766, Reward: 271.830±17.246, Episode_length: 258.200±204.578\n", ++ "Rollout 4177/9766, Reward: 281.730±22.888, Episode_length: 165.700±18.995\n", ++ "Rollout 4178/9766, Reward: 246.149±59.202, Episode_length: 379.100±319.053\n", ++ "Rollout 4179/9766, Reward: 278.565±19.728, Episode_length: 200.300±27.807\n", ++ "Rollout 4180/9766, Reward: 281.518±18.657, Episode_length: 246.500±178.744\n", ++ "Rollout 4181/9766, Reward: 280.069±18.669, Episode_length: 184.200±23.400\n", ++ "Rollout 4182/9766, Reward: 283.509±25.122, Episode_length: 244.500±151.492\n", ++ "Rollout 4183/9766, Reward: 272.844±42.107, Episode_length: 270.700±244.004\n", ++ "Rollout 4184/9766, Reward: 270.900±33.083, Episode_length: 264.300±245.746\n", ++ "Rollout 4185/9766, Reward: 266.759±37.136, Episode_length: 264.300±176.166\n", ++ "Rollout 4186/9766, Reward: 279.710±18.168, Episode_length: 183.500±29.867\n", ++ "Rollout 4187/9766, Reward: 264.894±44.361, Episode_length: 280.200±241.340\n", ++ "Rollout 4188/9766, Reward: 243.453±148.546, Episode_length: 213.000±53.100\n", ++ "Rollout 4189/9766, Reward: 274.041±20.972, Episode_length: 279.900±197.851\n", ++ "Rollout 4190/9766, Reward: 275.245±17.988, Episode_length: 201.700±30.748\n", ++ "Rollout 4191/9766, Reward: 280.414±17.282, Episode_length: 197.600±39.505\n", ++ "Rollout 4192/9766, Reward: 285.924±13.438, Episode_length: 193.800±30.420\n", ++ "Rollout 4193/9766, Reward: 266.882±38.595, Episode_length: 333.700±292.375\n", ++ "Rollout 4194/9766, Reward: 286.615±11.390, Episode_length: 203.600±39.583\n", ++ "Rollout 4195/9766, Reward: 195.723±227.632, Episode_length: 168.700±35.117\n", ++ "Rollout 4196/9766, Reward: -154.797±445.159, Episode_length: 146.000±63.193\n", ++ "Rollout 4197/9766, Reward: -101.304±425.909, Episode_length: 229.300±262.045\n", ++ "Rollout 4198/9766, Reward: 197.920±223.779, Episode_length: 178.200±44.452\n", ++ "Rollout 4199/9766, Reward: 110.711±346.868, Episode_length: 166.400±47.892\n", ++ "Rollout 4200/9766, Reward: 270.968±38.788, Episode_length: 277.600±242.500\n", ++ "Rollout 4201/9766, Reward: 274.117±23.229, Episode_length: 172.400±17.878\n", ++ "Rollout 4202/9766, Reward: 282.362±10.623, Episode_length: 217.700±37.070\n", ++ "Rollout 4203/9766, Reward: 276.706±13.035, Episode_length: 181.900±17.259\n", ++ "Rollout 4204/9766, Reward: 177.877±230.605, Episode_length: 257.100±183.415\n", ++ "Rollout 4205/9766, Reward: 279.109±18.132, Episode_length: 190.000±31.711\n", ++ "Rollout 4206/9766, Reward: 278.780±14.366, Episode_length: 178.100±16.718\n", ++ "Rollout 4207/9766, Reward: 287.352±18.328, Episode_length: 192.300±22.055\n", ++ "Rollout 4208/9766, Reward: 254.497±50.991, Episode_length: 371.300±318.832\n", ++ "Rollout 4209/9766, Reward: 258.381±35.541, Episode_length: 275.200±242.999\n", ++ "Rollout 4210/9766, Reward: 205.143±111.971, Episode_length: 437.100±369.083\n", ++ "Rollout 4211/9766, Reward: 215.295±128.772, Episode_length: 399.000±315.024\n", ++ "Rollout 4212/9766, Reward: 241.476±60.921, Episode_length: 523.200±390.702\n", ++ "Rollout 4213/9766, Reward: 206.105±42.780, Episode_length: 732.500±328.521\n", ++ "Rollout 4214/9766, Reward: 199.592±55.813, Episode_length: 786.300±328.252\n", ++ "Rollout 4215/9766, Reward: 242.063±46.460, Episode_length: 594.800±393.566\n", ++ "Rollout 4216/9766, Reward: 231.630±53.300, Episode_length: 551.100±369.220\n", ++ "Rollout 4217/9766, Reward: 246.846±62.774, Episode_length: 365.500±319.208\n", ++ "Rollout 4218/9766, Reward: 281.889±15.715, Episode_length: 211.400±36.371\n", ++ "Rollout 4219/9766, Reward: 283.183±38.407, Episode_length: 294.800±242.704\n", ++ "Rollout 4220/9766, Reward: 237.972±91.067, Episode_length: 351.600±325.781\n", ++ "Rollout 4221/9766, Reward: 248.608±83.549, Episode_length: 286.400±241.651\n", ++ "Rollout 4222/9766, Reward: 256.453±43.380, Episode_length: 372.200±318.886\n", ++ "Rollout 4223/9766, Reward: 266.592±31.395, Episode_length: 275.800±244.053\n", ++ "Rollout 4224/9766, Reward: 274.514±11.377, Episode_length: 179.200±26.305\n", ++ "Rollout 4225/9766, Reward: 285.537±14.066, Episode_length: 192.700±24.137\n", ++ "Rollout 4226/9766, Reward: 275.042±18.683, Episode_length: 188.900±27.941\n", ++ "Rollout 4227/9766, Reward: 285.609±16.689, Episode_length: 192.200±24.987\n", ++ "Rollout 4228/9766, Reward: 279.575±17.950, Episode_length: 187.700±29.499\n", ++ "Rollout 4229/9766, Reward: 286.198±21.232, Episode_length: 214.600±50.536\n", ++ "Rollout 4230/9766, Reward: 244.746±56.072, Episode_length: 438.600±368.563\n", ++ "Rollout 4231/9766, Reward: 261.274±55.527, Episode_length: 347.800±327.310\n", ++ "Rollout 4232/9766, Reward: 258.523±49.826, Episode_length: 412.900±344.266\n", ++ "Rollout 4233/9766, Reward: 234.773±81.011, Episode_length: 262.700±252.977\n", ++ "Rollout 4234/9766, Reward: 264.363±43.763, Episode_length: 321.800±264.254\n", ++ "Rollout 4235/9766, Reward: 261.215±57.043, Episode_length: 361.000±323.305\n", ++ "Rollout 4236/9766, Reward: 237.794±59.144, Episode_length: 562.400±383.196\n", ++ "Rollout 4237/9766, Reward: 192.203±58.225, Episode_length: 767.200±356.654\n", ++ "Rollout 4238/9766, Reward: 180.886±50.765, Episode_length: 847.200±305.600\n", ++ "Rollout 4239/9766, Reward: 192.270±56.917, Episode_length: 850.600±263.735\n", ++ "Rollout 4240/9766, Reward: 248.258±53.797, Episode_length: 397.100±342.625\n", ++ "Rollout 4241/9766, Reward: 256.930±43.689, Episode_length: 269.100±246.377\n", ++ "Rollout 4242/9766, Reward: 279.514±18.029, Episode_length: 184.500±21.727\n", ++ "Rollout 4243/9766, Reward: 294.051±18.975, Episode_length: 193.400±16.433\n", ++ "Rollout 4244/9766, Reward: 274.392±17.315, Episode_length: 253.100±161.176\n", ++ "Rollout 4245/9766, Reward: 268.304±19.156, Episode_length: 179.600±14.527\n", ++ "Rollout 4246/9766, Reward: 273.499±46.211, Episode_length: 259.600±248.014\n", ++ "Rollout 4247/9766, Reward: 273.466±18.375, Episode_length: 189.100±19.821\n", ++ "Rollout 4248/9766, Reward: 270.361±16.365, Episode_length: 177.700±19.935\n", ++ "Rollout 4249/9766, Reward: 278.245±17.373, Episode_length: 186.300±25.605\n", ++ "Rollout 4250/9766, Reward: 276.473±14.498, Episode_length: 179.700±11.782\n", ++ "Rollout 4251/9766, Reward: 231.328±167.039, Episode_length: 178.200±19.135\n", ++ "Rollout 4252/9766, Reward: 277.339±22.493, Episode_length: 172.900±14.700\n", ++ "Rollout 4253/9766, Reward: 292.359±17.830, Episode_length: 184.500±22.295\n", ++ "Rollout 4254/9766, Reward: 275.684±18.791, Episode_length: 186.300±19.121\n", ++ "Rollout 4255/9766, Reward: 283.403±17.387, Episode_length: 190.400±21.068\n", ++ "Rollout 4256/9766, Reward: 281.537±15.735, Episode_length: 171.800±17.848\n", ++ "Rollout 4257/9766, Reward: 259.943±66.729, Episode_length: 265.800±245.902\n", ++ "Rollout 4258/9766, Reward: 269.473±44.157, Episode_length: 255.000±248.963\n", ++ "Rollout 4259/9766, Reward: 289.697±11.922, Episode_length: 192.400±21.914\n", ++ "Rollout 4260/9766, Reward: 296.120±18.892, Episode_length: 194.400±14.001\n", ++ "Rollout 4261/9766, Reward: 290.723±23.347, Episode_length: 247.200±161.200\n", ++ "Rollout 4262/9766, Reward: 278.649±18.579, Episode_length: 185.100±31.986\n", ++ "Rollout 4263/9766, Reward: 261.261±40.332, Episode_length: 339.600±330.694\n", ++ "Rollout 4264/9766, Reward: 259.751±55.021, Episode_length: 354.600±323.267\n", ++ "Rollout 4265/9766, Reward: 284.826±16.476, Episode_length: 199.500±42.963\n", ++ "Rollout 4266/9766, Reward: 281.289±15.085, Episode_length: 186.800±34.531\n", ++ "Rollout 4267/9766, Reward: 277.323±20.411, Episode_length: 183.600±19.294\n", ++ "Rollout 4268/9766, Reward: 252.216±65.192, Episode_length: 383.000±315.320\n", ++ "Rollout 4269/9766, Reward: 192.203±147.709, Episode_length: 420.300±320.674\n", ++ "Rollout 4270/9766, Reward: 240.376±65.611, Episode_length: 391.200±332.250\n", ++ "Rollout 4271/9766, Reward: 258.064±43.264, Episode_length: 332.300±308.704\n", ++ "Rollout 4272/9766, Reward: 263.962±38.502, Episode_length: 329.900±301.740\n", ++ "Rollout 4273/9766, Reward: 263.862±45.178, Episode_length: 278.200±248.177\n", ++ "Rollout 4274/9766, Reward: 224.998±128.620, Episode_length: 231.200±157.377\n", ++ "Rollout 4275/9766, Reward: 280.258±12.223, Episode_length: 182.300±26.150\n", ++ "Rollout 4276/9766, Reward: 240.105±82.541, Episode_length: 332.000±296.126\n", ++ "Rollout 4277/9766, Reward: 285.197±19.260, Episode_length: 171.000±21.693\n", ++ "Rollout 4278/9766, Reward: 261.317±44.468, Episode_length: 255.100±248.635\n", ++ "Rollout 4279/9766, Reward: 271.739±33.314, Episode_length: 249.300±250.657\n", ++ "Rollout 4280/9766, Reward: 259.254±38.704, Episode_length: 254.200±249.155\n", ++ "Rollout 4281/9766, Reward: 278.680±13.099, Episode_length: 181.800±11.374\n", ++ "Rollout 4282/9766, Reward: 280.015±22.125, Episode_length: 235.300±135.489\n", ++ "Rollout 4283/9766, Reward: 270.679±36.681, Episode_length: 261.700±246.714\n", ++ "Rollout 4284/9766, Reward: 262.153±46.648, Episode_length: 347.400±327.922\n", ++ "Rollout 4285/9766, Reward: 285.902±15.087, Episode_length: 181.900±24.304\n", ++ "Rollout 4286/9766, Reward: 270.570±13.553, Episode_length: 285.800±240.539\n", ++ "Rollout 4287/9766, Reward: 274.133±43.669, Episode_length: 267.400±244.585\n", ++ "Rollout 4288/9766, Reward: 290.866±16.151, Episode_length: 174.400±11.672\n", ++ "Rollout 4289/9766, Reward: 284.202±17.899, Episode_length: 194.800±24.742\n", ++ "Rollout 4290/9766, Reward: 254.537±54.856, Episode_length: 432.500±335.048\n", ++ "Rollout 4291/9766, Reward: 288.943±14.878, Episode_length: 173.100±22.097\n", ++ "Rollout 4292/9766, Reward: 286.014±12.787, Episode_length: 172.800±21.669\n", ++ "Rollout 4293/9766, Reward: 278.156±33.654, Episode_length: 327.200±306.169\n", ++ "Rollout 4294/9766, Reward: 153.261±371.824, Episode_length: 256.800±249.507\n", ++ "Rollout 4295/9766, Reward: 289.658±14.073, Episode_length: 185.500±20.558\n", ++ "Rollout 4296/9766, Reward: 1.106±545.894, Episode_length: 156.100±20.613\n", ++ "Rollout 4297/9766, Reward: 277.070±8.712, Episode_length: 174.200±16.839\n", ++ "Rollout 4298/9766, Reward: 254.926±48.488, Episode_length: 346.600±327.135\n", ++ "Rollout 4299/9766, Reward: 286.127±20.130, Episode_length: 172.200±30.577\n", ++ "Rollout 4300/9766, Reward: 290.156±18.441, Episode_length: 185.000±26.397\n", ++ "Rollout 4301/9766, Reward: 281.585±40.548, Episode_length: 255.900±249.269\n", ++ "Rollout 4302/9766, Reward: 280.001±6.937, Episode_length: 173.300±25.366\n", ++ "Rollout 4303/9766, Reward: 280.371±38.073, Episode_length: 275.600±245.700\n", ++ "Rollout 4304/9766, Reward: 282.821±16.746, Episode_length: 201.500±69.773\n", ++ "Rollout 4305/9766, Reward: 261.624±38.898, Episode_length: 339.800±330.406\n", ++ "Rollout 4306/9766, Reward: 287.323±18.898, Episode_length: 184.700±23.238\n", ++ "Rollout 4307/9766, Reward: 262.893±47.532, Episode_length: 343.100±329.988\n", ++ "Rollout 4308/9766, Reward: 250.666±46.022, Episode_length: 329.400±335.749\n", ++ "Rollout 4309/9766, Reward: 279.709±13.909, Episode_length: 177.700±44.274\n", ++ "Rollout 4310/9766, Reward: 280.647±14.024, Episode_length: 183.100±24.394\n", ++ "Rollout 4311/9766, Reward: 214.438±131.162, Episode_length: 340.800±330.256\n", ++ "Rollout 4312/9766, Reward: 212.601±59.433, Episode_length: 674.700±399.810\n", ++ "Rollout 4313/9766, Reward: 214.404±53.183, Episode_length: 754.100±369.250\n", ++ "Rollout 4314/9766, Reward: 208.193±48.283, Episode_length: 808.500±315.758\n", ++ "Rollout 4315/9766, Reward: 223.918±60.202, Episode_length: 584.300±416.092\n", ++ "Rollout 4316/9766, Reward: 250.050±58.585, Episode_length: 474.700±356.930\n", ++ "Rollout 4317/9766, Reward: 207.019±56.871, Episode_length: 731.300±365.943\n", ++ "Rollout 4318/9766, Reward: 227.907±55.501, Episode_length: 580.300±419.863\n", ++ "Rollout 4319/9766, Reward: 231.712±62.818, Episode_length: 578.300±409.961\n", ++ "Rollout 4320/9766, Reward: 253.265±49.165, Episode_length: 332.600±333.918\n", ++ "Rollout 4321/9766, Reward: 285.316±13.978, Episode_length: 201.700±90.041\n", ++ "Rollout 4322/9766, Reward: 285.124±11.963, Episode_length: 179.600±23.239\n", ++ "Rollout 4323/9766, Reward: 277.168±19.158, Episode_length: 224.000±188.907\n", ++ "Rollout 4324/9766, Reward: 288.225±13.554, Episode_length: 188.500±22.137\n", ++ "Rollout 4325/9766, Reward: 282.073±12.203, Episode_length: 176.500±22.146\n", ++ "Rollout 4326/9766, Reward: 259.158±55.454, Episode_length: 355.200±323.510\n", ++ "Rollout 4327/9766, Reward: 286.064±18.469, Episode_length: 170.900±16.325\n", ++ "Rollout 4328/9766, Reward: 283.090±10.541, Episode_length: 169.200±16.278\n", ++ "Rollout 4329/9766, Reward: 261.912±34.707, Episode_length: 251.400±249.785\n", ++ "Rollout 4330/9766, Reward: 213.619±54.802, Episode_length: 667.500±407.469\n", ++ "Rollout 4331/9766, Reward: 262.797±42.636, Episode_length: 251.300±251.035\n", ++ "Rollout 4332/9766, Reward: 279.726±36.947, Episode_length: 261.900±246.678\n", ++ "Rollout 4333/9766, Reward: 286.308±13.019, Episode_length: 181.300±28.185\n", ++ "Rollout 4334/9766, Reward: 285.053±11.477, Episode_length: 168.500±19.846\n", ++ "Rollout 4335/9766, Reward: 255.565±49.795, Episode_length: 335.000±333.206\n", ++ "Rollout 4336/9766, Reward: 259.402±43.241, Episode_length: 258.200±248.179\n", ++ "Rollout 4337/9766, Reward: 273.862±40.965, Episode_length: 321.900±288.941\n", ++ "Rollout 4338/9766, Reward: 262.074±41.744, Episode_length: 253.000±251.809\n", ++ "Rollout 4339/9766, Reward: 279.271±16.681, Episode_length: 173.300±20.533\n", ++ "Rollout 4340/9766, Reward: 282.917±10.512, Episode_length: 180.400±30.578\n", ++ "Rollout 4341/9766, Reward: 284.366±16.456, Episode_length: 216.600±146.688\n", ++ "Rollout 4342/9766, Reward: 264.016±36.272, Episode_length: 342.300±304.888\n", ++ "Rollout 4343/9766, Reward: 276.651±15.973, Episode_length: 181.100±31.364\n", ++ "Rollout 4344/9766, Reward: 280.050±15.397, Episode_length: 178.000±47.760\n", ++ "Rollout 4345/9766, Reward: 280.994±12.495, Episode_length: 187.700±23.892\n", ++ "Rollout 4346/9766, Reward: 257.172±38.535, Episode_length: 252.900±249.688\n", ++ "Rollout 4347/9766, Reward: 279.763±15.234, Episode_length: 179.400±23.122\n", ++ "Rollout 4348/9766, Reward: 263.948±49.000, Episode_length: 344.900±308.762\n", ++ "Rollout 4349/9766, Reward: 267.845±36.093, Episode_length: 263.400±245.979\n", ++ "Rollout 4350/9766, Reward: 280.374±17.863, Episode_length: 194.700±33.362\n", ++ "Rollout 4351/9766, Reward: 272.396±23.590, Episode_length: 183.100±24.213\n", ++ "Rollout 4352/9766, Reward: 259.542±45.127, Episode_length: 315.700±271.367\n", ++ "Rollout 4353/9766, Reward: 261.584±81.623, Episode_length: 184.500±39.026\n", ++ "Rollout 4354/9766, Reward: 269.853±20.934, Episode_length: 170.100±21.035\n", ++ "Rollout 4355/9766, Reward: 277.990±16.971, Episode_length: 195.500±40.193\n", ++ "Rollout 4356/9766, Reward: 259.373±26.450, Episode_length: 223.000±82.941\n", ++ "Rollout 4357/9766, Reward: 275.001±10.037, Episode_length: 180.000±17.245\n", ++ "Rollout 4358/9766, Reward: 188.448±195.858, Episode_length: 204.800±50.636\n", ++ "Rollout 4359/9766, Reward: 267.138±20.637, Episode_length: 215.300±80.090\n", ++ "Rollout 4360/9766, Reward: 171.731±190.877, Episode_length: 159.700±31.582\n", ++ "Rollout 4361/9766, Reward: 272.229±22.129, Episode_length: 217.200±47.210\n", ++ "Rollout 4362/9766, Reward: 273.942±33.334, Episode_length: 283.600±216.632\n", ++ "Rollout 4363/9766, Reward: 275.428±19.701, Episode_length: 177.300±18.895\n", ++ "Rollout 4364/9766, Reward: 274.007±13.365, Episode_length: 205.300±42.909\n", ++ "Rollout 4365/9766, Reward: 283.958±22.168, Episode_length: 196.000±20.765\n", ++ "Rollout 4366/9766, Reward: 279.626±16.340, Episode_length: 203.100±44.187\n", ++ "Rollout 4367/9766, Reward: 290.115±14.054, Episode_length: 188.900±14.025\n", ++ "Rollout 4368/9766, Reward: 262.594±34.619, Episode_length: 253.400±249.260\n", ++ "Rollout 4369/9766, Reward: 268.995±15.825, Episode_length: 178.400±22.668\n", ++ "Rollout 4370/9766, Reward: 278.169±14.734, Episode_length: 230.200±178.663\n", ++ "Rollout 4371/9766, Reward: 263.652±43.392, Episode_length: 347.800±326.654\n", ++ "Rollout 4372/9766, Reward: 278.876±18.328, Episode_length: 183.600±13.915\n", ++ "Rollout 4373/9766, Reward: 278.591±15.445, Episode_length: 177.500±29.645\n", ++ "Rollout 4374/9766, Reward: 269.327±34.966, Episode_length: 257.400±249.182\n", ++ "Rollout 4375/9766, Reward: 287.144±11.470, Episode_length: 185.900±21.050\n", ++ "Rollout 4376/9766, Reward: 282.961±17.177, Episode_length: 177.500±29.388\n", ++ "Rollout 4377/9766, Reward: 271.288±42.744, Episode_length: 251.500±250.240\n", ++ "Rollout 4378/9766, Reward: 278.315±15.638, Episode_length: 167.700±29.045\n", ++ "Rollout 4379/9766, Reward: 283.927±19.662, Episode_length: 173.700±14.057\n", ++ "Rollout 4380/9766, Reward: 280.083±19.541, Episode_length: 210.900±99.688\n", ++ "Rollout 4381/9766, Reward: 280.446±15.323, Episode_length: 187.000±34.476\n", ++ "Rollout 4382/9766, Reward: 273.077±15.096, Episode_length: 226.700±134.067\n", ++ "Rollout 4383/9766, Reward: 257.664±33.270, Episode_length: 257.700±248.607\n", ++ "Rollout 4384/9766, Reward: 281.977±12.858, Episode_length: 179.100±24.279\n", ++ "Rollout 4385/9766, Reward: 245.855±49.813, Episode_length: 348.300±327.125\n", ++ "Rollout 4386/9766, Reward: 251.502±41.534, Episode_length: 335.100±332.858\n", ++ "Rollout 4387/9766, Reward: 270.542±37.699, Episode_length: 254.700±248.952\n", ++ "Rollout 4388/9766, Reward: 254.464±60.914, Episode_length: 347.100±327.682\n", ++ "Rollout 4389/9766, Reward: 296.030±9.544, Episode_length: 185.000±30.578\n", ++ "Rollout 4390/9766, Reward: 285.724±11.452, Episode_length: 171.600±19.820\n", ++ "Rollout 4391/9766, Reward: 275.184±19.847, Episode_length: 243.700±153.360\n", ++ "Rollout 4392/9766, Reward: 274.168±12.084, Episode_length: 176.400±13.410\n", ++ "Rollout 4393/9766, Reward: 281.598±15.095, Episode_length: 179.400±26.662\n", ++ "Rollout 4394/9766, Reward: 280.631±20.020, Episode_length: 179.000±24.645\n", ++ "Rollout 4395/9766, Reward: 260.629±56.290, Episode_length: 267.200±245.371\n", ++ "Rollout 4396/9766, Reward: 269.055±37.503, Episode_length: 282.500±240.920\n", ++ "Rollout 4397/9766, Reward: 266.759±44.503, Episode_length: 261.700±247.491\n", ++ "Rollout 4398/9766, Reward: 270.677±43.468, Episode_length: 268.300±245.087\n", ++ "Rollout 4399/9766, Reward: 264.656±53.588, Episode_length: 362.500±319.061\n", ++ "Rollout 4400/9766, Reward: 281.052±21.219, Episode_length: 247.900±201.327\n", ++ "Rollout 4401/9766, Reward: 278.812±13.671, Episode_length: 184.500±21.933\n", ++ "Rollout 4402/9766, Reward: 274.019±30.934, Episode_length: 308.900±188.705\n", ++ "Rollout 4403/9766, Reward: 226.437±61.781, Episode_length: 486.800±373.991\n", ++ "Rollout 4404/9766, Reward: 271.040±41.357, Episode_length: 276.300±242.579\n", ++ "Rollout 4405/9766, Reward: 278.716±15.838, Episode_length: 181.300±24.540\n", ++ "Rollout 4406/9766, Reward: 280.717±15.356, Episode_length: 192.800±27.151\n", ++ "Rollout 4407/9766, Reward: 289.788±16.366, Episode_length: 215.000±28.813\n", ++ "Rollout 4408/9766, Reward: 284.221±12.884, Episode_length: 203.700±15.881\n", ++ "Rollout 4409/9766, Reward: 275.938±20.453, Episode_length: 191.800±18.941\n", ++ "Rollout 4410/9766, Reward: 285.673±15.603, Episode_length: 195.000±18.232\n", ++ "Rollout 4411/9766, Reward: 283.848±13.363, Episode_length: 198.400±23.623\n", ++ "Rollout 4412/9766, Reward: 283.385±14.262, Episode_length: 185.800±25.155\n", ++ "Rollout 4413/9766, Reward: 287.467±14.131, Episode_length: 199.200±28.031\n", ++ "Rollout 4414/9766, Reward: 277.262±32.040, Episode_length: 345.900±302.172\n", ++ "Rollout 4415/9766, Reward: 282.302±13.343, Episode_length: 214.400±76.555\n", ++ "Rollout 4416/9766, Reward: 278.990±12.897, Episode_length: 172.100±19.378\n", ++ "Rollout 4417/9766, Reward: 281.069±16.885, Episode_length: 193.300±20.155\n", ++ "Rollout 4418/9766, Reward: 267.309±39.168, Episode_length: 267.800±244.674\n", ++ "Rollout 4419/9766, Reward: 146.511±391.915, Episode_length: 170.200±23.034\n", ++ "Rollout 4420/9766, Reward: 286.744±12.705, Episode_length: 190.300±23.554\n", ++ "Rollout 4421/9766, Reward: 119.344±463.275, Episode_length: 264.900±246.434\n", ++ "Rollout 4422/9766, Reward: 195.417±265.139, Episode_length: 163.100±20.945\n", ++ "Rollout 4423/9766, Reward: 282.858±14.643, Episode_length: 190.100±32.201\n", ++ "Rollout 4424/9766, Reward: 283.341±16.144, Episode_length: 177.800±24.363\n", ++ "Rollout 4425/9766, Reward: 127.881±481.262, Episode_length: 174.200±36.605\n", ++ "Rollout 4426/9766, Reward: 279.342±17.887, Episode_length: 169.800±28.833\n", ++ "Rollout 4427/9766, Reward: 277.947±7.615, Episode_length: 178.600±14.955\n", ++ "Rollout 4428/9766, Reward: 282.042±15.199, Episode_length: 245.300±154.629\n", ++ "Rollout 4429/9766, Reward: 282.537±9.373, Episode_length: 193.700±15.589\n", ++ "Rollout 4430/9766, Reward: 287.679±14.160, Episode_length: 199.200±26.623\n", ++ "Rollout 4431/9766, Reward: 276.091±17.651, Episode_length: 187.300±25.702\n", ++ "Rollout 4432/9766, Reward: 279.380±10.442, Episode_length: 171.400±20.254\n", ++ "Rollout 4433/9766, Reward: 282.626±21.802, Episode_length: 191.600±18.827\n", ++ "Rollout 4434/9766, Reward: 286.711±15.852, Episode_length: 183.000±21.986\n", ++ "Rollout 4435/9766, Reward: 281.399±19.410, Episode_length: 180.000±16.291\n", ++ "Rollout 4436/9766, Reward: 282.615±14.350, Episode_length: 189.700±28.256\n", ++ "Rollout 4437/9766, Reward: 288.924±11.957, Episode_length: 204.200±29.822\n", ++ "Rollout 4438/9766, Reward: 270.264±14.331, Episode_length: 183.400±20.006\n", ++ "Rollout 4439/9766, Reward: 270.074±7.276, Episode_length: 188.800±18.181\n", ++ "Rollout 4440/9766, Reward: 286.508±13.458, Episode_length: 187.000±29.428\n", ++ "Rollout 4441/9766, Reward: 288.334±12.696, Episode_length: 190.200±25.999\n", ++ "Rollout 4442/9766, Reward: 276.394±14.790, Episode_length: 187.700±19.058\n", ++ "Rollout 4443/9766, Reward: 285.530±13.698, Episode_length: 204.400±33.317\n", ++ "Rollout 4444/9766, Reward: 286.417±18.703, Episode_length: 210.000±21.804\n", ++ "Rollout 4445/9766, Reward: 275.752±9.596, Episode_length: 181.200±15.683\n", ++ "Rollout 4446/9766, Reward: 282.911±10.593, Episode_length: 187.700±20.553\n", ++ "Rollout 4447/9766, Reward: 289.248±9.577, Episode_length: 199.800±32.496\n", ++ "Rollout 4448/9766, Reward: 273.223±25.177, Episode_length: 190.500±17.767\n", ++ "Rollout 4449/9766, Reward: 271.738±51.795, Episode_length: 281.100±242.089\n", ++ "Rollout 4450/9766, Reward: 276.788±14.376, Episode_length: 253.300±203.824\n", ++ "Rollout 4451/9766, Reward: 285.589±20.715, Episode_length: 209.300±27.030\n", ++ "Rollout 4452/9766, Reward: 150.446±376.528, Episode_length: 186.800±32.990\n", ++ "Rollout 4453/9766, Reward: 114.502±479.754, Episode_length: 182.000±28.284\n", ++ "Rollout 4454/9766, Reward: 262.128±19.649, Episode_length: 248.400±136.849\n", ++ "Rollout 4455/9766, Reward: 273.474±20.213, Episode_length: 206.300±34.351\n", ++ "Rollout 4456/9766, Reward: 279.097±16.976, Episode_length: 211.400±38.237\n", ++ "Rollout 4457/9766, Reward: 271.919±27.217, Episode_length: 231.800±81.773\n", ++ "Rollout 4458/9766, Reward: 276.174±22.562, Episode_length: 199.900±31.415\n", ++ "Rollout 4459/9766, Reward: 280.369±21.720, Episode_length: 208.500±30.467\n", ++ "Rollout 4460/9766, Reward: 130.316±431.627, Episode_length: 186.100±29.201\n", ++ "Rollout 4461/9766, Reward: 291.142±11.371, Episode_length: 198.200±24.766\n", ++ "Rollout 4462/9766, Reward: 276.855±15.968, Episode_length: 192.100±29.965\n", ++ "Rollout 4463/9766, Reward: 284.922±15.783, Episode_length: 195.200±38.215\n", ++ "Rollout 4464/9766, Reward: 278.570±9.597, Episode_length: 203.500±36.884\n", ++ "Rollout 4465/9766, Reward: 262.346±37.672, Episode_length: 267.900±245.086\n", ++ "Rollout 4466/9766, Reward: 285.015±18.245, Episode_length: 195.100±35.498\n", ++ "Rollout 4467/9766, Reward: 226.498±126.871, Episode_length: 219.400±131.898\n", ++ "Rollout 4468/9766, Reward: 281.451±20.133, Episode_length: 188.700±28.203\n", ++ "Rollout 4469/9766, Reward: 290.844±9.778, Episode_length: 176.400±24.780\n", ++ "Rollout 4470/9766, Reward: 279.334±15.759, Episode_length: 177.600±13.887\n", ++ "Rollout 4471/9766, Reward: 270.721±12.139, Episode_length: 176.700±13.886\n", ++ "Rollout 4472/9766, Reward: 278.467±16.511, Episode_length: 174.700±22.459\n", ++ "Rollout 4473/9766, Reward: 286.942±18.272, Episode_length: 175.400±26.530\n", ++ "Rollout 4474/9766, Reward: 277.689±22.363, Episode_length: 176.800±19.431\n", ++ "Rollout 4475/9766, Reward: 281.305±18.906, Episode_length: 180.900±25.882\n", ++ "Rollout 4476/9766, Reward: 277.919±18.228, Episode_length: 166.900±17.369\n", ++ "Rollout 4477/9766, Reward: 273.812±44.404, Episode_length: 266.900±245.791\n", ++ "Rollout 4478/9766, Reward: 278.020±13.135, Episode_length: 184.400±21.846\n", ++ "Rollout 4479/9766, Reward: 282.094±19.476, Episode_length: 175.300±15.805\n", ++ "Rollout 4480/9766, Reward: 288.345±14.104, Episode_length: 181.200±18.654\n", ++ "Rollout 4481/9766, Reward: 269.201±28.902, Episode_length: 234.700±153.807\n", ++ "Rollout 4482/9766, Reward: 287.989±7.179, Episode_length: 178.200±22.569\n", ++ "Rollout 4483/9766, Reward: 239.182±144.216, Episode_length: 186.500±26.280\n", ++ "Rollout 4484/9766, Reward: 290.507±14.263, Episode_length: 197.000±22.334\n", ++ "Rollout 4485/9766, Reward: 274.594±16.071, Episode_length: 168.100±13.766\n", ++ "Rollout 4486/9766, Reward: 154.223±383.921, Episode_length: 179.700±29.752\n", ++ "Rollout 4487/9766, Reward: 173.888±321.406, Episode_length: 159.800±21.042\n", ++ "Rollout 4488/9766, Reward: 246.787±140.501, Episode_length: 174.600±24.398\n", ++ "Rollout 4489/9766, Reward: 289.117±12.752, Episode_length: 189.500±34.774\n", ++ "Rollout 4490/9766, Reward: 185.970±284.692, Episode_length: 210.800±117.788\n", ++ "Rollout 4491/9766, Reward: 170.047±344.768, Episode_length: 184.100±28.144\n", ++ "Rollout 4492/9766, Reward: 276.932±11.232, Episode_length: 185.900±28.144\n", ++ "Rollout 4493/9766, Reward: 153.572±375.562, Episode_length: 173.000±25.361\n", ++ "Rollout 4494/9766, Reward: 282.738±24.834, Episode_length: 193.400±33.341\n", ++ "Rollout 4495/9766, Reward: 283.633±10.203, Episode_length: 177.700±20.080\n", ++ "Rollout 4496/9766, Reward: 164.114±363.475, Episode_length: 182.900±60.336\n", ++ "Rollout 4497/9766, Reward: 279.242±13.660, Episode_length: 182.500±27.152\n", ++ "Rollout 4498/9766, Reward: 155.912±356.003, Episode_length: 203.000±85.708\n", ++ "Rollout 4499/9766, Reward: 128.687±425.759, Episode_length: 240.400±228.772\n", ++ "Rollout 4500/9766, Reward: 282.324±13.130, Episode_length: 183.500±21.786\n", ++ "Rollout 4501/9766, Reward: 277.199±10.817, Episode_length: 181.200±13.666\n", ++ "Rollout 4502/9766, Reward: 278.813±33.308, Episode_length: 268.900±244.688\n", ++ "Rollout 4503/9766, Reward: 265.963±39.261, Episode_length: 323.600±279.549\n", ++ "Rollout 4504/9766, Reward: 276.063±14.169, Episode_length: 186.900±35.948\n", ++ "Rollout 4505/9766, Reward: 265.792±40.920, Episode_length: 264.000±253.397\n", ++ "Rollout 4506/9766, Reward: 151.280±370.207, Episode_length: 167.300±26.340\n", ++ "Rollout 4507/9766, Reward: 283.192±18.281, Episode_length: 165.200±10.703\n", ++ "Rollout 4508/9766, Reward: 271.529±18.560, Episode_length: 327.800±244.760\n", ++ "Rollout 4509/9766, Reward: 270.600±35.437, Episode_length: 256.000±248.423\n", ++ "Rollout 4510/9766, Reward: 275.143±45.066, Episode_length: 267.300±244.510\n", ++ "Rollout 4511/9766, Reward: 275.566±17.741, Episode_length: 172.200±16.011\n", ++ "Rollout 4512/9766, Reward: 265.013±32.857, Episode_length: 255.500±248.925\n", ++ "Rollout 4513/9766, Reward: 282.708±19.194, Episode_length: 183.000±22.414\n", ++ "Rollout 4514/9766, Reward: 289.622±11.865, Episode_length: 165.500±18.151\n", ++ "Rollout 4515/9766, Reward: 273.530±38.699, Episode_length: 267.200±245.218\n", ++ "Rollout 4516/9766, Reward: 280.942±17.246, Episode_length: 177.000±19.183\n", ++ "Rollout 4517/9766, Reward: 285.442±37.290, Episode_length: 281.400±240.115\n", ++ "Rollout 4518/9766, Reward: 267.535±30.302, Episode_length: 259.200±247.334\n", ++ "Rollout 4519/9766, Reward: 285.438±13.856, Episode_length: 186.500±19.643\n", ++ "Rollout 4520/9766, Reward: 290.034±15.633, Episode_length: 187.600±17.391\n", ++ "Rollout 4521/9766, Reward: 282.475±19.482, Episode_length: 181.600±15.863\n", ++ "Rollout 4522/9766, Reward: 279.427±14.970, Episode_length: 177.200±18.546\n", ++ "Rollout 4523/9766, Reward: 289.254±19.283, Episode_length: 181.300±22.610\n", ++ "Rollout 4524/9766, Reward: 280.319±13.966, Episode_length: 178.000±18.580\n", ++ "Rollout 4525/9766, Reward: 280.453±22.857, Episode_length: 174.000±23.673\n", ++ "Rollout 4526/9766, Reward: 235.660±133.397, Episode_length: 161.000±31.244\n", ++ "Rollout 4527/9766, Reward: 277.792±18.756, Episode_length: 170.100±12.542\n", ++ "Rollout 4528/9766, Reward: 279.510±37.473, Episode_length: 257.500±248.184\n", ++ "Rollout 4529/9766, Reward: 273.533±37.551, Episode_length: 259.300±247.636\n", ++ "Rollout 4530/9766, Reward: 287.652±20.031, Episode_length: 182.200±19.984\n", ++ "Rollout 4531/9766, Reward: 262.571±40.629, Episode_length: 329.800±335.824\n", ++ "Rollout 4532/9766, Reward: 281.094±18.574, Episode_length: 171.400±15.995\n", ++ "Rollout 4533/9766, Reward: 292.585±14.688, Episode_length: 175.600±22.615\n", ++ "Rollout 4534/9766, Reward: 287.409±15.335, Episode_length: 173.500±23.040\n", ++ "Rollout 4535/9766, Reward: 281.500±17.397, Episode_length: 169.400±14.827\n", ++ "Rollout 4536/9766, Reward: 286.546±19.980, Episode_length: 184.000±26.751\n", ++ "Rollout 4537/9766, Reward: 275.511±15.862, Episode_length: 173.900±21.140\n", ++ "Rollout 4538/9766, Reward: 287.829±12.243, Episode_length: 183.600±11.164\n", ++ "Rollout 4539/9766, Reward: 281.792±15.101, Episode_length: 181.700±20.625\n", ++ "Rollout 4540/9766, Reward: 290.663±20.347, Episode_length: 184.300±25.656\n", ++ "Rollout 4541/9766, Reward: 291.937±14.603, Episode_length: 188.200±26.735\n", ++ "Rollout 4542/9766, Reward: 286.990±20.301, Episode_length: 182.900±28.052\n", ++ "Rollout 4543/9766, Reward: 265.642±41.034, Episode_length: 256.100±248.449\n", ++ "Rollout 4544/9766, Reward: 277.046±9.928, Episode_length: 171.400±19.438\n", ++ "Rollout 4545/9766, Reward: 289.404±14.035, Episode_length: 221.300±114.604\n", ++ "Rollout 4546/9766, Reward: 287.456±13.108, Episode_length: 176.500±17.310\n", ++ "Rollout 4547/9766, Reward: 284.879±18.230, Episode_length: 165.600±21.602\n", ++ "Rollout 4548/9766, Reward: 273.985±23.156, Episode_length: 195.200±63.617\n", ++ "Rollout 4549/9766, Reward: 292.557±10.947, Episode_length: 179.600±13.944\n", ++ "Rollout 4550/9766, Reward: 281.767±21.929, Episode_length: 265.400±210.743\n", ++ "Rollout 4551/9766, Reward: 275.601±15.941, Episode_length: 180.700±21.863\n", ++ "Rollout 4552/9766, Reward: 295.133±17.243, Episode_length: 191.500±21.942\n", ++ "Rollout 4553/9766, Reward: 284.348±18.841, Episode_length: 183.300±33.476\n", ++ "Rollout 4554/9766, Reward: 288.842±18.844, Episode_length: 187.100±33.934\n", ++ "Rollout 4555/9766, Reward: 288.175±17.865, Episode_length: 184.600±18.805\n", ++ "Rollout 4556/9766, Reward: 246.211±133.384, Episode_length: 169.400±30.260\n", ++ "Rollout 4557/9766, Reward: 297.040±13.699, Episode_length: 187.400±16.415\n", ++ "Rollout 4558/9766, Reward: 285.173±19.260, Episode_length: 185.100±21.938\n", ++ "Rollout 4559/9766, Reward: 280.767±25.423, Episode_length: 184.800±14.013\n", ++ "Rollout 4560/9766, Reward: 286.475±18.383, Episode_length: 182.400±20.766\n", ++ "Rollout 4561/9766, Reward: 291.073±13.318, Episode_length: 185.000±21.033\n", ++ "Rollout 4562/9766, Reward: 279.042±18.452, Episode_length: 174.500±18.156\n", ++ "Rollout 4563/9766, Reward: 284.633±18.820, Episode_length: 186.800±23.798\n", ++ "Rollout 4564/9766, Reward: 289.361±17.679, Episode_length: 176.700±23.694\n", ++ "Rollout 4565/9766, Reward: 284.842±18.801, Episode_length: 178.500±23.449\n", ++ "Rollout 4566/9766, Reward: 283.020±22.530, Episode_length: 183.300±21.698\n", ++ "Rollout 4567/9766, Reward: 290.004±17.159, Episode_length: 184.400±20.728\n", ++ "Rollout 4568/9766, Reward: 283.804±15.287, Episode_length: 182.500±16.776\n", ++ "Rollout 4569/9766, Reward: 276.097±13.105, Episode_length: 166.900±13.382\n", ++ "Rollout 4570/9766, Reward: 283.400±16.056, Episode_length: 178.300±26.582\n", ++ "Rollout 4571/9766, Reward: 288.359±16.333, Episode_length: 195.400±22.526\n", ++ "Rollout 4572/9766, Reward: 295.929±17.828, Episode_length: 188.400±16.402\n", ++ "Rollout 4573/9766, Reward: 289.591±19.572, Episode_length: 191.100±34.573\n", ++ "Rollout 4574/9766, Reward: 286.303±17.817, Episode_length: 191.400±29.384\n", ++ "Rollout 4575/9766, Reward: 286.383±20.435, Episode_length: 183.200±26.149\n", ++ "Rollout 4576/9766, Reward: 279.192±9.709, Episode_length: 173.400±17.934\n", ++ "Rollout 4577/9766, Reward: 289.354±16.083, Episode_length: 176.200±22.454\n", ++ "Rollout 4578/9766, Reward: 287.555±23.358, Episode_length: 179.400±21.374\n", ++ "Rollout 4579/9766, Reward: 247.020±122.641, Episode_length: 164.800±31.448\n", ++ "Rollout 4580/9766, Reward: 291.663±13.134, Episode_length: 187.100±21.059\n", ++ "Rollout 4581/9766, Reward: 258.610±74.568, Episode_length: 170.900±30.553\n", ++ "Rollout 4582/9766, Reward: 294.268±18.761, Episode_length: 188.500±18.189\n", ++ "Rollout 4583/9766, Reward: 263.669±74.940, Episode_length: 166.200±27.477\n", ++ "Rollout 4584/9766, Reward: 290.979±11.316, Episode_length: 177.500±25.272\n", ++ "Rollout 4585/9766, Reward: 267.294±79.919, Episode_length: 174.100±34.559\n", ++ "Rollout 4586/9766, Reward: 279.770±15.691, Episode_length: 179.900±18.163\n", ++ "Rollout 4587/9766, Reward: 283.399±15.628, Episode_length: 174.500±19.891\n", ++ "Rollout 4588/9766, Reward: 274.063±13.982, Episode_length: 245.700±206.145\n", ++ "Rollout 4589/9766, Reward: 284.223±13.548, Episode_length: 191.500±17.060\n", ++ "Rollout 4590/9766, Reward: 286.995±13.067, Episode_length: 181.400±23.787\n", ++ "Rollout 4591/9766, Reward: 296.251±21.520, Episode_length: 190.000±27.641\n", ++ "Rollout 4592/9766, Reward: 287.138±20.958, Episode_length: 174.500±21.708\n", ++ "Rollout 4593/9766, Reward: 283.084±22.113, Episode_length: 215.300±72.778\n", ++ "Rollout 4594/9766, Reward: 278.796±16.553, Episode_length: 178.400±25.370\n", ++ "Rollout 4595/9766, Reward: 283.681±15.428, Episode_length: 176.400±23.720\n", ++ "Rollout 4596/9766, Reward: 268.525±10.562, Episode_length: 241.000±194.820\n", ++ "Rollout 4597/9766, Reward: 283.045±21.863, Episode_length: 184.600±29.275\n", ++ "Rollout 4598/9766, Reward: 273.171±12.107, Episode_length: 165.000±15.369\n", ++ "Rollout 4599/9766, Reward: 287.810±20.290, Episode_length: 185.500±27.064\n", ++ "Rollout 4600/9766, Reward: 282.843±24.407, Episode_length: 257.800±204.250\n", ++ "Rollout 4601/9766, Reward: 279.419±13.644, Episode_length: 171.900±21.501\n", ++ "Rollout 4602/9766, Reward: 271.268±27.612, Episode_length: 245.600±222.321\n", ++ "Rollout 4603/9766, Reward: 275.147±16.573, Episode_length: 188.500±34.754\n", ++ "Rollout 4604/9766, Reward: 283.682±20.970, Episode_length: 179.600±17.054\n", ++ "Rollout 4605/9766, Reward: 282.787±16.916, Episode_length: 179.500±15.654\n", ++ "Rollout 4606/9766, Reward: 279.440±16.925, Episode_length: 178.500±22.940\n", ++ "Rollout 4607/9766, Reward: 283.061±12.251, Episode_length: 183.400±25.097\n", ++ "Rollout 4608/9766, Reward: 265.640±36.584, Episode_length: 249.500±111.088\n", ++ "Rollout 4609/9766, Reward: 272.666±8.771, Episode_length: 188.800±20.198\n", ++ "Rollout 4610/9766, Reward: 275.800±11.896, Episode_length: 176.900±31.750\n", ++ "Rollout 4611/9766, Reward: 283.381±21.049, Episode_length: 190.900±22.559\n", ++ "Rollout 4612/9766, Reward: 279.711±20.973, Episode_length: 192.600±22.642\n", ++ "Rollout 4613/9766, Reward: 283.486±25.085, Episode_length: 195.300±28.443\n", ++ "Rollout 4614/9766, Reward: 251.123±88.101, Episode_length: 268.500±245.376\n", ++ "Rollout 4615/9766, Reward: 287.809±26.177, Episode_length: 215.200±69.150\n", ++ "Rollout 4616/9766, Reward: 279.846±14.528, Episode_length: 180.300±19.184\n", ++ "Rollout 4617/9766, Reward: 283.909±24.582, Episode_length: 190.300±29.097\n", ++ "Rollout 4618/9766, Reward: 273.693±22.083, Episode_length: 231.700±112.205\n", ++ "Rollout 4619/9766, Reward: 280.892±13.234, Episode_length: 209.600±50.369\n", ++ "Rollout 4620/9766, Reward: 271.791±13.290, Episode_length: 180.900±19.670\n", ++ "Rollout 4621/9766, Reward: 287.097±13.527, Episode_length: 193.900±30.856\n", ++ "Rollout 4622/9766, Reward: 275.836±30.781, Episode_length: 226.300±70.994\n", ++ "Rollout 4623/9766, Reward: 280.691±20.048, Episode_length: 200.900±34.379\n", ++ "Rollout 4624/9766, Reward: 276.420±6.641, Episode_length: 187.600±34.188\n", ++ "Rollout 4625/9766, Reward: 272.934±22.342, Episode_length: 214.700±75.750\n", ++ "Rollout 4626/9766, Reward: 266.677±23.030, Episode_length: 232.700±117.150\n", ++ "Rollout 4627/9766, Reward: 282.918±14.883, Episode_length: 186.500±34.436\n", ++ "Rollout 4628/9766, Reward: 263.186±93.424, Episode_length: 278.800±242.316\n", ++ "Rollout 4629/9766, Reward: 268.835±26.380, Episode_length: 216.200±59.935\n", ++ "Rollout 4630/9766, Reward: 276.041±22.271, Episode_length: 173.600±19.628\n", ++ "Rollout 4631/9766, Reward: 275.758±15.236, Episode_length: 193.600±36.527\n", ++ "Rollout 4632/9766, Reward: 279.974±11.568, Episode_length: 197.300±35.404\n", ++ "Rollout 4633/9766, Reward: 262.821±26.700, Episode_length: 207.400±53.438\n", ++ "Rollout 4634/9766, Reward: 268.263±25.694, Episode_length: 278.200±166.897\n", ++ "Rollout 4635/9766, Reward: 261.436±40.699, Episode_length: 221.800±59.356\n", ++ "Rollout 4636/9766, Reward: 258.907±32.716, Episode_length: 334.900±184.943\n", ++ "Rollout 4637/9766, Reward: 230.623±58.573, Episode_length: 374.400±317.939\n", ++ "Rollout 4638/9766, Reward: 256.942±25.700, Episode_length: 342.800±179.653\n", ++ "Rollout 4639/9766, Reward: 17.300±419.007, Episode_length: 563.800±297.263\n", ++ "Rollout 4640/9766, Reward: 199.197±79.608, Episode_length: 555.600±292.183\n", ++ "Rollout 4641/9766, Reward: 229.577±71.451, Episode_length: 411.200±271.397\n", ++ "Rollout 4642/9766, Reward: 231.854±26.557, Episode_length: 506.700±246.863\n", ++ "Rollout 4643/9766, Reward: 212.881±45.857, Episode_length: 568.100±295.350\n", ++ "Rollout 4644/9766, Reward: 229.851±49.555, Episode_length: 457.400±276.397\n", ++ "Rollout 4645/9766, Reward: 230.663±45.912, Episode_length: 397.100±315.531\n", ++ "Rollout 4646/9766, Reward: 231.886±40.064, Episode_length: 395.200±246.522\n", ++ "Rollout 4647/9766, Reward: 250.628±42.879, Episode_length: 254.400±86.058\n", ++ "Rollout 4648/9766, Reward: 239.228±53.653, Episode_length: 496.500±254.606\n", ++ "Rollout 4649/9766, Reward: 269.105±20.082, Episode_length: 299.100±178.361\n", ++ "Rollout 4650/9766, Reward: 241.546±57.305, Episode_length: 419.900±350.401\n", ++ "Rollout 4651/9766, Reward: 272.714±27.358, Episode_length: 270.800±214.644\n", ++ "Rollout 4652/9766, Reward: 277.804±16.677, Episode_length: 202.300±41.838\n", ++ "Rollout 4653/9766, Reward: 226.409±74.075, Episode_length: 446.300±364.430\n", ++ "Rollout 4654/9766, Reward: 270.204±21.134, Episode_length: 222.300±51.719\n", ++ "Rollout 4655/9766, Reward: 248.320±50.446, Episode_length: 363.400±319.525\n", ++ "Rollout 4656/9766, Reward: 273.593±18.182, Episode_length: 223.200±102.988\n", ++ "Rollout 4657/9766, Reward: 268.526±25.763, Episode_length: 244.500±129.347\n", ++ "Rollout 4658/9766, Reward: 263.924±40.151, Episode_length: 285.600±241.118\n", ++ "Rollout 4659/9766, Reward: 182.106±49.934, Episode_length: 623.600±381.676\n", ++ "Rollout 4660/9766, Reward: 233.571±62.824, Episode_length: 454.200±358.833\n", ++ "Rollout 4661/9766, Reward: 238.114±40.398, Episode_length: 369.300±316.794\n", ++ "Rollout 4662/9766, Reward: 213.894±51.933, Episode_length: 579.500±351.619\n", ++ "Rollout 4663/9766, Reward: 256.030±13.144, Episode_length: 201.600±28.535\n", ++ "Rollout 4664/9766, Reward: 238.253±56.998, Episode_length: 351.300±325.742\n", ++ "Rollout 4665/9766, Reward: 220.213±53.311, Episode_length: 391.200±307.774\n", ++ "Rollout 4666/9766, Reward: 221.887±47.411, Episode_length: 454.000±318.387\n", ++ "Rollout 4667/9766, Reward: 207.711±50.969, Episode_length: 578.800±391.008\n", ++ "Rollout 4668/9766, Reward: 204.117±68.446, Episode_length: 558.100±344.400\n", ++ "Rollout 4669/9766, Reward: 220.793±53.438, Episode_length: 434.000±302.644\n", ++ "Rollout 4670/9766, Reward: 219.558±55.453, Episode_length: 412.900±298.116\n", ++ "Rollout 4671/9766, Reward: 225.094±38.744, Episode_length: 422.900±259.945\n", ++ "Rollout 4672/9766, Reward: 217.490±48.483, Episode_length: 566.100±288.271\n", ++ "Rollout 4673/9766, Reward: 234.064±21.094, Episode_length: 283.700±80.298\n", ++ "Rollout 4674/9766, Reward: 190.859±67.221, Episode_length: 569.500±373.738\n", ++ "Rollout 4675/9766, Reward: 237.977±27.321, Episode_length: 285.100±128.305\n", ++ "Rollout 4676/9766, Reward: 226.051±19.136, Episode_length: 385.500±241.178\n", ++ "Rollout 4677/9766, Reward: 152.653±107.513, Episode_length: 553.900±372.058\n", ++ "Rollout 4678/9766, Reward: 182.693±105.296, Episode_length: 380.200±232.973\n", ++ "Rollout 4679/9766, Reward: 208.477±31.670, Episode_length: 336.400±224.108\n", ++ "Rollout 4680/9766, Reward: 210.265±35.317, Episode_length: 317.400±163.504\n", ++ "Rollout 4681/9766, Reward: 221.362±44.362, Episode_length: 343.200±250.607\n", ++ "Rollout 4682/9766, Reward: 133.102±162.665, Episode_length: 456.600±357.070\n", ++ "Rollout 4683/9766, Reward: 210.908±42.743, Episode_length: 325.000±231.752\n", ++ "Rollout 4684/9766, Reward: 70.914±340.719, Episode_length: 586.500±278.181\n", ++ "Rollout 4685/9766, Reward: 209.290±43.988, Episode_length: 376.900±222.744\n", ++ "Rollout 4686/9766, Reward: 203.390±101.399, Episode_length: 384.200±245.415\n", ++ "Rollout 4687/9766, Reward: 193.405±81.845, Episode_length: 434.800±290.378\n", ++ "Rollout 4688/9766, Reward: 203.078±45.804, Episode_length: 321.400±229.697\n", ++ "Rollout 4689/9766, Reward: 190.568±82.130, Episode_length: 344.300±242.031\n", ++ "Rollout 4690/9766, Reward: 219.140±47.710, Episode_length: 273.900±243.095\n", ++ "Rollout 4691/9766, Reward: 234.451±30.649, Episode_length: 328.400±229.696\n", ++ "Rollout 4692/9766, Reward: 226.475±37.946, Episode_length: 333.600±258.299\n", ++ "Rollout 4693/9766, Reward: 221.548±43.932, Episode_length: 308.300±237.569\n", ++ "Rollout 4694/9766, Reward: 176.192±99.615, Episode_length: 449.400±362.823\n", ++ "Rollout 4695/9766, Reward: 225.990±45.327, Episode_length: 373.400±240.186\n", ++ "Rollout 4696/9766, Reward: 201.794±50.851, Episode_length: 456.800±325.397\n", ++ "Rollout 4697/9766, Reward: 194.221±104.946, Episode_length: 298.600±238.477\n", ++ "Rollout 4698/9766, Reward: 232.374±55.517, Episode_length: 347.300±227.562\n", ++ "Rollout 4699/9766, Reward: 231.280±70.229, Episode_length: 368.600±316.497\n", ++ "Rollout 4700/9766, Reward: 230.692±57.290, Episode_length: 386.600±290.245\n", ++ "Rollout 4701/9766, Reward: 102.914±204.907, Episode_length: 585.500±343.766\n", ++ "Rollout 4702/9766, Reward: 245.149±23.867, Episode_length: 250.400±71.012\n", ++ "Rollout 4703/9766, Reward: 258.003±42.949, Episode_length: 370.600±257.919\n", ++ "Rollout 4704/9766, Reward: 221.746±80.467, Episode_length: 384.800±265.080\n", ++ "Rollout 4705/9766, Reward: 232.979±32.965, Episode_length: 284.100±132.362\n", ++ "Rollout 4706/9766, Reward: 238.046±20.177, Episode_length: 313.900±113.145\n", ++ "Rollout 4707/9766, Reward: 191.162±57.877, Episode_length: 621.300±381.465\n", ++ "Rollout 4708/9766, Reward: 263.894±18.528, Episode_length: 237.300±68.112\n", ++ "Rollout 4709/9766, Reward: 235.733±38.797, Episode_length: 313.600±251.991\n", ++ "Rollout 4710/9766, Reward: 268.855±27.023, Episode_length: 219.400±34.048\n", ++ "Rollout 4711/9766, Reward: 251.293±28.667, Episode_length: 448.700±309.812\n", ++ "Rollout 4712/9766, Reward: 256.173±20.651, Episode_length: 273.900±166.337\n", ++ "Rollout 4713/9766, Reward: 253.325±22.813, Episode_length: 286.100±203.286\n", ++ "Rollout 4714/9766, Reward: 232.466±60.862, Episode_length: 448.700±316.780\n", ++ "Rollout 4715/9766, Reward: 250.501±43.354, Episode_length: 292.000±213.496\n", ++ "Rollout 4716/9766, Reward: 269.055±23.723, Episode_length: 263.000±71.010\n", ++ "Rollout 4717/9766, Reward: 232.301±61.655, Episode_length: 403.700±269.064\n", ++ "Rollout 4718/9766, Reward: 248.931±56.032, Episode_length: 353.200±261.925\n", ++ "Rollout 4719/9766, Reward: 262.979±18.897, Episode_length: 201.600±31.740\n", ++ "Rollout 4720/9766, Reward: 250.192±36.225, Episode_length: 292.400±194.649\n", ++ "Rollout 4721/9766, Reward: 252.422±31.497, Episode_length: 380.500±161.793\n", ++ "Rollout 4722/9766, Reward: 251.427±28.276, Episode_length: 253.100±91.753\n", ++ "Rollout 4723/9766, Reward: 240.776±42.939, Episode_length: 531.000±273.865\n", ++ "Rollout 4724/9766, Reward: 260.108±25.694, Episode_length: 316.400±211.337\n", ++ "Rollout 4725/9766, Reward: 223.632±58.433, Episode_length: 550.000±318.431\n", ++ "Rollout 4726/9766, Reward: 228.503±62.341, Episode_length: 469.800±290.108\n", ++ "Rollout 4727/9766, Reward: 244.081±22.316, Episode_length: 445.700±146.160\n", ++ "Rollout 4728/9766, Reward: 257.654±19.024, Episode_length: 318.000±202.252\n", ++ "Rollout 4729/9766, Reward: 247.693±44.907, Episode_length: 348.100±229.017\n", ++ "Rollout 4730/9766, Reward: 238.610±50.150, Episode_length: 665.900±356.827\n", ++ "Rollout 4731/9766, Reward: 270.544±30.748, Episode_length: 267.700±225.040\n", ++ "Rollout 4732/9766, Reward: 272.046±19.323, Episode_length: 187.600±26.889\n", ++ "Rollout 4733/9766, Reward: 275.957±13.750, Episode_length: 190.400±30.660\n", ++ "Rollout 4734/9766, Reward: 259.910±26.583, Episode_length: 233.000±75.958\n", ++ "Rollout 4735/9766, Reward: 247.419±43.773, Episode_length: 296.800±252.941\n", ++ "Rollout 4736/9766, Reward: 281.130±12.327, Episode_length: 181.700±39.933\n", ++ "Rollout 4737/9766, Reward: 274.270±29.093, Episode_length: 210.700±89.542\n", ++ "Rollout 4738/9766, Reward: 285.678±13.202, Episode_length: 193.300±39.998\n", ++ "Rollout 4739/9766, Reward: 283.119±12.865, Episode_length: 173.600±20.548\n", ++ "Rollout 4740/9766, Reward: 287.959±14.378, Episode_length: 207.600±35.018\n", ++ "Rollout 4741/9766, Reward: 283.621±18.130, Episode_length: 202.600±28.573\n", ++ "Rollout 4742/9766, Reward: 260.065±20.137, Episode_length: 189.100±64.596\n", ++ "Rollout 4743/9766, Reward: 261.120±60.477, Episode_length: 356.500±321.994\n", ++ "Rollout 4744/9766, Reward: 274.690±22.498, Episode_length: 201.600±20.646\n", ++ "Rollout 4745/9766, Reward: 277.872±25.903, Episode_length: 220.800±79.807\n", ++ "Rollout 4746/9766, Reward: 271.829±45.891, Episode_length: 276.900±241.614\n", ++ "Rollout 4747/9766, Reward: 199.177±75.272, Episode_length: 640.100±366.574\n", ++ "Rollout 4748/9766, Reward: 78.789±384.653, Episode_length: 649.200±340.498\n", ++ "Rollout 4749/9766, Reward: 159.956±58.366, Episode_length: 852.800±294.417\n", ++ "Rollout 4750/9766, Reward: 177.314±51.330, Episode_length: 733.500±331.603\n", ++ "Rollout 4751/9766, Reward: 237.582±55.113, Episode_length: 504.900±330.878\n", ++ "Rollout 4752/9766, Reward: 269.354±22.396, Episode_length: 209.100±104.856\n", ++ "Rollout 4753/9766, Reward: 274.816±34.887, Episode_length: 258.500±247.415\n", ++ "Rollout 4754/9766, Reward: 233.976±71.334, Episode_length: 423.500±377.881\n", ++ "Rollout 4755/9766, Reward: 274.896±20.418, Episode_length: 272.400±189.212\n", ++ "Rollout 4756/9766, Reward: 279.462±22.050, Episode_length: 264.800±228.606\n", ++ "Rollout 4757/9766, Reward: 289.587±10.899, Episode_length: 185.200±17.921\n", ++ "Rollout 4758/9766, Reward: 229.951±59.333, Episode_length: 677.600±290.930\n", ++ "Rollout 4759/9766, Reward: 292.146±14.902, Episode_length: 227.400±118.615\n", ++ "Rollout 4760/9766, Reward: 264.207±54.162, Episode_length: 342.200±329.051\n", ++ "Rollout 4761/9766, Reward: 254.072±46.743, Episode_length: 364.200±323.658\n", ++ "Rollout 4762/9766, Reward: 245.384±58.442, Episode_length: 425.600±376.408\n", ++ "Rollout 4763/9766, Reward: 256.976±46.582, Episode_length: 337.100±331.787\n", ++ "Rollout 4764/9766, Reward: 253.349±54.037, Episode_length: 385.900±335.944\n", ++ "Rollout 4765/9766, Reward: 258.862±63.330, Episode_length: 369.700±326.868\n", ++ "Rollout 4766/9766, Reward: 265.437±40.589, Episode_length: 267.200±245.106\n", ++ "Rollout 4767/9766, Reward: 281.066±19.248, Episode_length: 208.100±35.722\n", ++ "Rollout 4768/9766, Reward: 265.053±36.360, Episode_length: 264.700±246.150\n", ++ "Rollout 4769/9766, Reward: 245.590±44.526, Episode_length: 262.000±248.012\n", ++ "Rollout 4770/9766, Reward: 261.140±36.170, Episode_length: 261.600±247.282\n", ++ "Rollout 4771/9766, Reward: 270.438±24.339, Episode_length: 205.600±36.648\n", ++ "Rollout 4772/9766, Reward: 269.660±40.446, Episode_length: 281.900±240.953\n", ++ "Rollout 4773/9766, Reward: 226.027±69.400, Episode_length: 444.200±364.436\n", ++ "Rollout 4774/9766, Reward: 222.765±68.366, Episode_length: 459.600±359.508\n", ++ "Rollout 4775/9766, Reward: 240.782±51.373, Episode_length: 368.700±312.988\n", ++ "Rollout 4776/9766, Reward: 254.356±32.472, Episode_length: 276.800±134.724\n", ++ "Rollout 4777/9766, Reward: 230.937±58.619, Episode_length: 377.700±314.510\n", ++ "Rollout 4778/9766, Reward: 234.597±40.782, Episode_length: 393.800±294.875\n", ++ "Rollout 4779/9766, Reward: 231.674±56.508, Episode_length: 388.500±309.870\n", ++ "Rollout 4780/9766, Reward: 269.270±8.748, Episode_length: 212.800±39.168\n", ++ "Rollout 4781/9766, Reward: 267.548±28.223, Episode_length: 256.000±93.911\n", ++ "Rollout 4782/9766, Reward: 227.935±39.443, Episode_length: 530.900±353.966\n", ++ "Rollout 4783/9766, Reward: 190.551±76.070, Episode_length: 555.800±371.137\n", ++ "Rollout 4784/9766, Reward: 261.657±24.953, Episode_length: 286.200±202.261\n", ++ "Rollout 4785/9766, Reward: 240.066±48.802, Episode_length: 292.100±242.489\n", ++ "Rollout 4786/9766, Reward: 204.622±64.605, Episode_length: 517.200±395.375\n", ++ "Rollout 4787/9766, Reward: 223.700±56.396, Episode_length: 456.700±316.875\n", ++ "Rollout 4788/9766, Reward: 175.987±57.489, Episode_length: 678.000±326.501\n", ++ "Rollout 4789/9766, Reward: 237.427±40.574, Episode_length: 415.600±241.722\n", ++ "Rollout 4790/9766, Reward: 251.032±50.543, Episode_length: 311.900±246.637\n", ++ "Rollout 4791/9766, Reward: 244.239±50.022, Episode_length: 354.300±234.851\n", ++ "Rollout 4792/9766, Reward: 217.605±66.125, Episode_length: 500.900±365.571\n", ++ "Rollout 4793/9766, Reward: 270.618±17.723, Episode_length: 215.800±64.575\n", ++ "Rollout 4794/9766, Reward: 235.806±76.571, Episode_length: 279.500±242.938\n", ++ "Rollout 4795/9766, Reward: 228.625±55.791, Episode_length: 571.400±360.279\n", ++ "Rollout 4796/9766, Reward: 263.663±17.699, Episode_length: 198.400±61.942\n", ++ "Rollout 4797/9766, Reward: 174.366±86.876, Episode_length: 601.700±376.997\n", ++ "Rollout 4798/9766, Reward: 222.763±63.880, Episode_length: 545.100±354.139\n", ++ "Rollout 4799/9766, Reward: 243.593±26.885, Episode_length: 315.400±265.877\n", ++ "Rollout 4800/9766, Reward: 217.887±63.840, Episode_length: 448.400±365.928\n", ++ "Rollout 4801/9766, Reward: 238.104±57.625, Episode_length: 343.000±329.239\n", ++ "Rollout 4802/9766, Reward: 258.114±19.006, Episode_length: 320.900±248.607\n", ++ "Rollout 4803/9766, Reward: 236.763±85.888, Episode_length: 275.400±245.284\n", ++ "Rollout 4804/9766, Reward: 250.050±61.185, Episode_length: 278.500±241.982\n", ++ "Rollout 4805/9766, Reward: 255.735±38.070, Episode_length: 330.700±268.041\n", ++ "Rollout 4806/9766, Reward: 267.181±34.764, Episode_length: 199.800±59.692\n", ++ "Rollout 4807/9766, Reward: 252.455±21.046, Episode_length: 207.100±26.965\n", ++ "Rollout 4808/9766, Reward: 252.123±48.408, Episode_length: 327.400±249.102\n", ++ "Rollout 4809/9766, Reward: 221.035±47.505, Episode_length: 471.400±320.504\n", ++ "Rollout 4810/9766, Reward: 226.443±75.943, Episode_length: 275.200±245.206\n", ++ "Rollout 4811/9766, Reward: 242.563±20.135, Episode_length: 209.300±48.668\n", ++ "Rollout 4812/9766, Reward: 216.248±67.988, Episode_length: 346.800±206.726\n", ++ "Rollout 4813/9766, Reward: 228.481±33.505, Episode_length: 327.400±98.094\n", ++ "Rollout 4814/9766, Reward: 225.057±98.039, Episode_length: 341.300±273.756\n", ++ "Rollout 4815/9766, Reward: 228.405±73.624, Episode_length: 371.400±315.474\n", ++ "Rollout 4816/9766, Reward: 164.447±239.329, Episode_length: 320.400±277.957\n", ++ "Rollout 4817/9766, Reward: 253.983±56.673, Episode_length: 284.200±241.098\n", ++ "Rollout 4818/9766, Reward: 247.073±49.373, Episode_length: 292.200±241.884\n", ++ "Rollout 4819/9766, Reward: 237.293±54.457, Episode_length: 347.300±326.994\n", ++ "Rollout 4820/9766, Reward: 104.325±435.858, Episode_length: 291.200±244.204\n", ++ "Rollout 4821/9766, Reward: 281.887±23.130, Episode_length: 188.800±23.284\n", ++ "Rollout 4822/9766, Reward: 237.247±67.781, Episode_length: 361.600±320.349\n", ++ "Rollout 4823/9766, Reward: 263.113±19.973, Episode_length: 225.300±92.927\n", ++ "Rollout 4824/9766, Reward: 268.571±30.587, Episode_length: 268.900±126.075\n", ++ "Rollout 4825/9766, Reward: 258.271±30.114, Episode_length: 258.000±100.727\n", ++ "Rollout 4826/9766, Reward: 258.041±32.622, Episode_length: 377.100±297.221\n", ++ "Rollout 4827/9766, Reward: 247.634±78.615, Episode_length: 229.000±133.246\n", ++ "Rollout 4828/9766, Reward: 239.771±68.745, Episode_length: 211.600±43.699\n", ++ "Rollout 4829/9766, Reward: 265.431±37.076, Episode_length: 247.500±107.760\n", ++ "Rollout 4830/9766, Reward: 219.583±80.905, Episode_length: 384.000±329.506\n", ++ "Rollout 4831/9766, Reward: 238.276±62.580, Episode_length: 339.800±230.409\n", ++ "Rollout 4832/9766, Reward: 268.030±29.404, Episode_length: 245.400±119.492\n", ++ "Rollout 4833/9766, Reward: 262.065±42.541, Episode_length: 286.600±238.669\n", ++ "Rollout 4834/9766, Reward: 251.797±39.132, Episode_length: 296.500±219.557\n", ++ "Rollout 4835/9766, Reward: 238.993±59.784, Episode_length: 346.900±326.870\n", ++ "Rollout 4836/9766, Reward: 228.511±66.584, Episode_length: 432.300±371.878\n", ++ "Rollout 4837/9766, Reward: 247.934±43.718, Episode_length: 402.000±329.620\n", ++ "Rollout 4838/9766, Reward: 261.730±47.364, Episode_length: 267.100±244.941\n", ++ "Rollout 4839/9766, Reward: 257.524±44.445, Episode_length: 285.600±238.975\n", ++ "Rollout 4840/9766, Reward: 254.713±40.454, Episode_length: 285.000±241.222\n", ++ "Rollout 4841/9766, Reward: 237.043±67.724, Episode_length: 440.100±367.740\n", ++ "Rollout 4842/9766, Reward: 258.775±29.521, Episode_length: 273.300±125.371\n", ++ "Rollout 4843/9766, Reward: 267.763±25.368, Episode_length: 218.300±85.129\n", ++ "Rollout 4844/9766, Reward: 248.993±52.206, Episode_length: 270.200±244.111\n", ++ "Rollout 4845/9766, Reward: 277.909±16.212, Episode_length: 208.300±40.988\n", ++ "Rollout 4846/9766, Reward: 238.957±44.789, Episode_length: 386.300±310.233\n", ++ "Rollout 4847/9766, Reward: 271.684±30.201, Episode_length: 234.900±69.053\n", ++ "Rollout 4848/9766, Reward: 250.587±38.191, Episode_length: 312.400±241.234\n", ++ "Rollout 4849/9766, Reward: 247.418±52.626, Episode_length: 288.100±240.372\n", ++ "Rollout 4850/9766, Reward: 230.107±54.832, Episode_length: 439.600±345.444\n", ++ "Rollout 4851/9766, Reward: 228.434±48.059, Episode_length: 339.300±158.061\n", ++ "Rollout 4852/9766, Reward: 269.607±33.737, Episode_length: 237.900±62.591\n", ++ "Rollout 4853/9766, Reward: 255.278±45.588, Episode_length: 305.300±235.884\n", ++ "Rollout 4854/9766, Reward: 238.504±44.781, Episode_length: 256.000±89.433\n", ++ "Rollout 4855/9766, Reward: 265.666±18.789, Episode_length: 214.500±50.802\n", ++ "Rollout 4856/9766, Reward: 273.878±29.707, Episode_length: 229.800±55.683\n", ++ "Rollout 4857/9766, Reward: 252.831±33.856, Episode_length: 258.500±177.198\n", ++ "Rollout 4858/9766, Reward: 265.407±22.891, Episode_length: 220.700±67.763\n", ++ "Rollout 4859/9766, Reward: 234.514±29.267, Episode_length: 266.300±114.403\n", ++ "Rollout 4860/9766, Reward: 234.752±43.374, Episode_length: 529.600±288.564\n", ++ "Rollout 4861/9766, Reward: 226.787±36.507, Episode_length: 540.800±244.950\n", ++ "Rollout 4862/9766, Reward: 248.170±47.973, Episode_length: 381.900±247.519\n", ++ "Rollout 4863/9766, Reward: 242.277±40.962, Episode_length: 379.400±153.095\n", ++ "Rollout 4864/9766, Reward: 231.437±38.801, Episode_length: 542.600±256.217\n", ++ "Rollout 4865/9766, Reward: 242.672±41.824, Episode_length: 395.200±259.255\n", ++ "Rollout 4866/9766, Reward: 221.089±52.213, Episode_length: 519.100±327.918\n", ++ "Rollout 4867/9766, Reward: 209.610±115.144, Episode_length: 302.300±132.959\n", ++ "Rollout 4868/9766, Reward: 186.957±73.494, Episode_length: 580.700±356.585\n", ++ "Rollout 4869/9766, Reward: 229.387±54.116, Episode_length: 421.800±333.643\n", ++ "Rollout 4870/9766, Reward: 234.894±16.492, Episode_length: 486.200±269.862\n", ++ "Rollout 4871/9766, Reward: 210.081±88.563, Episode_length: 416.400±307.334\n", ++ "Rollout 4872/9766, Reward: 227.873±43.697, Episode_length: 532.900±253.541\n", ++ "Rollout 4873/9766, Reward: 215.619±37.929, Episode_length: 403.900±253.158\n", ++ "Rollout 4874/9766, Reward: 233.532±41.854, Episode_length: 400.000±249.171\n", ++ "Rollout 4875/9766, Reward: 212.181±78.973, Episode_length: 563.000±346.602\n", ++ "Rollout 4876/9766, Reward: 219.891±47.336, Episode_length: 466.600±272.565\n", ++ "Rollout 4877/9766, Reward: 234.902±27.671, Episode_length: 335.300±143.590\n", ++ "Rollout 4878/9766, Reward: 233.079±66.812, Episode_length: 256.700±130.504\n", ++ "Rollout 4879/9766, Reward: 253.251±40.387, Episode_length: 270.200±99.877\n", ++ "Rollout 4880/9766, Reward: 229.048±102.157, Episode_length: 301.100±250.123\n", ++ "Rollout 4881/9766, Reward: 262.598±18.819, Episode_length: 217.600±66.569\n", ++ "Rollout 4882/9766, Reward: 248.663±24.905, Episode_length: 383.700±209.983\n", ++ "Rollout 4883/9766, Reward: 207.796±66.196, Episode_length: 546.400±396.000\n", ++ "Rollout 4884/9766, Reward: 248.858±33.315, Episode_length: 398.800±322.323\n", ++ "Rollout 4885/9766, Reward: 224.090±47.516, Episode_length: 503.600±405.459\n", ++ "Rollout 4886/9766, Reward: 238.123±38.833, Episode_length: 404.700±316.347\n", ++ "Rollout 4887/9766, Reward: 257.776±37.587, Episode_length: 284.500±246.256\n", ++ "Rollout 4888/9766, Reward: 229.999±68.225, Episode_length: 357.500±322.108\n", ++ "Rollout 4889/9766, Reward: 258.741±45.861, Episode_length: 279.800±245.838\n", ++ "Rollout 4890/9766, Reward: 258.270±18.856, Episode_length: 210.400±44.016\n", ++ "Rollout 4891/9766, Reward: 219.368±100.138, Episode_length: 356.500±273.176\n", ++ "Rollout 4892/9766, Reward: 213.472±52.813, Episode_length: 510.000±374.577\n", ++ "Rollout 4893/9766, Reward: 249.086±45.139, Episode_length: 261.700±247.360\n", ++ "Rollout 4894/9766, Reward: 180.434±69.046, Episode_length: 713.200±351.598\n", ++ "Rollout 4895/9766, Reward: 201.434±81.279, Episode_length: 494.500±363.083\n", ++ "Rollout 4896/9766, Reward: 247.685±40.223, Episode_length: 378.400±273.973\n", ++ "Rollout 4897/9766, Reward: 177.495±76.956, Episode_length: 652.800±361.752\n", ++ "Rollout 4898/9766, Reward: 242.391±46.977, Episode_length: 357.400±317.083\n", ++ "Rollout 4899/9766, Reward: 245.539±49.878, Episode_length: 326.600±244.074\n", ++ "Rollout 4900/9766, Reward: 216.337±56.167, Episode_length: 595.400±355.373\n", ++ "Rollout 4901/9766, Reward: 208.951±52.522, Episode_length: 676.300±373.740\n", ++ "Rollout 4902/9766, Reward: 234.794±53.417, Episode_length: 433.600±319.553\n", ++ "Rollout 4903/9766, Reward: 234.367±44.876, Episode_length: 466.100±343.500\n", ++ "Rollout 4904/9766, Reward: 194.875±58.829, Episode_length: 620.800±393.663\n", ++ "Rollout 4905/9766, Reward: 217.437±63.984, Episode_length: 446.600±366.115\n", ++ "Rollout 4906/9766, Reward: 200.275±74.467, Episode_length: 524.500±388.906\n", ++ "Rollout 4907/9766, Reward: 247.748±39.220, Episode_length: 300.900±236.259\n", ++ "Rollout 4908/9766, Reward: 182.163±55.098, Episode_length: 624.700±366.561\n", ++ "Rollout 4909/9766, Reward: 213.944±55.991, Episode_length: 525.300±378.993\n", ++ "Rollout 4910/9766, Reward: 259.512±29.796, Episode_length: 198.500±23.504\n", ++ "Rollout 4911/9766, Reward: 246.510±45.391, Episode_length: 444.200±325.870\n", ++ "Rollout 4912/9766, Reward: 215.331±58.381, Episode_length: 517.900±341.695\n", ++ "Rollout 4913/9766, Reward: 184.978±66.377, Episode_length: 702.600±369.909\n", ++ "Rollout 4914/9766, Reward: 164.392±82.347, Episode_length: 634.100±374.688\n", ++ "Rollout 4915/9766, Reward: 234.312±52.159, Episode_length: 375.300±315.533\n", ++ "Rollout 4916/9766, Reward: 222.005±49.571, Episode_length: 295.600±238.996\n", ++ "Rollout 4917/9766, Reward: 261.400±22.211, Episode_length: 221.700±64.945\n", ++ "Rollout 4918/9766, Reward: 239.312±46.784, Episode_length: 273.900±243.855\n", ++ "Rollout 4919/9766, Reward: 243.588±61.287, Episode_length: 353.300±324.872\n", ++ "Rollout 4920/9766, Reward: 236.504±37.551, Episode_length: 364.600±319.468\n", ++ "Rollout 4921/9766, Reward: 241.201±51.431, Episode_length: 318.000±273.613\n", ++ "Rollout 4922/9766, Reward: 219.784±49.830, Episode_length: 432.900±296.664\n", ++ "Rollout 4923/9766, Reward: 214.736±120.805, Episode_length: 296.400±249.886\n", ++ "Rollout 4924/9766, Reward: 209.905±95.128, Episode_length: 411.900±300.758\n", ++ "Rollout 4925/9766, Reward: 162.657±146.234, Episode_length: 512.900±332.336\n", ++ "Rollout 4926/9766, Reward: 258.700±20.252, Episode_length: 251.300±134.856\n", ++ "Rollout 4927/9766, Reward: 235.312±70.545, Episode_length: 227.900±93.967\n", ++ "Rollout 4928/9766, Reward: 220.856±60.794, Episode_length: 405.900±305.629\n", ++ "Rollout 4929/9766, Reward: 253.399±26.674, Episode_length: 223.400±48.494\n", ++ "Rollout 4930/9766, Reward: 260.896±28.441, Episode_length: 200.300±34.537\n", ++ "Rollout 4931/9766, Reward: 263.521±28.145, Episode_length: 196.200±57.320\n", ++ "Rollout 4932/9766, Reward: 258.853±31.380, Episode_length: 217.900±82.037\n", ++ "Rollout 4933/9766, Reward: 209.418±127.918, Episode_length: 229.600±80.305\n", ++ "Rollout 4934/9766, Reward: 250.567±28.470, Episode_length: 242.300±103.290\n", ++ "Rollout 4935/9766, Reward: 278.833±11.322, Episode_length: 195.500±25.441\n", ++ "Rollout 4936/9766, Reward: 265.126±38.418, Episode_length: 207.700±54.032\n", ++ "Rollout 4937/9766, Reward: 253.451±33.418, Episode_length: 254.900±155.015\n", ++ "Rollout 4938/9766, Reward: 260.039±26.620, Episode_length: 187.800±31.422\n", ++ "Rollout 4939/9766, Reward: 260.654±17.855, Episode_length: 212.500±46.751\n", ++ "Rollout 4940/9766, Reward: 253.298±46.572, Episode_length: 291.200±245.602\n", ++ "Rollout 4941/9766, Reward: 264.533±25.296, Episode_length: 205.200±53.349\n", ++ "Rollout 4942/9766, Reward: 264.254±18.001, Episode_length: 174.200±28.583\n", ++ "Rollout 4943/9766, Reward: 262.357±30.431, Episode_length: 252.900±229.646\n", ++ "Rollout 4944/9766, Reward: 264.908±20.767, Episode_length: 208.200±39.387\n", ++ "Rollout 4945/9766, Reward: 264.448±24.718, Episode_length: 200.200±75.681\n", ++ "Rollout 4946/9766, Reward: 251.171±37.895, Episode_length: 297.500±176.305\n", ++ "Rollout 4947/9766, Reward: 242.561±94.789, Episode_length: 266.600±247.534\n", ++ "Rollout 4948/9766, Reward: 272.910±24.731, Episode_length: 188.700±18.942\n", ++ "Rollout 4949/9766, Reward: 249.890±79.087, Episode_length: 188.800±47.753\n", ++ "Rollout 4950/9766, Reward: 231.116±56.652, Episode_length: 427.100±375.614\n", ++ "Rollout 4951/9766, Reward: 270.358±23.441, Episode_length: 201.700±53.766\n", ++ "Rollout 4952/9766, Reward: 286.322±22.980, Episode_length: 205.800±29.983\n", ++ "Rollout 4953/9766, Reward: 280.302±19.268, Episode_length: 180.700±28.320\n", ++ "Rollout 4954/9766, Reward: 264.608±58.041, Episode_length: 280.700±240.765\n", ++ "Rollout 4955/9766, Reward: 272.837±23.838, Episode_length: 255.400±125.131\n", ++ "Rollout 4956/9766, Reward: 231.842±87.970, Episode_length: 252.400±251.669\n", ++ "Rollout 4957/9766, Reward: 266.589±21.767, Episode_length: 186.700±30.509\n", ++ "Rollout 4958/9766, Reward: 267.345±20.881, Episode_length: 244.300±142.609\n", ++ "Rollout 4959/9766, Reward: 269.838±19.583, Episode_length: 169.900±21.286\n", ++ "Rollout 4960/9766, Reward: 272.119±14.656, Episode_length: 172.700±19.360\n", ++ "Rollout 4961/9766, Reward: 272.952±41.567, Episode_length: 265.000±245.646\n", ++ "Rollout 4962/9766, Reward: 241.784±81.692, Episode_length: 259.000±250.632\n", ++ "Rollout 4963/9766, Reward: 250.478±86.171, Episode_length: 168.900±45.198\n", ++ "Rollout 4964/9766, Reward: 247.675±64.389, Episode_length: 352.700±324.650\n", ++ "Rollout 4965/9766, Reward: 267.043±58.469, Episode_length: 267.800±246.210\n", ++ "Rollout 4966/9766, Reward: 264.563±45.550, Episode_length: 261.200±246.735\n", ++ "Rollout 4967/9766, Reward: 278.771±12.909, Episode_length: 181.700±30.213\n", ++ "Rollout 4968/9766, Reward: 284.127±10.435, Episode_length: 185.700±20.766\n", ++ "Rollout 4969/9766, Reward: 251.495±65.149, Episode_length: 162.000±15.153\n", ++ "Rollout 4970/9766, Reward: 287.616±15.269, Episode_length: 191.700±38.236\n", ++ "Rollout 4971/9766, Reward: 263.852±34.934, Episode_length: 227.000±143.071\n", ++ "Rollout 4972/9766, Reward: 271.621±22.836, Episode_length: 187.800±46.840\n", ++ "Rollout 4973/9766, Reward: 277.004±14.458, Episode_length: 213.000±58.634\n", ++ "Rollout 4974/9766, Reward: 275.825±40.822, Episode_length: 291.300±145.577\n", ++ "Rollout 4975/9766, Reward: 281.121±17.857, Episode_length: 212.300±83.352\n", ++ "Rollout 4976/9766, Reward: 279.252±13.544, Episode_length: 177.300±18.006\n", ++ "Rollout 4977/9766, Reward: 266.971±24.616, Episode_length: 224.200±141.704\n", ++ "Rollout 4978/9766, Reward: 277.125±36.613, Episode_length: 259.300±235.612\n", ++ "Rollout 4979/9766, Reward: 284.607±22.200, Episode_length: 189.300±20.445\n", ++ "Rollout 4980/9766, Reward: 263.168±54.560, Episode_length: 253.800±249.125\n", ++ "Rollout 4981/9766, Reward: 273.395±14.679, Episode_length: 173.800±23.025\n", ++ "Rollout 4982/9766, Reward: 255.883±38.001, Episode_length: 248.700±250.898\n", ++ "Rollout 4983/9766, Reward: 276.464±12.715, Episode_length: 167.900±18.025\n", ++ "Rollout 4984/9766, Reward: 279.428±17.963, Episode_length: 165.700±26.042\n", ++ "Rollout 4985/9766, Reward: 289.338±11.632, Episode_length: 264.200±211.092\n", ++ "Rollout 4986/9766, Reward: 231.080±104.251, Episode_length: 256.800±250.325\n", ++ "Rollout 4987/9766, Reward: 258.903±77.238, Episode_length: 228.800±92.587\n", ++ "Rollout 4988/9766, Reward: 251.802±49.423, Episode_length: 457.000±338.453\n", ++ "Rollout 4989/9766, Reward: 256.981±29.826, Episode_length: 320.600±277.837\n", ++ "Rollout 4990/9766, Reward: 268.192±39.226, Episode_length: 260.800±247.387\n", ++ "Rollout 4991/9766, Reward: 222.581±91.570, Episode_length: 399.100±246.241\n", ++ "Rollout 4992/9766, Reward: 265.815±18.375, Episode_length: 273.500±137.745\n", ++ "Rollout 4993/9766, Reward: 247.496±44.488, Episode_length: 466.600±353.085\n", ++ "Rollout 4994/9766, Reward: 276.839±10.754, Episode_length: 441.200±251.244\n", ++ "Rollout 4995/9766, Reward: 276.414±16.941, Episode_length: 170.900±16.109\n", ++ "Rollout 4996/9766, Reward: 253.956±88.003, Episode_length: 178.000±39.623\n", ++ "Rollout 4997/9766, Reward: 272.223±28.270, Episode_length: 277.100±248.628\n", ++ "Rollout 4998/9766, Reward: 256.743±78.083, Episode_length: 152.200±27.400\n", ++ "Rollout 4999/9766, Reward: 284.081±16.130, Episode_length: 174.400±25.117\n", ++ "Rollout 5000/9766, Reward: 286.696±16.860, Episode_length: 178.800±22.391\n", ++ "Rollout 5001/9766, Reward: 275.944±43.617, Episode_length: 261.600±246.887\n", ++ "Rollout 5002/9766, Reward: 250.254±85.686, Episode_length: 156.800±25.258\n", ++ "Rollout 5003/9766, Reward: 232.498±75.799, Episode_length: 289.100±289.479\n", ++ "Rollout 5004/9766, Reward: 285.296±12.341, Episode_length: 182.500±20.011\n", ++ "Rollout 5005/9766, Reward: 14.322±411.261, Episode_length: 167.000±71.254\n", ++ "Rollout 5006/9766, Reward: 103.076±337.987, Episode_length: 157.800±40.516\n", ++ "Rollout 5007/9766, Reward: 288.814±18.378, Episode_length: 189.900±29.293\n", ++ "Rollout 5008/9766, Reward: 287.737±15.181, Episode_length: 203.500±36.642\n", ++ "Rollout 5009/9766, Reward: 275.549±23.111, Episode_length: 206.200±76.227\n", ++ "Rollout 5010/9766, Reward: 292.272±13.429, Episode_length: 177.300±23.186\n", ++ "Rollout 5011/9766, Reward: 281.040±27.518, Episode_length: 206.700±108.373\n", ++ "Rollout 5012/9766, Reward: 290.129±15.978, Episode_length: 187.300±13.513\n", ++ "Rollout 5013/9766, Reward: 274.919±28.367, Episode_length: 227.900±102.233\n", ++ "Rollout 5014/9766, Reward: 279.068±16.700, Episode_length: 184.000±18.847\n", ++ "Rollout 5015/9766, Reward: 279.384±16.925, Episode_length: 177.300±20.445\n", ++ "Rollout 5016/9766, Reward: 270.962±24.382, Episode_length: 190.800±28.826\n", ++ "Rollout 5017/9766, Reward: 280.206±16.177, Episode_length: 213.500±85.061\n", ++ "Rollout 5018/9766, Reward: 285.978±21.566, Episode_length: 249.400±177.009\n", ++ "Rollout 5019/9766, Reward: 276.309±15.976, Episode_length: 164.000±18.396\n", ++ "Rollout 5020/9766, Reward: 287.202±18.392, Episode_length: 183.100±18.902\n", ++ "Rollout 5021/9766, Reward: 276.835±14.243, Episode_length: 173.800±18.632\n", ++ "Rollout 5022/9766, Reward: 272.844±17.635, Episode_length: 179.200±28.467\n", ++ "Rollout 5023/9766, Reward: 281.805±15.760, Episode_length: 169.200±17.520\n", ++ "Rollout 5024/9766, Reward: 276.131±41.771, Episode_length: 264.800±245.612\n", ++ "Rollout 5025/9766, Reward: 284.131±16.413, Episode_length: 182.600±22.966\n", ++ "Rollout 5026/9766, Reward: 281.411±23.471, Episode_length: 181.300±17.065\n", ++ "Rollout 5027/9766, Reward: 252.323±49.886, Episode_length: 339.000±330.688\n", ++ "Rollout 5028/9766, Reward: 276.492±16.075, Episode_length: 168.200±8.471\n", ++ "Rollout 5029/9766, Reward: 287.064±19.367, Episode_length: 180.100±25.272\n", ++ "Rollout 5030/9766, Reward: 287.260±18.764, Episode_length: 167.700±23.622\n", ++ "Rollout 5031/9766, Reward: 297.922±13.602, Episode_length: 181.300±21.684\n", ++ "Rollout 5032/9766, Reward: 285.747±34.312, Episode_length: 354.300±299.591\n", ++ "Rollout 5033/9766, Reward: 276.865±11.897, Episode_length: 248.400±248.821\n", ++ "Rollout 5034/9766, Reward: 287.645±17.477, Episode_length: 181.200±21.061\n", ++ "Rollout 5035/9766, Reward: 266.234±78.661, Episode_length: 178.200±35.380\n", ++ "Rollout 5036/9766, Reward: 274.535±22.776, Episode_length: 193.300±55.832\n", ++ "Rollout 5037/9766, Reward: 272.605±33.248, Episode_length: 218.600±75.634\n", ++ "Rollout 5038/9766, Reward: 278.547±20.237, Episode_length: 172.300±25.823\n", ++ "Rollout 5039/9766, Reward: 284.625±13.383, Episode_length: 179.000±17.578\n", ++ "Rollout 5040/9766, Reward: 271.911±25.358, Episode_length: 205.500±78.314\n", ++ "Rollout 5041/9766, Reward: 267.470±25.029, Episode_length: 201.000±67.976\n", ++ "Rollout 5042/9766, Reward: 283.636±16.659, Episode_length: 178.200±14.777\n", ++ "Rollout 5043/9766, Reward: 281.126±14.455, Episode_length: 171.800±15.065\n", ++ "Rollout 5044/9766, Reward: 280.050±17.477, Episode_length: 171.100±20.437\n", ++ "Rollout 5045/9766, Reward: 288.417±16.274, Episode_length: 191.000±40.219\n", ++ "Rollout 5046/9766, Reward: 280.230±19.275, Episode_length: 170.300±18.569\n", ++ "Rollout 5047/9766, Reward: 289.724±17.887, Episode_length: 176.300±19.375\n", ++ "Rollout 5048/9766, Reward: 238.428±98.710, Episode_length: 251.800±252.239\n", ++ "Rollout 5049/9766, Reward: 278.467±22.533, Episode_length: 204.100±72.202\n", ++ "Rollout 5050/9766, Reward: 291.653±13.347, Episode_length: 176.700±21.670\n", ++ "Rollout 5051/9766, Reward: 291.041±11.570, Episode_length: 176.200±18.654\n", ++ "Rollout 5052/9766, Reward: 277.682±17.136, Episode_length: 173.400±16.925\n", ++ "Rollout 5053/9766, Reward: 290.377±15.250, Episode_length: 178.700±29.587\n", ++ "Rollout 5054/9766, Reward: 284.097±15.730, Episode_length: 176.200±22.234\n", ++ "Rollout 5055/9766, Reward: 271.809±51.183, Episode_length: 255.400±248.710\n", ++ "Rollout 5056/9766, Reward: 279.021±18.092, Episode_length: 174.400±21.336\n", ++ "Rollout 5057/9766, Reward: 278.958±15.725, Episode_length: 178.800±24.355\n", ++ "Rollout 5058/9766, Reward: 274.601±11.383, Episode_length: 163.800±21.794\n", ++ "Rollout 5059/9766, Reward: 270.607±23.986, Episode_length: 190.500±71.201\n", ++ "Rollout 5060/9766, Reward: 284.186±20.398, Episode_length: 172.600±27.489\n", ++ "Rollout 5061/9766, Reward: 280.443±22.339, Episode_length: 176.300±17.205\n", ++ "Rollout 5062/9766, Reward: 286.266±14.900, Episode_length: 170.900±18.593\n", ++ "Rollout 5063/9766, Reward: 288.894±21.059, Episode_length: 179.600±19.891\n", ++ "Rollout 5064/9766, Reward: 278.307±17.300, Episode_length: 175.600±20.733\n", ++ "Rollout 5065/9766, Reward: 254.822±76.317, Episode_length: 167.400±14.122\n", ++ "Rollout 5066/9766, Reward: 288.618±11.940, Episode_length: 178.600±19.815\n", ++ "Rollout 5067/9766, Reward: 285.756±20.663, Episode_length: 177.500±23.346\n", ++ "Rollout 5068/9766, Reward: 281.303±15.781, Episode_length: 181.000±27.662\n", ++ "Rollout 5069/9766, Reward: 288.545±13.001, Episode_length: 177.600±22.721\n", ++ "Rollout 5070/9766, Reward: 294.442±18.525, Episode_length: 178.900±24.607\n", ++ "Rollout 5071/9766, Reward: 287.588±15.334, Episode_length: 173.000±18.221\n", ++ "Rollout 5072/9766, Reward: 279.942±18.898, Episode_length: 176.000±25.286\n", ++ "Rollout 5073/9766, Reward: 287.447±13.853, Episode_length: 171.200±21.807\n", ++ "Rollout 5074/9766, Reward: 293.687±19.162, Episode_length: 171.000±24.356\n", ++ "Rollout 5075/9766, Reward: 276.557±23.733, Episode_length: 175.100±18.168\n", ++ "Rollout 5076/9766, Reward: 274.329±15.968, Episode_length: 164.400±15.147\n", ++ "Rollout 5077/9766, Reward: 282.799±18.959, Episode_length: 167.400±17.901\n", ++ "Rollout 5078/9766, Reward: 284.172±16.830, Episode_length: 179.800±17.943\n", ++ "Rollout 5079/9766, Reward: 293.837±12.216, Episode_length: 190.100±33.569\n", ++ "Rollout 5080/9766, Reward: 292.401±10.604, Episode_length: 179.200±26.630\n", ++ "Rollout 5081/9766, Reward: 271.436±35.390, Episode_length: 252.500±249.598\n", ++ "Rollout 5082/9766, Reward: 279.454±21.274, Episode_length: 172.100±24.407\n", ++ "Rollout 5083/9766, Reward: 280.273±16.401, Episode_length: 165.700±28.185\n", ++ "Rollout 5084/9766, Reward: 286.623±15.715, Episode_length: 185.800±26.457\n", ++ "Rollout 5085/9766, Reward: 290.960±17.903, Episode_length: 174.500±22.259\n", ++ "Rollout 5086/9766, Reward: 281.239±40.573, Episode_length: 252.000±249.806\n", ++ "Rollout 5087/9766, Reward: 281.060±24.400, Episode_length: 168.400±24.784\n", ++ "Rollout 5088/9766, Reward: 294.213±15.015, Episode_length: 172.400±13.410\n", ++ "Rollout 5089/9766, Reward: 279.053±18.106, Episode_length: 163.700±18.358\n", ++ "Rollout 5090/9766, Reward: 285.957±15.715, Episode_length: 177.000±15.550\n", ++ "Rollout 5091/9766, Reward: 288.444±23.328, Episode_length: 172.800±25.408\n", ++ "Rollout 5092/9766, Reward: 284.458±20.251, Episode_length: 229.200±193.195\n", ++ "Rollout 5093/9766, Reward: 286.132±15.635, Episode_length: 166.900±25.836\n", ++ "Rollout 5094/9766, Reward: 289.193±19.982, Episode_length: 175.700±22.109\n", ++ "Rollout 5095/9766, Reward: 274.185±15.056, Episode_length: 165.900±15.063\n", ++ "Rollout 5096/9766, Reward: 278.917±18.649, Episode_length: 171.300±18.889\n", ++ "Rollout 5097/9766, Reward: 280.893±18.166, Episode_length: 173.600±17.625\n", ++ "Rollout 5098/9766, Reward: 286.776±16.865, Episode_length: 166.900±20.022\n", ++ "Rollout 5099/9766, Reward: 286.905±18.895, Episode_length: 177.500±18.162\n", ++ "Rollout 5100/9766, Reward: 296.934±16.060, Episode_length: 169.800±25.926\n", ++ "Rollout 5101/9766, Reward: 290.012±15.581, Episode_length: 176.100±19.107\n", ++ "Rollout 5102/9766, Reward: 291.935±10.549, Episode_length: 178.400±22.191\n", ++ "Rollout 5103/9766, Reward: 292.650±15.522, Episode_length: 177.600±20.915\n", ++ "Rollout 5104/9766, Reward: 283.871±15.385, Episode_length: 182.200±19.929\n", ++ "Rollout 5105/9766, Reward: 296.380±10.629, Episode_length: 175.000±22.494\n", ++ "Rollout 5106/9766, Reward: 286.403±22.045, Episode_length: 187.300±24.719\n", ++ "Rollout 5107/9766, Reward: 292.205±17.301, Episode_length: 185.400±17.025\n", ++ "Rollout 5108/9766, Reward: 281.199±38.382, Episode_length: 256.300±248.413\n", ++ "Rollout 5109/9766, Reward: 216.846±169.956, Episode_length: 160.800±15.098\n", ++ "Rollout 5110/9766, Reward: 286.322±14.379, Episode_length: 176.100±19.937\n", ++ "Rollout 5111/9766, Reward: 278.811±15.245, Episode_length: 167.300±11.296\n", ++ "Rollout 5112/9766, Reward: 278.862±14.816, Episode_length: 192.700±37.659\n", ++ "Rollout 5113/9766, Reward: 192.123±272.598, Episode_length: 171.100±23.032\n", ++ "Rollout 5114/9766, Reward: 293.811±7.336, Episode_length: 187.600±30.751\n", ++ "Rollout 5115/9766, Reward: 282.053±21.177, Episode_length: 175.700±21.513\n", ++ "Rollout 5116/9766, Reward: 295.359±16.516, Episode_length: 171.400±21.453\n", ++ "Rollout 5117/9766, Reward: 295.558±9.090, Episode_length: 175.100±10.700\n", ++ "Rollout 5118/9766, Reward: 232.395±61.191, Episode_length: 587.100±407.382\n", ++ "Rollout 5119/9766, Reward: 293.395±12.658, Episode_length: 185.300±13.929\n", ++ "Rollout 5120/9766, Reward: 294.099±15.069, Episode_length: 174.500±15.455\n", ++ "Rollout 5121/9766, Reward: 292.377±19.396, Episode_length: 180.600±20.723\n", ++ "Rollout 5122/9766, Reward: 255.245±81.117, Episode_length: 161.000±27.770\n", ++ "Rollout 5123/9766, Reward: 193.688±52.241, Episode_length: 827.700±344.602\n", ++ "Rollout 5124/9766, Reward: 264.410±24.608, Episode_length: 380.500±113.378\n", ++ "Rollout 5125/9766, Reward: 269.047±11.998, Episode_length: 625.500±200.413\n", ++ "Rollout 5126/9766, Reward: 266.532±18.115, Episode_length: 293.700±65.585\n", ++ "Rollout 5127/9766, Reward: 198.659±55.761, Episode_length: 774.200±303.494\n", ++ "Rollout 5128/9766, Reward: 268.555±20.110, Episode_length: 297.300±56.445\n", ++ "Rollout 5129/9766, Reward: 270.644±17.594, Episode_length: 337.700±78.881\n", ++ "Rollout 5130/9766, Reward: 249.039±49.822, Episode_length: 329.300±226.385\n", ++ "Rollout 5131/9766, Reward: 258.367±25.084, Episode_length: 295.500±96.744\n", ++ "Rollout 5132/9766, Reward: 254.774±36.736, Episode_length: 326.400±131.473\n", ++ "Rollout 5133/9766, Reward: 236.492±47.347, Episode_length: 427.700±289.399\n", ++ "Rollout 5134/9766, Reward: 224.981±39.126, Episode_length: 409.400±250.737\n", ++ "Rollout 5135/9766, Reward: 200.783±62.089, Episode_length: 620.000±330.708\n", ++ "Rollout 5136/9766, Reward: 239.928±39.674, Episode_length: 483.100±286.915\n", ++ "Rollout 5137/9766, Reward: 230.801±49.148, Episode_length: 501.200±266.629\n", ++ "Rollout 5138/9766, Reward: 189.529±67.796, Episode_length: 676.300±350.138\n", ++ "Rollout 5139/9766, Reward: 232.462±44.918, Episode_length: 607.100±266.424\n", ++ "Rollout 5140/9766, Reward: 204.077±61.337, Episode_length: 634.000±288.149\n", ++ "Rollout 5141/9766, Reward: 183.833±56.597, Episode_length: 696.500±314.849\n", ++ "Rollout 5142/9766, Reward: 242.080±51.306, Episode_length: 426.600±318.666\n", ++ "Rollout 5143/9766, Reward: 225.955±49.725, Episode_length: 461.800±334.078\n", ++ "Rollout 5144/9766, Reward: 222.545±51.270, Episode_length: 502.000±273.071\n", ++ "Rollout 5145/9766, Reward: 218.963±40.964, Episode_length: 422.100±272.317\n", ++ "Rollout 5146/9766, Reward: 225.671±56.207, Episode_length: 442.300±315.515\n", ++ "Rollout 5147/9766, Reward: 237.201±44.095, Episode_length: 441.000±296.234\n", ++ "Rollout 5148/9766, Reward: 213.857±57.452, Episode_length: 528.800±324.503\n", ++ "Rollout 5149/9766, Reward: 202.925±59.189, Episode_length: 575.000±323.124\n", ++ "Rollout 5150/9766, Reward: 185.321±59.359, Episode_length: 711.900±275.006\n", ++ "Rollout 5151/9766, Reward: 231.357±53.578, Episode_length: 416.600±310.531\n", ++ "Rollout 5152/9766, Reward: 244.763±36.680, Episode_length: 372.800±213.921\n", ++ "Rollout 5153/9766, Reward: 230.135±63.221, Episode_length: 492.500±295.922\n", ++ "Rollout 5154/9766, Reward: 230.605±42.908, Episode_length: 309.500±111.317\n", ++ "Rollout 5155/9766, Reward: 192.272±66.355, Episode_length: 631.800±372.886\n", ++ "Rollout 5156/9766, Reward: 218.118±47.015, Episode_length: 492.400±307.044\n", ++ "Rollout 5157/9766, Reward: 242.383±33.910, Episode_length: 487.500±275.613\n", ++ "Rollout 5158/9766, Reward: 197.707±48.781, Episode_length: 506.100±331.581\n", ++ "Rollout 5159/9766, Reward: 201.744±70.950, Episode_length: 567.900±354.421\n", ++ "Rollout 5160/9766, Reward: 185.507±61.521, Episode_length: 634.600±351.600\n", ++ "Rollout 5161/9766, Reward: 210.961±35.674, Episode_length: 533.100±291.338\n", ++ "Rollout 5162/9766, Reward: 230.124±43.068, Episode_length: 423.200±256.393\n", ++ "Rollout 5163/9766, Reward: 216.476±61.547, Episode_length: 480.400±326.579\n", ++ "Rollout 5164/9766, Reward: 210.913±84.333, Episode_length: 370.600±259.980\n", ++ "Rollout 5165/9766, Reward: 220.687±35.902, Episode_length: 467.900±272.351\n", ++ "Rollout 5166/9766, Reward: 211.655±63.005, Episode_length: 591.400±326.135\n", ++ "Rollout 5167/9766, Reward: 214.816±59.259, Episode_length: 454.700±294.598\n", ++ "Rollout 5168/9766, Reward: 221.949±34.382, Episode_length: 441.700±259.030\n", ++ "Rollout 5169/9766, Reward: 230.103±32.432, Episode_length: 367.800±190.768\n", ++ "Rollout 5170/9766, Reward: 186.775±52.295, Episode_length: 608.800±335.489\n", ++ "Rollout 5171/9766, Reward: 229.909±37.518, Episode_length: 401.000±241.076\n", ++ "Rollout 5172/9766, Reward: 214.343±73.134, Episode_length: 621.200±342.375\n", ++ "Rollout 5173/9766, Reward: 249.948±49.738, Episode_length: 389.000±317.734\n", ++ "Rollout 5174/9766, Reward: 239.761±36.885, Episode_length: 415.800±247.827\n", ++ "Rollout 5175/9766, Reward: 233.783±37.178, Episode_length: 311.000±213.340\n", ++ "Rollout 5176/9766, Reward: 204.104±64.216, Episode_length: 550.600±370.677\n", ++ "Rollout 5177/9766, Reward: 218.736±63.688, Episode_length: 416.600±312.851\n", ++ "Rollout 5178/9766, Reward: 222.568±58.687, Episode_length: 463.100±357.674\n", ++ "Rollout 5179/9766, Reward: 204.645±56.267, Episode_length: 604.000±350.050\n", ++ "Rollout 5180/9766, Reward: 222.536±42.768, Episode_length: 478.400±326.906\n", ++ "Rollout 5181/9766, Reward: 207.564±46.556, Episode_length: 533.000±326.723\n", ++ "Rollout 5182/9766, Reward: 201.733±77.669, Episode_length: 455.100±349.990\n", ++ "Rollout 5183/9766, Reward: 231.071±81.080, Episode_length: 303.700±261.461\n", ++ "Rollout 5184/9766, Reward: 244.697±47.411, Episode_length: 354.100±257.257\n", ++ "Rollout 5185/9766, Reward: 228.743±40.037, Episode_length: 478.500±311.099\n", ++ "Rollout 5186/9766, Reward: 220.611±56.444, Episode_length: 312.400±197.258\n", ++ "Rollout 5187/9766, Reward: 262.229±21.557, Episode_length: 220.400±76.911\n", ++ "Rollout 5188/9766, Reward: 194.794±61.459, Episode_length: 359.800±258.289\n", ++ "Rollout 5189/9766, Reward: 217.012±53.764, Episode_length: 544.600±301.922\n", ++ "Rollout 5190/9766, Reward: 157.619±74.029, Episode_length: 512.200±408.281\n", ++ "Rollout 5191/9766, Reward: 212.256±74.954, Episode_length: 267.800±247.455\n", ++ "Rollout 5192/9766, Reward: 184.745±74.227, Episode_length: 527.100±390.108\n", ++ "Rollout 5193/9766, Reward: 218.032±60.054, Episode_length: 361.700±195.858\n", ++ "Rollout 5194/9766, Reward: 195.475±77.503, Episode_length: 337.100±249.420\n", ++ "Rollout 5195/9766, Reward: 242.605±14.816, Episode_length: 366.600±219.169\n", ++ "Rollout 5196/9766, Reward: 135.373±133.103, Episode_length: 198.800±69.657\n", ++ "Rollout 5197/9766, Reward: 214.615±69.877, Episode_length: 256.200±76.196\n", ++ "Rollout 5198/9766, Reward: 214.208±52.272, Episode_length: 346.000±182.010\n", ++ "Rollout 5199/9766, Reward: 208.945±61.822, Episode_length: 442.300±291.603\n", ++ "Rollout 5200/9766, Reward: 228.078±72.352, Episode_length: 258.700±129.297\n", ++ "Rollout 5201/9766, Reward: 226.196±58.650, Episode_length: 464.700±361.147\n", ++ "Rollout 5202/9766, Reward: 220.996±77.832, Episode_length: 374.600±292.263\n", ++ "Rollout 5203/9766, Reward: 140.755±129.782, Episode_length: 350.100±326.389\n", ++ "Rollout 5204/9766, Reward: 205.618±77.574, Episode_length: 342.900±257.067\n", ++ "Rollout 5205/9766, Reward: 223.637±31.009, Episode_length: 367.600±241.524\n", ++ "Rollout 5206/9766, Reward: 248.160±16.513, Episode_length: 343.600±187.585\n", ++ "Rollout 5207/9766, Reward: 241.861±18.235, Episode_length: 245.800±65.294\n", ++ "Rollout 5208/9766, Reward: 207.283±55.983, Episode_length: 304.400±138.354\n", ++ "Rollout 5209/9766, Reward: 208.278±71.097, Episode_length: 279.300±242.975\n", ++ "Rollout 5210/9766, Reward: 217.979±58.969, Episode_length: 453.600±360.115\n", ++ "Rollout 5211/9766, Reward: 210.517±22.647, Episode_length: 345.000±150.609\n", ++ "Rollout 5212/9766, Reward: 197.943±96.921, Episode_length: 315.900±234.564\n", ++ "Rollout 5213/9766, Reward: 223.977±35.911, Episode_length: 306.900±167.652\n", ++ "Rollout 5214/9766, Reward: 241.490±20.197, Episode_length: 358.300±170.624\n", ++ "Rollout 5215/9766, Reward: 220.052±30.877, Episode_length: 404.500±243.760\n", ++ "Rollout 5216/9766, Reward: 139.837±159.907, Episode_length: 345.400±249.858\n", ++ "Rollout 5217/9766, Reward: 196.822±76.511, Episode_length: 271.700±106.027\n", ++ "Rollout 5218/9766, Reward: 192.508±54.795, Episode_length: 405.200±303.032\n", ++ "Rollout 5219/9766, Reward: 228.337±30.891, Episode_length: 256.300±71.264\n", ++ "Rollout 5220/9766, Reward: 180.221±80.411, Episode_length: 389.400±318.895\n", ++ "Rollout 5221/9766, Reward: 185.389±76.995, Episode_length: 412.100±307.242\n", ++ "Rollout 5222/9766, Reward: 252.558±41.432, Episode_length: 277.800±184.233\n", ++ "Rollout 5223/9766, Reward: 214.288±39.538, Episode_length: 250.300±88.634\n", ++ "Rollout 5224/9766, Reward: 208.391±101.221, Episode_length: 359.000±239.436\n", ++ "Rollout 5225/9766, Reward: 217.156±75.896, Episode_length: 249.000±91.378\n", ++ "Rollout 5226/9766, Reward: 203.371±52.601, Episode_length: 352.900±225.224\n", ++ "Rollout 5227/9766, Reward: 228.001±67.627, Episode_length: 222.600±54.410\n", ++ "Rollout 5228/9766, Reward: 202.204±174.259, Episode_length: 276.500±169.483\n", ++ "Rollout 5229/9766, Reward: 230.180±50.298, Episode_length: 380.500±291.076\n", ++ "Rollout 5230/9766, Reward: 252.830±23.606, Episode_length: 260.500±59.899\n", ++ "Rollout 5231/9766, Reward: 236.877±56.747, Episode_length: 343.200±237.721\n", ++ "Rollout 5232/9766, Reward: 237.117±52.315, Episode_length: 258.000±93.533\n", ++ "Rollout 5233/9766, Reward: 266.561±40.080, Episode_length: 281.400±174.331\n", ++ "Rollout 5234/9766, Reward: 223.837±57.485, Episode_length: 337.800±232.053\n", ++ "Rollout 5235/9766, Reward: 276.857±17.053, Episode_length: 188.700±19.334\n", ++ "Rollout 5236/9766, Reward: 270.015±24.303, Episode_length: 271.200±151.754\n", ++ "Rollout 5237/9766, Reward: 264.022±39.983, Episode_length: 282.700±239.649\n", ++ "Rollout 5238/9766, Reward: 247.944±62.782, Episode_length: 405.800±337.497\n", ++ "Rollout 5239/9766, Reward: 266.643±19.167, Episode_length: 199.600±16.596\n", ++ "Rollout 5240/9766, Reward: 246.385±53.849, Episode_length: 358.100±321.814\n", ++ "Rollout 5241/9766, Reward: 268.222±21.032, Episode_length: 194.600±19.946\n", ++ "Rollout 5242/9766, Reward: 273.969±16.048, Episode_length: 196.900±18.828\n", ++ "Rollout 5243/9766, Reward: 258.999±52.326, Episode_length: 281.100±241.107\n", ++ "Rollout 5244/9766, Reward: 250.511±46.188, Episode_length: 290.200±253.654\n", ++ "Rollout 5245/9766, Reward: 275.725±23.830, Episode_length: 190.600±20.636\n", ++ "Rollout 5246/9766, Reward: 270.438±14.876, Episode_length: 201.100±37.020\n", ++ "Rollout 5247/9766, Reward: 265.169±21.804, Episode_length: 219.600±62.407\n", ++ "Rollout 5248/9766, Reward: 268.876±23.110, Episode_length: 232.000±110.597\n", ++ "Rollout 5249/9766, Reward: 275.744±19.223, Episode_length: 197.700±35.468\n", ++ "Rollout 5250/9766, Reward: 253.493±34.991, Episode_length: 280.000±100.904\n", ++ "Rollout 5251/9766, Reward: 259.544±24.912, Episode_length: 233.400±50.369\n", ++ "Rollout 5252/9766, Reward: 251.316±43.854, Episode_length: 269.700±244.557\n", ++ "Rollout 5253/9766, Reward: 226.058±77.572, Episode_length: 313.100±248.890\n", ++ "Rollout 5254/9766, Reward: 268.037±18.563, Episode_length: 194.700±49.344\n", ++ "Rollout 5255/9766, Reward: 281.546±16.713, Episode_length: 210.300±27.749\n", ++ "Rollout 5256/9766, Reward: 245.476±72.536, Episode_length: 203.600±71.504\n", ++ "Rollout 5257/9766, Reward: 268.353±16.815, Episode_length: 200.100±39.075\n", ++ "Rollout 5258/9766, Reward: 277.283±17.200, Episode_length: 174.200±21.720\n", ++ "Rollout 5259/9766, Reward: 278.924±20.509, Episode_length: 193.500±17.845\n", ++ "Rollout 5260/9766, Reward: 263.519±17.811, Episode_length: 180.300±22.826\n", ++ "Rollout 5261/9766, Reward: 282.326±13.182, Episode_length: 176.800±20.079\n", ++ "Rollout 5262/9766, Reward: 259.037±54.021, Episode_length: 329.700±287.825\n", ++ "Rollout 5263/9766, Reward: 268.528±70.698, Episode_length: 173.300±23.397\n", ++ "Rollout 5264/9766, Reward: 265.957±32.975, Episode_length: 259.200±247.417\n", ++ "Rollout 5265/9766, Reward: 252.444±74.402, Episode_length: 178.900±27.388\n", ++ "Rollout 5266/9766, Reward: 269.678±37.889, Episode_length: 274.500±243.473\n", ++ "Rollout 5267/9766, Reward: 282.468±18.475, Episode_length: 186.200±30.646\n", ++ "Rollout 5268/9766, Reward: 257.162±75.477, Episode_length: 200.200±39.939\n", ++ "Rollout 5269/9766, Reward: 260.633±72.283, Episode_length: 190.800±33.508\n", ++ "Rollout 5270/9766, Reward: 265.202±39.987, Episode_length: 292.600±240.631\n", ++ "Rollout 5271/9766, Reward: 232.104±79.146, Episode_length: 331.400±334.739\n", ++ "Rollout 5272/9766, Reward: 142.941±313.893, Episode_length: 331.300±335.297\n", ++ "Rollout 5273/9766, Reward: 282.005±19.999, Episode_length: 175.100±18.929\n", ++ "Rollout 5274/9766, Reward: 272.920±38.996, Episode_length: 271.900±243.283\n", ++ "Rollout 5275/9766, Reward: 274.440±16.729, Episode_length: 172.700±21.941\n", ++ "Rollout 5276/9766, Reward: 276.742±19.112, Episode_length: 180.200±26.836\n", ++ "Rollout 5277/9766, Reward: 140.830±327.378, Episode_length: 341.700±329.633\n", ++ "Rollout 5278/9766, Reward: 180.487±284.115, Episode_length: 258.300±248.965\n", ++ "Rollout 5279/9766, Reward: 200.110±52.114, Episode_length: 749.900±382.048\n", ++ "Rollout 5280/9766, Reward: 213.786±56.103, Episode_length: 700.700±373.382\n", ++ "Rollout 5281/9766, Reward: 178.814±269.330, Episode_length: 272.500±57.093\n", ++ "Rollout 5282/9766, Reward: 232.621±50.391, Episode_length: 581.400±403.612\n", ++ "Rollout 5283/9766, Reward: 271.027±42.292, Episode_length: 425.000±362.254\n", ++ "Rollout 5284/9766, Reward: 259.361±43.026, Episode_length: 423.000±365.780\n", ++ "Rollout 5285/9766, Reward: 268.588±45.602, Episode_length: 338.600±323.275\n", ++ "Rollout 5286/9766, Reward: 278.624±36.529, Episode_length: 257.400±248.297\n", ++ "Rollout 5287/9766, Reward: 250.510±51.658, Episode_length: 515.100±382.545\n", ++ "Rollout 5288/9766, Reward: 247.865±45.817, Episode_length: 483.900±379.446\n", ++ "Rollout 5289/9766, Reward: -142.732±730.065, Episode_length: 168.900±29.002\n", ++ "Rollout 5290/9766, Reward: -83.810±747.346, Episode_length: 268.000±247.937\n", ++ "Rollout 5291/9766, Reward: 233.307±42.876, Episode_length: 680.000±372.353\n", ++ "Rollout 5292/9766, Reward: 137.153±415.413, Episode_length: 330.500±327.516\n", ++ "Rollout 5293/9766, Reward: -20.643±584.825, Episode_length: 264.500±246.506\n", ++ "Rollout 5294/9766, Reward: -138.164±693.481, Episode_length: 177.700±44.759\n", ++ "Rollout 5295/9766, Reward: 276.721±13.534, Episode_length: 196.400±64.732\n", ++ "Rollout 5296/9766, Reward: 205.295±213.969, Episode_length: 170.300±32.982\n", ++ "Rollout 5297/9766, Reward: 48.440±469.863, Episode_length: 163.300±35.911\n", ++ "Rollout 5298/9766, Reward: 281.243±12.508, Episode_length: 214.700±117.812\n", ++ "Rollout 5299/9766, Reward: 82.025±403.198, Episode_length: 204.600±124.072\n", ++ "Rollout 5300/9766, Reward: 269.663±32.507, Episode_length: 264.600±245.646\n", ++ "Rollout 5301/9766, Reward: 82.830±411.001, Episode_length: 154.800±25.325\n", ++ "Rollout 5302/9766, Reward: 100.986±505.426, Episode_length: 273.500±244.688\n", ++ "Rollout 5303/9766, Reward: 194.737±261.836, Episode_length: 186.000±33.445\n", ++ "Rollout 5304/9766, Reward: 106.464±344.007, Episode_length: 164.400±30.398\n", ++ "Rollout 5305/9766, Reward: 275.748±37.266, Episode_length: 276.000±242.832\n", ++ "Rollout 5306/9766, Reward: 182.303±293.056, Episode_length: 186.400±30.578\n", ++ "Rollout 5307/9766, Reward: 199.501±274.660, Episode_length: 201.600±28.118\n", ++ "Rollout 5308/9766, Reward: 294.240±11.927, Episode_length: 193.000±28.071\n", ++ "Rollout 5309/9766, Reward: 281.023±11.901, Episode_length: 185.900±27.930\n", ++ "Rollout 5310/9766, Reward: 283.157±19.889, Episode_length: 195.700±32.821\n", ++ "Rollout 5311/9766, Reward: 288.886±11.966, Episode_length: 196.200±29.260\n", ++ "Rollout 5312/9766, Reward: 288.934±15.155, Episode_length: 193.600±22.975\n", ++ "Rollout 5313/9766, Reward: 113.272±546.425, Episode_length: 209.900±19.398\n", ++ "Rollout 5314/9766, Reward: 187.403±298.622, Episode_length: 191.500±28.949\n", ++ "Rollout 5315/9766, Reward: 290.712±10.733, Episode_length: 194.100±19.527\n", ++ "Rollout 5316/9766, Reward: 289.285±15.495, Episode_length: 204.200±28.028\n", ++ "Rollout 5317/9766, Reward: 279.911±18.724, Episode_length: 178.200±12.718\n", ++ "Rollout 5318/9766, Reward: 278.643±12.736, Episode_length: 169.800±23.966\n", ++ "Rollout 5319/9766, Reward: 284.849±14.651, Episode_length: 192.400±27.543\n", ++ "Rollout 5320/9766, Reward: 287.825±18.983, Episode_length: 203.800±31.102\n", ++ "Rollout 5321/9766, Reward: 293.595±15.267, Episode_length: 181.400±26.964\n", ++ "Rollout 5322/9766, Reward: 285.040±13.395, Episode_length: 197.800±29.267\n", ++ "Rollout 5323/9766, Reward: 261.183±46.499, Episode_length: 270.200±245.268\n", ++ "Rollout 5324/9766, Reward: 270.550±22.220, Episode_length: 240.000±152.812\n", ++ "Rollout 5325/9766, Reward: 271.076±22.499, Episode_length: 200.900±91.883\n", ++ "Rollout 5326/9766, Reward: 273.373±15.428, Episode_length: 202.000±29.038\n", ++ "Rollout 5327/9766, Reward: 270.755±20.238, Episode_length: 255.700±185.715\n", ++ "Rollout 5328/9766, Reward: 183.169±248.665, Episode_length: 283.000±188.652\n", ++ "Rollout 5329/9766, Reward: 264.317±12.430, Episode_length: 208.600±36.710\n", ++ "Rollout 5330/9766, Reward: 258.800±30.738, Episode_length: 269.400±164.021\n", ++ "Rollout 5331/9766, Reward: 166.573±274.032, Episode_length: 256.200±180.190\n", ++ "Rollout 5332/9766, Reward: 171.586±259.314, Episode_length: 277.500±198.946\n", ++ "Rollout 5333/9766, Reward: 227.593±75.964, Episode_length: 349.100±281.030\n", ++ "Rollout 5334/9766, Reward: 170.348±256.983, Episode_length: 272.600±197.972\n", ++ "Rollout 5335/9766, Reward: 256.948±30.581, Episode_length: 273.200±55.304\n", ++ "Rollout 5336/9766, Reward: 232.977±44.201, Episode_length: 342.500±231.374\n", ++ "Rollout 5337/9766, Reward: 220.073±81.635, Episode_length: 292.200±237.300\n", ++ "Rollout 5338/9766, Reward: 228.709±47.070, Episode_length: 273.900±97.841\n", ++ "Rollout 5339/9766, Reward: 244.070±33.534, Episode_length: 271.200±68.587\n", ++ "Rollout 5340/9766, Reward: 248.330±27.222, Episode_length: 249.300±49.289\n", ++ "Rollout 5341/9766, Reward: 262.285±27.947, Episode_length: 295.900±168.265\n", ++ "Rollout 5342/9766, Reward: 202.912±74.525, Episode_length: 304.700±241.121\n", ++ "Rollout 5343/9766, Reward: 248.011±15.207, Episode_length: 212.400±32.500\n", ++ "Rollout 5344/9766, Reward: 251.391±28.101, Episode_length: 241.900±52.235\n", ++ "Rollout 5345/9766, Reward: 227.836±40.444, Episode_length: 400.700±263.041\n", ++ "Rollout 5346/9766, Reward: 258.237±19.375, Episode_length: 211.800±47.858\n", ++ "Rollout 5347/9766, Reward: 246.501±21.206, Episode_length: 314.800±182.867\n", ++ "Rollout 5348/9766, Reward: 247.627±49.499, Episode_length: 322.600±244.130\n", ++ "Rollout 5349/9766, Reward: 255.758±26.985, Episode_length: 230.300±57.705\n", ++ "Rollout 5350/9766, Reward: 257.000±16.014, Episode_length: 257.500±64.839\n", ++ "Rollout 5351/9766, Reward: 253.970±36.065, Episode_length: 215.900±40.273\n", ++ "Rollout 5352/9766, Reward: 251.056±20.194, Episode_length: 237.400±46.911\n", ++ "Rollout 5353/9766, Reward: 251.500±27.142, Episode_length: 270.700±77.977\n", ++ "Rollout 5354/9766, Reward: 245.744±51.180, Episode_length: 308.100±234.283\n", ++ "Rollout 5355/9766, Reward: 187.409±49.013, Episode_length: 450.400±282.520\n", ++ "Rollout 5356/9766, Reward: 220.804±68.345, Episode_length: 489.500±352.860\n", ++ "Rollout 5357/9766, Reward: 244.563±38.261, Episode_length: 357.300±289.788\n", ++ "Rollout 5358/9766, Reward: 141.512±262.477, Episode_length: 446.300±326.106\n", ++ "Rollout 5359/9766, Reward: 185.653±271.158, Episode_length: 197.300±26.196\n", ++ "Rollout 5360/9766, Reward: 241.074±82.520, Episode_length: 277.700±244.824\n", ++ "Rollout 5361/9766, Reward: 286.874±17.520, Episode_length: 208.300±34.768\n", ++ "Rollout 5362/9766, Reward: 279.984±16.412, Episode_length: 192.800±23.579\n", ++ "Rollout 5363/9766, Reward: 260.995±57.113, Episode_length: 288.700±238.116\n", ++ "Rollout 5364/9766, Reward: 292.276±12.230, Episode_length: 203.000±32.385\n", ++ "Rollout 5365/9766, Reward: 286.948±18.489, Episode_length: 201.900±31.313\n", ++ "Rollout 5366/9766, Reward: 276.609±31.540, Episode_length: 215.500±68.025\n", ++ "Rollout 5367/9766, Reward: 285.398±20.592, Episode_length: 200.500±32.101\n", ++ "Rollout 5368/9766, Reward: 278.315±22.082, Episode_length: 221.800±35.111\n", ++ "Rollout 5369/9766, Reward: 263.270±37.495, Episode_length: 243.600±92.563\n", ++ "Rollout 5370/9766, Reward: 264.604±42.845, Episode_length: 330.700±234.410\n", ++ "Rollout 5371/9766, Reward: 260.130±66.984, Episode_length: 307.000±243.391\n", ++ "Rollout 5372/9766, Reward: 284.404±15.134, Episode_length: 191.400±26.318\n", ++ "Rollout 5373/9766, Reward: 256.015±29.916, Episode_length: 229.200±146.954\n", ++ "Rollout 5374/9766, Reward: 263.374±26.616, Episode_length: 205.600±58.485\n", ++ "Rollout 5375/9766, Reward: 276.277±29.043, Episode_length: 190.000±62.426\n", ++ "Rollout 5376/9766, Reward: 280.054±15.102, Episode_length: 201.200±38.023\n", ++ "Rollout 5377/9766, Reward: 278.595±18.976, Episode_length: 196.000±21.204\n", ++ "Rollout 5378/9766, Reward: 286.551±12.233, Episode_length: 197.700±26.710\n", ++ "Rollout 5379/9766, Reward: 280.163±14.885, Episode_length: 168.800±15.052\n", ++ "Rollout 5380/9766, Reward: 281.306±17.582, Episode_length: 189.000±24.339\n", ++ "Rollout 5381/9766, Reward: 285.526±21.733, Episode_length: 177.300±25.730\n", ++ "Rollout 5382/9766, Reward: 281.290±20.635, Episode_length: 179.400±33.122\n", ++ "Rollout 5383/9766, Reward: 279.506±20.253, Episode_length: 205.300±80.626\n", ++ "Rollout 5384/9766, Reward: 279.814±17.688, Episode_length: 169.500±24.804\n", ++ "Rollout 5385/9766, Reward: 275.330±18.119, Episode_length: 196.300±49.667\n", ++ "Rollout 5386/9766, Reward: 289.430±16.152, Episode_length: 193.100±24.399\n", ++ "Rollout 5387/9766, Reward: 289.340±17.977, Episode_length: 200.200±36.166\n", ++ "Rollout 5388/9766, Reward: 282.491±19.077, Episode_length: 176.100±26.501\n", ++ "Rollout 5389/9766, Reward: 277.020±13.812, Episode_length: 174.400±21.435\n", ++ "Rollout 5390/9766, Reward: 281.281±17.835, Episode_length: 192.000±27.111\n", ++ "Rollout 5391/9766, Reward: 292.992±19.433, Episode_length: 188.400±33.892\n", ++ "Rollout 5392/9766, Reward: 286.681±10.651, Episode_length: 185.500±26.352\n", ++ "Rollout 5393/9766, Reward: 272.805±36.454, Episode_length: 250.200±250.861\n", ++ "Rollout 5394/9766, Reward: 287.676±12.269, Episode_length: 187.400±16.972\n", ++ "Rollout 5395/9766, Reward: 285.187±9.642, Episode_length: 179.100±29.036\n", ++ "Rollout 5396/9766, Reward: 276.053±22.179, Episode_length: 212.000±110.393\n", ++ "Rollout 5397/9766, Reward: 286.774±18.735, Episode_length: 203.500±35.229\n", ++ "Rollout 5398/9766, Reward: 275.292±28.281, Episode_length: 204.100±67.591\n", ++ "Rollout 5399/9766, Reward: 281.999±13.810, Episode_length: 228.300±92.220\n", ++ "Rollout 5400/9766, Reward: 273.304±17.214, Episode_length: 191.000±19.370\n", ++ "Rollout 5401/9766, Reward: 283.604±16.677, Episode_length: 191.100±20.032\n", ++ "Rollout 5402/9766, Reward: 284.868±11.889, Episode_length: 177.700±21.171\n", ++ "Rollout 5403/9766, Reward: 286.124±17.916, Episode_length: 176.300±24.972\n", ++ "Rollout 5404/9766, Reward: 270.088±28.988, Episode_length: 253.700±171.995\n", ++ "Rollout 5405/9766, Reward: 278.579±22.316, Episode_length: 197.900±59.767\n", ++ "Rollout 5406/9766, Reward: 287.806±15.416, Episode_length: 197.100±32.461\n", ++ "Rollout 5407/9766, Reward: 272.964±22.113, Episode_length: 218.800±133.211\n", ++ "Rollout 5408/9766, Reward: 280.491±15.087, Episode_length: 195.100±22.954\n", ++ "Rollout 5409/9766, Reward: 275.999±8.663, Episode_length: 181.200±22.925\n", ++ "Rollout 5410/9766, Reward: 269.255±39.364, Episode_length: 247.400±251.270\n", ++ "Rollout 5411/9766, Reward: 266.211±43.881, Episode_length: 262.400±248.589\n", ++ "Rollout 5412/9766, Reward: 282.984±14.798, Episode_length: 185.500±31.611\n", ++ "Rollout 5413/9766, Reward: 265.943±19.073, Episode_length: 311.200±111.852\n", ++ "Rollout 5414/9766, Reward: 266.112±19.651, Episode_length: 269.200±33.117\n", ++ "Rollout 5415/9766, Reward: 273.797±20.357, Episode_length: 296.300±64.453\n", ++ "Rollout 5416/9766, Reward: 271.229±22.587, Episode_length: 260.500±88.098\n", ++ "Rollout 5417/9766, Reward: 248.571±40.176, Episode_length: 404.500±258.933\n", ++ "Rollout 5418/9766, Reward: 267.685±24.334, Episode_length: 258.600±118.005\n", ++ "Rollout 5419/9766, Reward: 273.014±16.477, Episode_length: 276.000±61.617\n", ++ "Rollout 5420/9766, Reward: 273.880±18.638, Episode_length: 255.900±21.524\n", ++ "Rollout 5421/9766, Reward: 276.282±15.368, Episode_length: 176.500±21.148\n", ++ "Rollout 5422/9766, Reward: 276.573±18.985, Episode_length: 179.100±20.117\n", ++ "Rollout 5423/9766, Reward: 284.239±16.195, Episode_length: 177.800±22.838\n", ++ "Rollout 5424/9766, Reward: 281.402±12.918, Episode_length: 178.400±23.001\n", ++ "Rollout 5425/9766, Reward: 285.914±16.591, Episode_length: 180.300±22.150\n", ++ "Rollout 5426/9766, Reward: 294.372±13.836, Episode_length: 196.200±30.016\n", ++ "Rollout 5427/9766, Reward: 286.641±16.928, Episode_length: 193.100±32.160\n", ++ "Rollout 5428/9766, Reward: 277.960±15.160, Episode_length: 200.900±23.407\n", ++ "Rollout 5429/9766, Reward: 292.943±16.538, Episode_length: 179.200±32.273\n", ++ "Rollout 5430/9766, Reward: 277.351±23.946, Episode_length: 183.500±23.720\n", ++ "Rollout 5431/9766, Reward: 247.900±33.139, Episode_length: 390.900±306.091\n", ++ "Rollout 5432/9766, Reward: 246.668±57.628, Episode_length: 375.900±248.257\n", ++ "Rollout 5433/9766, Reward: 252.485±14.528, Episode_length: 266.400±164.157\n", ++ "Rollout 5434/9766, Reward: 267.006±32.564, Episode_length: 315.200±232.553\n", ++ "Rollout 5435/9766, Reward: 250.419±41.484, Episode_length: 317.500±240.940\n", ++ "Rollout 5436/9766, Reward: 226.681±66.794, Episode_length: 467.900±353.674\n", ++ "Rollout 5437/9766, Reward: 257.440±49.846, Episode_length: 299.900±237.330\n", ++ "Rollout 5438/9766, Reward: 210.267±85.101, Episode_length: 420.600±297.744\n", ++ "Rollout 5439/9766, Reward: 251.323±33.095, Episode_length: 239.200±88.097\n", ++ "Rollout 5440/9766, Reward: 258.358±29.749, Episode_length: 293.300±150.715\n", ++ "Rollout 5441/9766, Reward: 257.009±34.248, Episode_length: 211.700±55.218\n", ++ "Rollout 5442/9766, Reward: 244.802±39.593, Episode_length: 236.400±109.959\n", ++ "Rollout 5443/9766, Reward: 253.268±24.117, Episode_length: 199.000±61.276\n", ++ "Rollout 5444/9766, Reward: 265.939±28.181, Episode_length: 252.400±166.043\n", ++ "Rollout 5445/9766, Reward: 254.902±33.732, Episode_length: 266.900±149.777\n", ++ "Rollout 5446/9766, Reward: 226.655±68.375, Episode_length: 334.200±271.899\n", ++ "Rollout 5447/9766, Reward: 216.963±66.256, Episode_length: 377.600±313.749\n", ++ "Rollout 5448/9766, Reward: 234.952±52.795, Episode_length: 344.700±231.014\n", ++ "Rollout 5449/9766, Reward: 219.064��81.531, Episode_length: 364.200±319.527\n", ++ "Rollout 5450/9766, Reward: 214.026±52.124, Episode_length: 462.100±355.996\n", ++ "Rollout 5451/9766, Reward: 206.723±46.242, Episode_length: 406.800±304.245\n", ++ "Rollout 5452/9766, Reward: 195.971±58.582, Episode_length: 478.700±288.626\n", ++ "Rollout 5453/9766, Reward: 203.957±92.036, Episode_length: 317.400±234.296\n", ++ "Rollout 5454/9766, Reward: 239.295±40.508, Episode_length: 298.300±131.106\n", ++ "Rollout 5455/9766, Reward: 231.419±31.938, Episode_length: 274.000±72.654\n", ++ "Rollout 5456/9766, Reward: 213.665±41.641, Episode_length: 379.300±230.576\n", ++ "Rollout 5457/9766, Reward: 216.686±26.619, Episode_length: 303.100±107.374\n", ++ "Rollout 5458/9766, Reward: 152.292±106.886, Episode_length: 519.200±328.948\n", ++ "Rollout 5459/9766, Reward: 214.808±43.119, Episode_length: 316.700±231.025\n", ++ "Rollout 5460/9766, Reward: 188.863±113.722, Episode_length: 400.500±302.057\n", ++ "Rollout 5461/9766, Reward: 226.592±40.726, Episode_length: 356.800±191.314\n", ++ "Rollout 5462/9766, Reward: 231.620±39.714, Episode_length: 257.900±80.170\n", ++ "Rollout 5463/9766, Reward: 231.697±20.986, Episode_length: 232.700±45.013\n", ++ "Rollout 5464/9766, Reward: 234.862±36.952, Episode_length: 297.600±129.697\n", ++ "Rollout 5465/9766, Reward: 228.373±52.898, Episode_length: 336.200±234.323\n", ++ "Rollout 5466/9766, Reward: 178.890±92.620, Episode_length: 443.700±338.013\n", ++ "Rollout 5467/9766, Reward: 219.659±47.901, Episode_length: 335.600±225.827\n", ++ "Rollout 5468/9766, Reward: 219.351±75.546, Episode_length: 399.200±261.256\n", ++ "Rollout 5469/9766, Reward: 205.410±73.170, Episode_length: 378.400±267.109\n", ++ "Rollout 5470/9766, Reward: 191.733±57.199, Episode_length: 498.500±332.598\n", ++ "Rollout 5471/9766, Reward: 231.225±26.313, Episode_length: 352.300±210.194\n", ++ "Rollout 5472/9766, Reward: 226.559±39.643, Episode_length: 264.100±59.852\n", ++ "Rollout 5473/9766, Reward: 204.320±56.457, Episode_length: 502.700±351.625\n", ++ "Rollout 5474/9766, Reward: 212.389±67.150, Episode_length: 357.900±260.943\n", ++ "Rollout 5475/9766, Reward: 222.769±50.287, Episode_length: 556.300±327.843\n", ++ "Rollout 5476/9766, Reward: 228.273±45.995, Episode_length: 377.600±320.676\n", ++ "Rollout 5477/9766, Reward: 217.244±48.449, Episode_length: 307.100±112.574\n", ++ "Rollout 5478/9766, Reward: 224.530±48.904, Episode_length: 376.200±322.665\n", ++ "Rollout 5479/9766, Reward: 234.840±42.340, Episode_length: 401.000±261.546\n", ++ "Rollout 5480/9766, Reward: 254.082±28.488, Episode_length: 232.700±56.338\n", ++ "Rollout 5481/9766, Reward: 230.593±52.843, Episode_length: 279.600±85.118\n", ++ "Rollout 5482/9766, Reward: 258.709±32.376, Episode_length: 223.600±47.599\n", ++ "Rollout 5483/9766, Reward: 250.448±32.421, Episode_length: 233.300±64.399\n", ++ "Rollout 5484/9766, Reward: 263.668±27.908, Episode_length: 256.000±79.059\n", ++ "Rollout 5485/9766, Reward: 242.919±30.312, Episode_length: 286.700±121.689\n", ++ "Rollout 5486/9766, Reward: 210.505±99.931, Episode_length: 350.000±249.546\n", ++ "Rollout 5487/9766, Reward: 228.306±55.899, Episode_length: 342.000±248.136\n", ++ "Rollout 5488/9766, Reward: 250.964±22.401, Episode_length: 287.200±143.774\n", ++ "Rollout 5489/9766, Reward: 242.408±30.896, Episode_length: 206.700±30.529\n", ++ "Rollout 5490/9766, Reward: 243.128±27.028, Episode_length: 241.400±102.226\n", ++ "Rollout 5491/9766, Reward: 237.436±57.492, Episode_length: 395.000±322.795\n", ++ "Rollout 5492/9766, Reward: 242.734±45.346, Episode_length: 262.800±246.478\n", ++ "Rollout 5493/9766, Reward: 265.680±31.358, Episode_length: 217.500±55.630\n", ++ "Rollout 5494/9766, Reward: 264.135±31.867, Episode_length: 238.200±61.934\n", ++ "Rollout 5495/9766, Reward: 275.440±19.264, Episode_length: 198.600±42.176\n", ++ "Rollout 5496/9766, Reward: 274.947±22.361, Episode_length: 185.100±25.563\n", ++ "Rollout 5497/9766, Reward: 269.056±14.962, Episode_length: 179.300±18.979\n", ++ "Rollout 5498/9766, Reward: 262.235±11.708, Episode_length: 186.400±20.646\n", ++ "Rollout 5499/9766, Reward: 275.943±8.180, Episode_length: 192.800±23.455\n", ++ "Rollout 5500/9766, Reward: 196.764±87.117, Episode_length: 330.400±336.879\n", ++ "Rollout 5501/9766, Reward: 255.537±43.359, Episode_length: 284.300±247.125\n", ++ "Rollout 5502/9766, Reward: 253.380±32.546, Episode_length: 255.900±74.381\n", ++ "Rollout 5503/9766, Reward: 259.732±41.912, Episode_length: 259.300±247.125\n", ++ "Rollout 5504/9766, Reward: 263.543±24.694, Episode_length: 294.600±93.203\n", ++ "Rollout 5505/9766, Reward: 274.061±26.841, Episode_length: 186.500±24.072\n", ++ "Rollout 5506/9766, Reward: 264.334±30.296, Episode_length: 208.100±68.323\n", ++ "Rollout 5507/9766, Reward: 273.160±20.836, Episode_length: 200.000±20.823\n", ++ "Rollout 5508/9766, Reward: 275.005±18.423, Episode_length: 205.400±37.649\n", ++ "Rollout 5509/9766, Reward: 247.913±39.569, Episode_length: 265.300±248.348\n", ++ "Rollout 5510/9766, Reward: 266.845±47.279, Episode_length: 280.400±241.637\n", ++ "Rollout 5511/9766, Reward: 268.163±12.463, Episode_length: 199.300±30.017\n", ++ "Rollout 5512/9766, Reward: 252.983±50.405, Episode_length: 315.300±250.510\n", ++ "Rollout 5513/9766, Reward: 236.324±107.792, Episode_length: 313.200±232.244\n", ++ "Rollout 5514/9766, Reward: 243.577±56.833, Episode_length: 348.800±243.050\n", ++ "Rollout 5515/9766, Reward: 217.796±71.657, Episode_length: 287.500±242.359\n", ++ "Rollout 5516/9766, Reward: 262.906±22.031, Episode_length: 219.500±34.633\n", ++ "Rollout 5517/9766, Reward: 261.860±28.275, Episode_length: 231.200±39.436\n", ++ "Rollout 5518/9766, Reward: 224.690±64.545, Episode_length: 442.700±365.033\n", ++ "Rollout 5519/9766, Reward: 215.482±71.735, Episode_length: 389.800±311.202\n", ++ "Rollout 5520/9766, Reward: 236.827±48.243, Episode_length: 334.100±235.368\n", ++ "Rollout 5521/9766, Reward: 230.897±54.784, Episode_length: 400.200±315.258\n", ++ "Rollout 5522/9766, Reward: 227.684±37.473, Episode_length: 379.900±175.806\n", ++ "Rollout 5523/9766, Reward: 260.430±45.773, Episode_length: 347.200±269.204\n", ++ "Rollout 5524/9766, Reward: 245.144±58.958, Episode_length: 372.200±316.910\n", ++ "Rollout 5525/9766, Reward: 236.081±80.986, Episode_length: 373.900±316.045\n", ++ "Rollout 5526/9766, Reward: 262.270±24.190, Episode_length: 223.900±43.249\n", ++ "Rollout 5527/9766, Reward: 219.416±73.643, Episode_length: 506.700±371.056\n", ++ "Rollout 5528/9766, Reward: 258.589±17.465, Episode_length: 218.000±81.027\n", ++ "Rollout 5529/9766, Reward: 254.144±36.922, Episode_length: 281.800±112.297\n", ++ "Rollout 5530/9766, Reward: 271.256±16.397, Episode_length: 215.300±47.791\n", ++ "Rollout 5531/9766, Reward: 223.087±34.611, Episode_length: 246.400±68.466\n", ++ "Rollout 5532/9766, Reward: 224.425±59.741, Episode_length: 387.500±308.481\n", ++ "Rollout 5533/9766, Reward: 257.696±20.261, Episode_length: 231.200±52.226\n", ++ "Rollout 5534/9766, Reward: 208.565±75.808, Episode_length: 344.200±229.664\n", ++ "Rollout 5535/9766, Reward: 262.585±38.485, Episode_length: 246.000±75.607\n", ++ "Rollout 5536/9766, Reward: 266.431±37.238, Episode_length: 259.800±76.685\n", ++ "Rollout 5537/9766, Reward: 262.700±31.272, Episode_length: 215.200±60.821\n", ++ "Rollout 5538/9766, Reward: 251.100±43.532, Episode_length: 253.000±83.022\n", ++ "Rollout 5539/9766, Reward: 229.983±78.719, Episode_length: 300.600±237.248\n", ++ "Rollout 5540/9766, Reward: 237.829±36.062, Episode_length: 230.300±99.194\n", ++ "Rollout 5541/9766, Reward: 243.010±36.921, Episode_length: 323.500±232.608\n", ++ "Rollout 5542/9766, Reward: 239.567±44.728, Episode_length: 312.500±113.456\n", ++ "Rollout 5543/9766, Reward: 253.134±42.276, Episode_length: 223.700±51.328\n", ++ "Rollout 5544/9766, Reward: 233.654±37.953, Episode_length: 310.200±236.861\n", ++ "Rollout 5545/9766, Reward: 240.677±70.370, Episode_length: 219.600±76.000\n", ++ "Rollout 5546/9766, Reward: 245.863±45.356, Episode_length: 361.700±322.554\n", ++ "Rollout 5547/9766, Reward: 269.457±21.999, Episode_length: 239.700±84.777\n", ++ "Rollout 5548/9766, Reward: 245.308±31.199, Episode_length: 363.400±297.908\n", ++ "Rollout 5549/9766, Reward: 261.763±21.325, Episode_length: 207.400±58.532\n", ++ "Rollout 5550/9766, Reward: 273.500±14.235, Episode_length: 227.800±48.973\n", ++ "Rollout 5551/9766, Reward: 273.034±34.359, Episode_length: 228.000±79.071\n", ++ "Rollout 5552/9766, Reward: 270.581±15.300, Episode_length: 194.300±29.152\n", ++ "Rollout 5553/9766, Reward: 270.635±27.883, Episode_length: 203.700±39.268\n", ++ "Rollout 5554/9766, Reward: 252.934±46.013, Episode_length: 272.200±244.166\n", ++ "Rollout 5555/9766, Reward: 257.403±36.952, Episode_length: 226.000±79.457\n", ++ "Rollout 5556/9766, Reward: 256.645±20.593, Episode_length: 190.100±41.633\n", ++ "Rollout 5557/9766, Reward: 259.074±12.633, Episode_length: 192.300±24.216\n", ++ "Rollout 5558/9766, Reward: 259.284±20.187, Episode_length: 229.300±77.724\n", ++ "Rollout 5559/9766, Reward: 260.336±17.640, Episode_length: 182.800±22.986\n", ++ "Rollout 5560/9766, Reward: 271.346±21.271, Episode_length: 202.200±37.005\n", ++ "Rollout 5561/9766, Reward: 267.894±19.276, Episode_length: 197.800±23.769\n", ++ "Rollout 5562/9766, Reward: 239.822±35.390, Episode_length: 324.200±243.178\n", ++ "Rollout 5563/9766, Reward: 240.901±32.021, Episode_length: 230.500±77.099\n", ++ "Rollout 5564/9766, Reward: 254.197±19.365, Episode_length: 228.600±66.839\n", ++ "Rollout 5565/9766, Reward: 250.802±46.176, Episode_length: 310.800±207.603\n", ++ "Rollout 5566/9766, Reward: 269.454±35.275, Episode_length: 226.900±41.678\n", ++ "Rollout 5567/9766, Reward: 226.038±60.570, Episode_length: 396.700±309.698\n", ++ "Rollout 5568/9766, Reward: 230.583±51.546, Episode_length: 369.400±318.499\n", ++ "Rollout 5569/9766, Reward: 259.576±38.195, Episode_length: 232.900±67.475\n", ++ "Rollout 5570/9766, Reward: 230.242±74.395, Episode_length: 494.700±348.902\n", ++ "Rollout 5571/9766, Reward: 267.003±14.618, Episode_length: 258.500±218.632\n", ++ "Rollout 5572/9766, Reward: 273.673±20.649, Episode_length: 319.300±196.084\n", ++ "Rollout 5573/9766, Reward: 256.010±71.071, Episode_length: 201.500±36.819\n", ++ "Rollout 5574/9766, Reward: 275.804±42.379, Episode_length: 283.900±252.509\n", ++ "Rollout 5575/9766, Reward: 238.296±57.696, Episode_length: 420.400±380.182\n", ++ "Rollout 5576/9766, Reward: 266.866±36.895, Episode_length: 240.100±128.203\n", ++ "Rollout 5577/9766, Reward: 263.118±82.815, Episode_length: 188.600±42.751\n", ++ "Rollout 5578/9766, Reward: 262.419±40.781, Episode_length: 274.900±242.770\n", ++ "Rollout 5579/9766, Reward: 257.938±51.806, Episode_length: 351.000±324.978\n", ++ "Rollout 5580/9766, Reward: 287.168±23.698, Episode_length: 218.900±57.255\n", ++ "Rollout 5581/9766, Reward: 267.510±18.053, Episode_length: 191.000±69.315\n", ++ "Rollout 5582/9766, Reward: 276.065±20.610, Episode_length: 199.000±64.231\n", ++ "Rollout 5583/9766, Reward: 267.566±22.942, Episode_length: 177.300±14.086\n", ++ "Rollout 5584/9766, Reward: 275.352±15.088, Episode_length: 225.400±80.418\n", ++ "Rollout 5585/9766, Reward: 278.996±18.247, Episode_length: 228.300±58.347\n", ++ "Rollout 5586/9766, Reward: 282.566±19.842, Episode_length: 203.800±58.008\n", ++ "Rollout 5587/9766, Reward: 287.149±18.872, Episode_length: 208.300±77.044\n", ++ "Rollout 5588/9766, Reward: 284.268±26.392, Episode_length: 222.500±39.080\n", ++ "Rollout 5589/9766, Reward: 281.158±20.619, Episode_length: 196.800±26.442\n", ++ "Rollout 5590/9766, Reward: 280.410±19.656, Episode_length: 189.600±24.997\n", ++ "Rollout 5591/9766, Reward: 283.432±16.691, Episode_length: 198.000±17.567\n", ++ "Rollout 5592/9766, Reward: 268.130±31.168, Episode_length: 287.100±174.981\n", ++ "Rollout 5593/9766, Reward: 269.396±36.788, Episode_length: 263.800±246.207\n", ++ "Rollout 5594/9766, Reward: 285.852±20.532, Episode_length: 186.500±23.269\n", ++ "Rollout 5595/9766, Reward: 276.134±19.339, Episode_length: 256.700±202.202\n", ++ "Rollout 5596/9766, Reward: 281.125±19.098, Episode_length: 208.700±58.145\n", ++ "Rollout 5597/9766, Reward: 275.029±15.756, Episode_length: 181.100±30.025\n", ++ "Rollout 5598/9766, Reward: 264.499±38.307, Episode_length: 257.900±250.350\n", ++ "Rollout 5599/9766, Reward: 276.313±17.416, Episode_length: 175.500±36.568\n", ++ "Rollout 5600/9766, Reward: 293.082±13.038, Episode_length: 182.500±13.966\n", ++ "Rollout 5601/9766, Reward: 283.198±15.764, Episode_length: 196.700±37.768\n", ++ "Rollout 5602/9766, Reward: 283.099±17.732, Episode_length: 186.300±29.799\n", ++ "Rollout 5603/9766, Reward: 285.223±23.606, Episode_length: 231.400±136.124\n", ++ "Rollout 5604/9766, Reward: 279.535±15.006, Episode_length: 175.700±36.362\n", ++ "Rollout 5605/9766, Reward: 285.434±34.607, Episode_length: 274.700±244.170\n", ++ "Rollout 5606/9766, Reward: 263.763±35.878, Episode_length: 292.600±242.498\n", ++ "Rollout 5607/9766, Reward: 261.086±41.616, Episode_length: 343.900±329.433\n", ++ "Rollout 5608/9766, Reward: 276.672±15.492, Episode_length: 167.100±20.835\n", ++ "Rollout 5609/9766, Reward: 286.869±17.886, Episode_length: 178.300±31.264\n", ++ "Rollout 5610/9766, Reward: 290.189±13.393, Episode_length: 200.600±38.148\n", ++ "Rollout 5611/9766, Reward: 268.338±39.810, Episode_length: 255.000±249.639\n", ++ "Rollout 5612/9766, Reward: 269.388±47.226, Episode_length: 263.200±246.365\n", ++ "Rollout 5613/9766, Reward: 252.347±43.394, Episode_length: 352.000±324.153\n", ++ "Rollout 5614/9766, Reward: 284.004±14.552, Episode_length: 212.800±39.329\n", ++ "Rollout 5615/9766, Reward: 275.606±41.984, Episode_length: 296.900±239.008\n", ++ "Rollout 5616/9766, Reward: 277.893±12.871, Episode_length: 187.800±21.526\n", ++ "Rollout 5617/9766, Reward: 281.274±16.448, Episode_length: 188.900±26.323\n", ++ "Rollout 5618/9766, Reward: 264.903±41.656, Episode_length: 268.800±244.815\n", ++ "Rollout 5619/9766, Reward: 264.554±36.155, Episode_length: 277.100±243.240\n", ++ "Rollout 5620/9766, Reward: 274.904±22.453, Episode_length: 204.000±46.400\n", ++ "Rollout 5621/9766, Reward: 278.988±20.553, Episode_length: 197.400±24.889\n", ++ "Rollout 5622/9766, Reward: 266.586±26.926, Episode_length: 205.500±55.565\n", ++ "Rollout 5623/9766, Reward: 279.649±32.984, Episode_length: 282.500±239.629\n", ++ "Rollout 5624/9766, Reward: 270.028±23.048, Episode_length: 206.700±71.892\n", ++ "Rollout 5625/9766, Reward: 271.158±17.040, Episode_length: 256.900±150.916\n", ++ "Rollout 5626/9766, Reward: 281.348±16.513, Episode_length: 194.400±28.883\n", ++ "Rollout 5627/9766, Reward: 280.948±14.382, Episode_length: 192.000±27.810\n", ++ "Rollout 5628/9766, Reward: 275.094±9.472, Episode_length: 172.600±19.489\n", ++ "Rollout 5629/9766, Reward: 278.400±14.378, Episode_length: 194.900±18.844\n", ++ "Rollout 5630/9766, Reward: 282.958±18.212, Episode_length: 192.400±22.936\n", ++ "Rollout 5631/9766, Reward: 282.711±17.999, Episode_length: 190.500±28.097\n", ++ "Rollout 5632/9766, Reward: 281.088±31.016, Episode_length: 203.700±66.581\n", ++ "Rollout 5633/9766, Reward: 288.417±19.675, Episode_length: 193.300±22.150\n", ++ "Rollout 5634/9766, Reward: 277.797±35.859, Episode_length: 203.000±36.884\n", ++ "Rollout 5635/9766, Reward: 284.157±18.616, Episode_length: 186.300±19.990\n", ++ "Rollout 5636/9766, Reward: 286.290±19.948, Episode_length: 193.000±18.127\n", ++ "Rollout 5637/9766, Reward: 272.743±21.100, Episode_length: 202.900±51.003\n", ++ "Rollout 5638/9766, Reward: 282.208±22.485, Episode_length: 184.900±18.603\n", ++ "Rollout 5639/9766, Reward: 274.085±15.848, Episode_length: 200.100±61.225\n", ++ "Rollout 5640/9766, Reward: 287.753±13.061, Episode_length: 207.600±21.063\n", ++ "Rollout 5641/9766, Reward: 272.434±20.575, Episode_length: 190.600±24.393\n", ++ "Rollout 5642/9766, Reward: 267.327±35.453, Episode_length: 209.000±55.746\n", ++ "Rollout 5643/9766, Reward: 280.373±20.963, Episode_length: 196.900±18.124\n", ++ "Rollout 5644/9766, Reward: 258.851±21.609, Episode_length: 199.300±54.719\n", ++ "Rollout 5645/9766, Reward: 279.285±20.991, Episode_length: 181.800±16.036\n", ++ "Rollout 5646/9766, Reward: 274.850±9.154, Episode_length: 184.700±17.321\n", ++ "Rollout 5647/9766, Reward: 272.304±31.128, Episode_length: 228.900±115.016\n", ++ "Rollout 5648/9766, Reward: 275.214±24.110, Episode_length: 186.800±26.351\n", ++ "Rollout 5649/9766, Reward: 283.706±12.675, Episode_length: 205.000±53.863\n", ++ "Rollout 5650/9766, Reward: 274.457±11.369, Episode_length: 183.400±22.566\n", ++ "Rollout 5651/9766, Reward: 254.893±18.516, Episode_length: 220.900±103.628\n", ++ "Rollout 5652/9766, Reward: 268.830±20.032, Episode_length: 213.600±78.176\n", ++ "Rollout 5653/9766, Reward: 274.233±24.982, Episode_length: 202.900±46.619\n", ++ "Rollout 5654/9766, Reward: 282.172±21.641, Episode_length: 187.600±31.484\n", ++ "Rollout 5655/9766, Reward: 281.469±19.663, Episode_length: 196.200±17.921\n", ++ "Rollout 5656/9766, Reward: 267.841±41.114, Episode_length: 198.300±88.617\n", ++ "Rollout 5657/9766, Reward: 279.107±22.916, Episode_length: 191.200±25.392\n", ++ "Rollout 5658/9766, Reward: 289.959±12.767, Episode_length: 182.000±28.531\n", ++ "Rollout 5659/9766, Reward: 261.786±49.275, Episode_length: 323.500±304.542\n", ++ "Rollout 5660/9766, Reward: 274.553±15.621, Episode_length: 206.100±132.426\n", ++ "Rollout 5661/9766, Reward: 275.005±21.579, Episode_length: 281.800±228.122\n", ++ "Rollout 5662/9766, Reward: 264.832±35.870, Episode_length: 262.900±246.245\n", ++ "Rollout 5663/9766, Reward: 280.716±36.748, Episode_length: 250.100±250.423\n", ++ "Rollout 5664/9766, Reward: 276.069±41.996, Episode_length: 259.400±247.485\n", ++ "Rollout 5665/9766, Reward: 286.186±14.730, Episode_length: 177.400±24.447\n", ++ "Rollout 5666/9766, Reward: 283.563±19.408, Episode_length: 180.000±24.298\n", ++ "Rollout 5667/9766, Reward: 283.482±21.683, Episode_length: 172.100±17.143\n", ++ "Rollout 5668/9766, Reward: 280.374±18.294, Episode_length: 189.300±32.552\n", ++ "Rollout 5669/9766, Reward: 282.892±15.432, Episode_length: 172.200±22.072\n", ++ "Rollout 5670/9766, Reward: 287.322±12.156, Episode_length: 173.800±22.121\n", ++ "Rollout 5671/9766, Reward: 288.897±14.370, Episode_length: 174.800±20.158\n", ++ "Rollout 5672/9766, Reward: 278.199±21.651, Episode_length: 238.500±190.174\n", ++ "Rollout 5673/9766, Reward: 293.847±13.690, Episode_length: 176.300±19.396\n", ++ "Rollout 5674/9766, Reward: 284.841±18.405, Episode_length: 209.200±70.559\n", ++ "Rollout 5675/9766, Reward: 285.275±12.112, Episode_length: 184.800±54.146\n", ++ "Rollout 5676/9766, Reward: 284.487±15.544, Episode_length: 183.400±32.632\n", ++ "Rollout 5677/9766, Reward: 275.537±20.861, Episode_length: 198.200±35.059\n", ++ "Rollout 5678/9766, Reward: 290.570��19.207, Episode_length: 185.000±23.095\n", ++ "Rollout 5679/9766, Reward: 271.480±16.127, Episode_length: 171.400±27.897\n", ++ "Rollout 5680/9766, Reward: 285.397±16.689, Episode_length: 178.100±17.897\n", ++ "Rollout 5681/9766, Reward: 281.821±15.698, Episode_length: 192.700±47.346\n", ++ "Rollout 5682/9766, Reward: 289.437±16.035, Episode_length: 177.700±14.581\n", ++ "Rollout 5683/9766, Reward: 282.746±17.239, Episode_length: 204.200±118.721\n", ++ "Rollout 5684/9766, Reward: 288.269±12.272, Episode_length: 180.400±27.292\n", ++ "Rollout 5685/9766, Reward: 278.131±21.131, Episode_length: 226.700±166.255\n", ++ "Rollout 5686/9766, Reward: 286.843±20.267, Episode_length: 218.800±82.720\n", ++ "Rollout 5687/9766, Reward: 286.772±18.589, Episode_length: 164.400±21.120\n", ++ "Rollout 5688/9766, Reward: 288.899±12.859, Episode_length: 183.600±29.021\n", ++ "Rollout 5689/9766, Reward: 290.284±16.343, Episode_length: 188.300±34.630\n", ++ "Rollout 5690/9766, Reward: 290.390±19.475, Episode_length: 171.900±22.111\n", ++ "Rollout 5691/9766, Reward: 293.118±13.678, Episode_length: 193.400±12.555\n", ++ "Rollout 5692/9766, Reward: 300.830±14.455, Episode_length: 177.300±25.405\n", ++ "Rollout 5693/9766, Reward: 263.823±85.971, Episode_length: 161.000±29.370\n", ++ "Rollout 5694/9766, Reward: 285.186±8.884, Episode_length: 164.300±22.253\n", ++ "Rollout 5695/9766, Reward: 290.232±14.977, Episode_length: 171.300±17.624\n", ++ "Rollout 5696/9766, Reward: 296.023±15.376, Episode_length: 185.500±23.114\n", ++ "Rollout 5697/9766, Reward: 277.197±19.318, Episode_length: 191.600±65.888\n", ++ "Rollout 5698/9766, Reward: 292.148±16.677, Episode_length: 169.800±23.937\n", ++ "Rollout 5699/9766, Reward: 258.988±80.942, Episode_length: 166.200±31.993\n", ++ "Rollout 5700/9766, Reward: 277.633±18.864, Episode_length: 210.700±91.498\n", ++ "Rollout 5701/9766, Reward: 260.049±73.323, Episode_length: 163.200±28.565\n", ++ "Rollout 5702/9766, Reward: 275.634±13.905, Episode_length: 177.900±18.944\n", ++ "Rollout 5703/9766, Reward: 267.115±36.658, Episode_length: 265.000±246.780\n", ++ "Rollout 5704/9766, Reward: 277.849±18.246, Episode_length: 166.400±17.545\n", ++ "Rollout 5705/9766, Reward: 281.127±16.076, Episode_length: 186.200±28.882\n", ++ "Rollout 5706/9766, Reward: 288.321±16.226, Episode_length: 178.100±21.380\n", ++ "Rollout 5707/9766, Reward: 282.575±13.882, Episode_length: 241.600±210.306\n", ++ "Rollout 5708/9766, Reward: 289.601±19.678, Episode_length: 177.200±30.944\n", ++ "Rollout 5709/9766, Reward: 290.412±14.658, Episode_length: 171.100±22.501\n", ++ "Rollout 5710/9766, Reward: 285.671±13.246, Episode_length: 258.000±243.793\n", ++ "Rollout 5711/9766, Reward: 275.899±29.747, Episode_length: 263.700±245.780\n", ++ "Rollout 5712/9766, Reward: 275.304±43.478, Episode_length: 245.100±251.937\n", ++ "Rollout 5713/9766, Reward: 290.143±16.297, Episode_length: 178.100±28.877\n", ++ "Rollout 5714/9766, Reward: 259.943±87.217, Episode_length: 170.700±35.160\n", ++ "Rollout 5715/9766, Reward: 285.215±16.993, Episode_length: 176.500±16.070\n", ++ "Rollout 5716/9766, Reward: 283.202±38.112, Episode_length: 260.900±247.233\n", ++ "Rollout 5717/9766, Reward: 279.400±17.116, Episode_length: 172.000±32.921\n", ++ "Rollout 5718/9766, Reward: 251.222±79.816, Episode_length: 156.900±30.392\n", ++ "Rollout 5719/9766, Reward: 261.880±79.720, Episode_length: 172.200±36.734\n", ++ "Rollout 5720/9766, Reward: 265.349±80.025, Episode_length: 175.600±39.256\n", ++ "Rollout 5721/9766, Reward: 291.011±17.038, Episode_length: 176.700±26.919\n", ++ "Rollout 5722/9766, Reward: 282.601±16.643, Episode_length: 162.700±17.777\n", ++ "Rollout 5723/9766, Reward: 279.923±14.822, Episode_length: 176.800±17.826\n", ++ "Rollout 5724/9766, Reward: 297.670±15.749, Episode_length: 189.500±28.811\n", ++ "Rollout 5725/9766, Reward: 282.929±12.799, Episode_length: 167.800±22.868\n", ++ "Rollout 5726/9766, Reward: 280.532±17.730, Episode_length: 171.000±18.472\n", ++ "Rollout 5727/9766, Reward: 288.351±18.806, Episode_length: 178.400±20.412\n", ++ "Rollout 5728/9766, Reward: 277.213±20.478, Episode_length: 173.800±35.431\n", ++ "Rollout 5729/9766, Reward: 277.824±18.017, Episode_length: 234.400±185.124\n", ++ "Rollout 5730/9766, Reward: 292.525±16.434, Episode_length: 184.000±22.307\n", ++ "Rollout 5731/9766, Reward: 281.866±39.268, Episode_length: 263.500±245.675\n", ++ "Rollout 5732/9766, Reward: 281.569±8.029, Episode_length: 250.100±212.717\n", ++ "Rollout 5733/9766, Reward: 280.180±14.101, Episode_length: 168.000±14.629\n", ++ "Rollout 5734/9766, Reward: 287.415±10.615, Episode_length: 244.100±142.858\n", ++ "Rollout 5735/9766, Reward: 290.565±21.402, Episode_length: 174.100±10.986\n", ++ "Rollout 5736/9766, Reward: 292.479±16.835, Episode_length: 184.400±14.589\n", ++ "Rollout 5737/9766, Reward: 275.643±18.466, Episode_length: 164.600±17.188\n", ++ "Rollout 5738/9766, Reward: 287.457±14.299, Episode_length: 167.200±24.766\n", ++ "Rollout 5739/9766, Reward: 254.115±86.395, Episode_length: 156.700±30.057\n", ++ "Rollout 5740/9766, Reward: 271.363±41.613, Episode_length: 259.800±247.706\n", ++ "Rollout 5741/9766, Reward: 256.398±81.107, Episode_length: 175.300±31.544\n", ++ "Rollout 5742/9766, Reward: 286.482±13.763, Episode_length: 187.100±13.953\n", ++ "Rollout 5743/9766, Reward: 282.480±13.907, Episode_length: 169.100±15.814\n", ++ "Rollout 5744/9766, Reward: 281.767±14.428, Episode_length: 180.800±38.579\n", ++ "Rollout 5745/9766, Reward: 289.431±13.476, Episode_length: 170.700±20.981\n", ++ "Rollout 5746/9766, Reward: 285.909±8.283, Episode_length: 174.400±17.912\n", ++ "Rollout 5747/9766, Reward: 283.337±13.124, Episode_length: 244.100±231.591\n", ++ "Rollout 5748/9766, Reward: 258.166±84.311, Episode_length: 161.900±28.012\n", ++ "Rollout 5749/9766, Reward: 280.367±37.957, Episode_length: 259.000±247.413\n", ++ "Rollout 5750/9766, Reward: 290.010±15.332, Episode_length: 223.100±159.906\n", ++ "Rollout 5751/9766, Reward: 273.253±37.250, Episode_length: 453.100±346.878\n", ++ "Rollout 5752/9766, Reward: 279.992±10.023, Episode_length: 169.000±13.266\n", ++ "Rollout 5753/9766, Reward: 276.612±14.292, Episode_length: 188.800±44.743\n", ++ "Rollout 5754/9766, Reward: 277.853±36.573, Episode_length: 445.400±315.159\n", ++ "Rollout 5755/9766, Reward: 285.975±19.941, Episode_length: 258.200±185.606\n", ++ "Rollout 5756/9766, Reward: 253.989±88.249, Episode_length: 236.200±203.962\n", ++ "Rollout 5757/9766, Reward: 290.587±17.411, Episode_length: 183.500±14.030\n", ++ "Rollout 5758/9766, Reward: 271.439±37.564, Episode_length: 260.100±247.055\n", ++ "Rollout 5759/9766, Reward: 289.558±14.128, Episode_length: 173.300±19.131\n", ++ "Rollout 5760/9766, Reward: 282.915±18.828, Episode_length: 167.900±14.356\n", ++ "Rollout 5761/9766, Reward: 289.086±12.977, Episode_length: 188.200±19.964\n", ++ "Rollout 5762/9766, Reward: 287.677±19.984, Episode_length: 194.000±45.091\n", ++ "Rollout 5763/9766, Reward: 290.552±18.765, Episode_length: 179.500±15.383\n", ++ "Rollout 5764/9766, Reward: 278.505±17.426, Episode_length: 172.700±15.159\n", ++ "Rollout 5765/9766, Reward: 278.447±14.502, Episode_length: 201.500±39.131\n", ++ "Rollout 5766/9766, Reward: 283.391±16.301, Episode_length: 180.400±21.850\n", ++ "Rollout 5767/9766, Reward: 287.782±9.133, Episode_length: 181.600±13.973\n", ++ "Rollout 5768/9766, Reward: 293.061±16.103, Episode_length: 192.900±17.172\n", ++ "Rollout 5769/9766, Reward: 299.416±10.827, Episode_length: 186.200±21.156\n", ++ "Rollout 5770/9766, Reward: 282.468±14.353, Episode_length: 172.100±13.946\n", ++ "Rollout 5771/9766, Reward: 288.887±18.040, Episode_length: 182.200±19.702\n", ++ "Rollout 5772/9766, Reward: 283.422±33.939, Episode_length: 266.600±245.260\n", ++ "Rollout 5773/9766, Reward: 278.693±12.067, Episode_length: 174.100±15.241\n", ++ "Rollout 5774/9766, Reward: 284.248±18.927, Episode_length: 200.700±55.954\n", ++ "Rollout 5775/9766, Reward: 293.868±17.809, Episode_length: 198.100±45.593\n", ++ "Rollout 5776/9766, Reward: 284.127±17.855, Episode_length: 179.700±17.487\n", ++ "Rollout 5777/9766, Reward: 275.391±19.329, Episode_length: 173.600±13.215\n", ++ "Rollout 5778/9766, Reward: 292.684±20.074, Episode_length: 195.100±21.700\n", ++ "Rollout 5779/9766, Reward: 288.394±17.279, Episode_length: 184.500±25.053\n", ++ "Rollout 5780/9766, Reward: 279.378±20.977, Episode_length: 191.900±44.751\n", ++ "Rollout 5781/9766, Reward: 276.261±37.828, Episode_length: 255.800±249.129\n", ++ "Rollout 5782/9766, Reward: 294.044±13.072, Episode_length: 177.300±18.612\n", ++ "Rollout 5783/9766, Reward: 290.738±18.293, Episode_length: 203.500±90.320\n", ++ "Rollout 5784/9766, Reward: 287.130±14.231, Episode_length: 217.400±99.431\n", ++ "Rollout 5785/9766, Reward: 270.403±37.879, Episode_length: 309.800±276.096\n", ++ "Rollout 5786/9766, Reward: 275.594±42.676, Episode_length: 339.300±330.543\n", ++ "Rollout 5787/9766, Reward: 261.798±41.173, Episode_length: 394.600±345.631\n", ++ "Rollout 5788/9766, Reward: 287.444±26.043, Episode_length: 210.000±68.046\n", ++ "Rollout 5789/9766, Reward: 276.652±17.070, Episode_length: 155.400±8.991\n", ++ "Rollout 5790/9766, Reward: 293.475±14.441, Episode_length: 185.400±44.143\n", ++ "Rollout 5791/9766, Reward: 246.267±53.241, Episode_length: 657.100±389.064\n", ++ "Rollout 5792/9766, Reward: 215.722±64.124, Episode_length: 709.300±368.901\n", ++ "Rollout 5793/9766, Reward: 283.980±15.717, Episode_length: 171.100±20.157\n", ++ "Rollout 5794/9766, Reward: 278.171±16.129, Episode_length: 203.100±86.707\n", ++ "Rollout 5795/9766, Reward: 268.277±39.927, Episode_length: 248.400±251.096\n", ++ "Rollout 5796/9766, Reward: 256.993±44.762, Episode_length: 407.700±361.468\n", ++ "Rollout 5797/9766, Reward: 283.460±35.482, Episode_length: 258.700±247.966\n", ++ "Rollout 5798/9766, Reward: 281.491±18.213, Episode_length: 172.000±11.463\n", ++ "Rollout 5799/9766, Reward: 287.456±14.696, Episode_length: 199.700±68.912\n", ++ "Rollout 5800/9766, Reward: 167.541±34.239, Episode_length: 998.500±4.500\n", ++ "Rollout 5801/9766, Reward: 169.615±30.389, Episode_length: 989.200±32.400\n", ++ "Rollout 5802/9766, Reward: 259.129±41.030, Episode_length: 500.100±355.745\n", ++ "Rollout 5803/9766, Reward: 195.120±43.729, Episode_length: 906.900±251.941\n", ++ "Rollout 5804/9766, Reward: 287.130±11.166, Episode_length: 265.500±247.509\n", ++ "Rollout 5805/9766, Reward: 290.576±12.502, Episode_length: 312.600±296.208\n", ++ "Rollout 5806/9766, Reward: 287.136±16.686, Episode_length: 177.000±29.870\n", ++ "Rollout 5807/9766, Reward: 291.967±13.974, Episode_length: 175.100±12.070\n", ++ "Rollout 5808/9766, Reward: 276.032±16.839, Episode_length: 170.500±12.010\n", ++ "Rollout 5809/9766, Reward: 294.168±18.799, Episode_length: 179.000±23.677\n", ++ "Rollout 5810/9766, Reward: 281.879±23.016, Episode_length: 175.600±20.819\n", ++ "Rollout 5811/9766, Reward: 286.413±18.641, Episode_length: 173.700±21.717\n", ++ "Rollout 5812/9766, Reward: 246.844±97.823, Episode_length: 160.600±21.648\n", ++ "Rollout 5813/9766, Reward: 297.521±18.355, Episode_length: 190.600±23.707\n", ++ "Rollout 5814/9766, Reward: 280.556±18.477, Episode_length: 179.800±46.054\n", ++ "Rollout 5815/9766, Reward: 290.634±14.471, Episode_length: 176.100±8.596\n", ++ "Rollout 5816/9766, Reward: 287.776±18.024, Episode_length: 174.400±24.561\n", ++ "Rollout 5817/9766, Reward: 288.428±19.116, Episode_length: 178.500±20.723\n", ++ "Rollout 5818/9766, Reward: 286.030±13.302, Episode_length: 189.900±45.763\n", ++ "Rollout 5819/9766, Reward: 286.037±19.034, Episode_length: 170.600±15.467\n", ++ "Rollout 5820/9766, Reward: 270.677±36.545, Episode_length: 251.900±250.334\n", ++ "Rollout 5821/9766, Reward: 295.428±16.365, Episode_length: 182.600±18.624\n", ++ "Rollout 5822/9766, Reward: 272.886±45.436, Episode_length: 344.600±328.860\n", ++ "Rollout 5823/9766, Reward: 194.450±41.531, Episode_length: 905.600±249.288\n", ++ "Rollout 5824/9766, Reward: 284.450±16.685, Episode_length: 164.200±25.455\n", ++ "Rollout 5825/9766, Reward: 301.209±18.095, Episode_length: 177.900±21.988\n", ++ "Rollout 5826/9766, Reward: 292.329±12.272, Episode_length: 180.400±21.588\n", ++ "Rollout 5827/9766, Reward: 289.293±19.281, Episode_length: 171.400±19.719\n", ++ "Rollout 5828/9766, Reward: 271.268±49.583, Episode_length: 255.600±248.555\n", ++ "Rollout 5829/9766, Reward: 284.499±38.822, Episode_length: 280.000±240.826\n", ++ "Rollout 5830/9766, Reward: 284.562±17.443, Episode_length: 162.200±13.541\n", ++ "Rollout 5831/9766, Reward: 268.832±53.798, Episode_length: 338.000±331.623\n", ++ "Rollout 5832/9766, Reward: 279.591±16.733, Episode_length: 209.700±131.251\n", ++ "Rollout 5833/9766, Reward: 282.205±10.122, Episode_length: 167.800±16.958\n", ++ "Rollout 5834/9766, Reward: 288.442±15.531, Episode_length: 174.500±24.752\n", ++ "Rollout 5835/9766, Reward: 272.881±34.461, Episode_length: 252.600±249.916\n", ++ "Rollout 5836/9766, Reward: 291.656±15.823, Episode_length: 181.000±27.612\n", ++ "Rollout 5837/9766, Reward: 285.413±14.972, Episode_length: 172.100±17.346\n", ++ "Rollout 5838/9766, Reward: 268.057±42.384, Episode_length: 257.600±248.718\n", ++ "Rollout 5839/9766, Reward: 289.225±14.675, Episode_length: 179.300±26.477\n", ++ "Rollout 5840/9766, Reward: 295.975±14.565, Episode_length: 195.200±30.961\n", ++ "Rollout 5841/9766, Reward: 275.738±36.941, Episode_length: 261.600±246.609\n", ++ "Rollout 5842/9766, Reward: 287.899±15.269, Episode_length: 180.000±27.499\n", ++ "Rollout 5843/9766, Reward: 275.794±12.910, Episode_length: 232.500±167.866\n", ++ "Rollout 5844/9766, Reward: 276.445±51.443, Episode_length: 271.700±243.019\n", ++ "Rollout 5845/9766, Reward: 285.496±18.891, Episode_length: 184.000±16.062\n", ++ "Rollout 5846/9766, Reward: 268.544±18.226, Episode_length: 348.300±196.252\n", ++ "Rollout 5847/9766, Reward: 252.957±41.408, Episode_length: 441.100±216.557\n", ++ "Rollout 5848/9766, Reward: 242.041±47.195, Episode_length: 425.000±320.083\n", ++ "Rollout 5849/9766, Reward: 261.047±48.088, Episode_length: 279.300±247.106\n", ++ "Rollout 5850/9766, Reward: 275.601±22.892, Episode_length: 265.600±173.239\n", ++ "Rollout 5851/9766, Reward: 267.906±45.637, Episode_length: 324.100±277.376\n", ++ "Rollout 5852/9766, Reward: 283.493±21.520, Episode_length: 229.000±164.628\n", ++ "Rollout 5853/9766, Reward: 281.902±18.049, Episode_length: 176.600±15.160\n", ++ "Rollout 5854/9766, Reward: 272.904±47.235, Episode_length: 268.500±244.881\n", ++ "Rollout 5855/9766, Reward: 282.676±24.041, Episode_length: 227.700±102.638\n", ++ "Rollout 5856/9766, Reward: 253.962±51.228, Episode_length: 325.700±239.125\n", ++ "Rollout 5857/9766, Reward: 238.823±31.958, Episode_length: 307.400±106.740\n", ++ "Rollout 5858/9766, Reward: 246.016±37.921, Episode_length: 332.400±183.205\n", ++ "Rollout 5859/9766, Reward: 152.042±205.137, Episode_length: 472.500±228.024\n", ++ "Rollout 5860/9766, Reward: 208.529±61.948, Episode_length: 462.100±355.384\n", ++ "Rollout 5861/9766, Reward: 236.088±13.695, Episode_length: 313.800±72.346\n", ++ "Rollout 5862/9766, Reward: 219.900±58.914, Episode_length: 408.100±316.213\n", ++ "Rollout 5863/9766, Reward: 232.316±60.110, Episode_length: 328.200±266.141\n", ++ "Rollout 5864/9766, Reward: 190.372±145.683, Episode_length: 268.600±63.627\n", ++ "Rollout 5865/9766, Reward: 200.436±44.996, Episode_length: 496.300±335.205\n", ++ "Rollout 5866/9766, Reward: 222.027±56.875, Episode_length: 470.600±353.660\n", ++ "Rollout 5867/9766, Reward: 192.123±63.365, Episode_length: 354.400±243.819\n", ++ "Rollout 5868/9766, Reward: 192.230±69.422, Episode_length: 466.600±356.840\n", ++ "Rollout 5869/9766, Reward: 229.452±28.715, Episode_length: 346.100±221.694\n", ++ "Rollout 5870/9766, Reward: 224.316±48.340, Episode_length: 395.100±264.169\n", ++ "Rollout 5871/9766, Reward: 232.398±33.972, Episode_length: 333.800±256.797\n", ++ "Rollout 5872/9766, Reward: 234.243±43.197, Episode_length: 410.500±237.087\n", ++ "Rollout 5873/9766, Reward: 208.578±60.610, Episode_length: 548.300±308.709\n", ++ "Rollout 5874/9766, Reward: 217.980±56.932, Episode_length: 406.400±270.063\n", ++ "Rollout 5875/9766, Reward: 233.507±32.933, Episode_length: 283.600±130.048\n", ++ "Rollout 5876/9766, Reward: 232.015±42.137, Episode_length: 561.000±180.006\n", ++ "Rollout 5877/9766, Reward: 234.918±55.850, Episode_length: 373.800±319.092\n", ++ "Rollout 5878/9766, Reward: 250.197±56.257, Episode_length: 321.600±256.463\n", ++ "Rollout 5879/9766, Reward: 206.511±45.162, Episode_length: 500.300±306.810\n", ++ "Rollout 5880/9766, Reward: 252.430±45.552, Episode_length: 458.000±354.433\n", ++ "Rollout 5881/9766, Reward: 237.130±58.257, Episode_length: 392.800±308.454\n", ++ "Rollout 5882/9766, Reward: 256.949±55.582, Episode_length: 268.800±245.070\n", ++ "Rollout 5883/9766, Reward: 237.511±54.402, Episode_length: 435.400±370.278\n", ++ "Rollout 5884/9766, Reward: 255.657±47.355, Episode_length: 325.800±291.583\n", ++ "Rollout 5885/9766, Reward: 243.693±50.251, Episode_length: 364.900±318.453\n", ++ "Rollout 5886/9766, Reward: 246.868±54.878, Episode_length: 407.800±332.161\n", ++ "Rollout 5887/9766, Reward: 235.072±69.509, Episode_length: 435.700±370.488\n", ++ "Rollout 5888/9766, Reward: 228.657±63.840, Episode_length: 425.000±343.659\n", ++ "Rollout 5889/9766, Reward: 235.149±79.044, Episode_length: 438.900±368.014\n", ++ "Rollout 5890/9766, Reward: 231.478±62.087, Episode_length: 484.900±366.369\n", ++ "Rollout 5891/9766, Reward: 248.274±53.473, Episode_length: 338.600±277.538\n", ++ "Rollout 5892/9766, Reward: 248.879±45.985, Episode_length: 299.800±260.945\n", ++ "Rollout 5893/9766, Reward: 274.383±19.550, Episode_length: 215.900±80.289\n", ++ "Rollout 5894/9766, Reward: 261.638±47.151, Episode_length: 244.400±114.744\n", ++ "Rollout 5895/9766, Reward: 270.063±38.790, Episode_length: 229.600±80.599\n", ++ "Rollout 5896/9766, Reward: 238.943±73.963, Episode_length: 241.000±253.953\n", ++ "Rollout 5897/9766, Reward: 264.108±20.873, Episode_length: 189.800±37.421\n", ++ "Rollout 5898/9766, Reward: 278.342±20.728, Episode_length: 187.100±28.243\n", ++ "Rollout 5899/9766, Reward: 260.963±24.598, Episode_length: 197.200±47.797\n", ++ "Rollout 5900/9766, Reward: 282.350±9.038, Episode_length: 168.300±18.719\n", ++ "Rollout 5901/9766, Reward: 246.402±87.546, Episode_length: 267.500±245.843\n", ++ "Rollout 5902/9766, Reward: 279.326±17.019, Episode_length: 180.800±20.745\n", ++ "Rollout 5903/9766, Reward: 280.087±21.745, Episode_length: 180.000±26.180\n", ++ "Rollout 5904/9766, Reward: 259.912±35.235, Episode_length: 375.600±335.379\n", ++ "Rollout 5905/9766, Reward: 267.922±51.529, Episode_length: 257.000±248.278\n", ++ "Rollout 5906/9766, Reward: 282.996±16.808, Episode_length: 212.800±79.409\n", ++ "Rollout 5907/9766, Reward: 288.139±17.045, Episode_length: 181.100±30.346\n", ++ "Rollout 5908/9766, Reward: 277.173±20.615, Episode_length: 254.700±227.796\n", ++ "Rollout 5909/9766, Reward: 191.086±25.909, Episode_length: 925.400±187.791\n", ++ "Rollout 5910/9766, Reward: 265.336±33.268, Episode_length: 262.000±246.689\n", ++ "Rollout 5911/9766, Reward: 274.189±24.571, Episode_length: 218.000±55.735\n", ++ "Rollout 5912/9766, Reward: 263.857±22.821, Episode_length: 203.600±27.262\n", ++ "Rollout 5913/9766, Reward: 255.181±34.677, Episode_length: 321.800±237.422\n", ++ "Rollout 5914/9766, Reward: 272.810±15.354, Episode_length: 185.300±27.619\n", ++ "Rollout 5915/9766, Reward: 263.002±45.111, Episode_length: 327.800±243.070\n", ++ "Rollout 5916/9766, Reward: 263.833±27.977, Episode_length: 258.000±67.854\n", ++ "Rollout 5917/9766, Reward: 260.440±47.316, Episode_length: 267.000±245.508\n", ++ "Rollout 5918/9766, Reward: 234.300±63.974, Episode_length: 389.600±324.180\n", ++ "Rollout 5919/9766, Reward: 262.605±16.349, Episode_length: 218.000±113.624\n", ++ "Rollout 5920/9766, Reward: 262.417±35.843, Episode_length: 242.600±90.500\n", ++ "Rollout 5921/9766, Reward: 281.197±13.016, Episode_length: 186.200±14.048\n", ++ "Rollout 5922/9766, Reward: 254.249±61.585, Episode_length: 287.100±243.397\n", ++ "Rollout 5923/9766, Reward: 271.748±18.168, Episode_length: 181.900±24.655\n", ++ "Rollout 5924/9766, Reward: 254.501±78.768, Episode_length: 204.600±65.335\n", ++ "Rollout 5925/9766, Reward: 282.153±7.660, Episode_length: 185.400±17.066\n", ++ "Rollout 5926/9766, Reward: 283.092±14.495, Episode_length: 180.300±30.033\n", ++ "Rollout 5927/9766, Reward: 285.286±14.118, Episode_length: 178.600±22.227\n", ++ "Rollout 5928/9766, Reward: 259.450±64.520, Episode_length: 188.900±32.188\n", ++ "Rollout 5929/9766, Reward: 268.152±70.557, Episode_length: 179.900±32.950\n", ++ "Rollout 5930/9766, Reward: 250.240±65.055, Episode_length: 192.500±74.948\n", ++ "Rollout 5931/9766, Reward: 284.410±15.173, Episode_length: 189.800±12.568\n", ++ "Rollout 5932/9766, Reward: 270.029±33.016, Episode_length: 272.400±243.174\n", ++ "Rollout 5933/9766, Reward: 268.383±32.813, Episode_length: 203.100±76.842\n", ++ "Rollout 5934/9766, Reward: 290.510±15.418, Episode_length: 260.200±207.574\n", ++ "Rollout 5935/9766, Reward: 205.347±202.091, Episode_length: 184.700±22.830\n", ++ "Rollout 5936/9766, Reward: 240.799±88.726, Episode_length: 162.400±33.076\n", ++ "Rollout 5937/9766, Reward: 253.488±54.014, Episode_length: 418.900±338.454\n", ++ "Rollout 5938/9766, Reward: 247.996±70.499, Episode_length: 227.100±107.955\n", ++ "Rollout 5939/9766, Reward: 267.195±10.384, Episode_length: 251.600±125.166\n", ++ "Rollout 5940/9766, Reward: 246.043±73.074, Episode_length: 324.300±312.977\n", ++ "Rollout 5941/9766, Reward: 253.113±51.186, Episode_length: 419.200±362.112\n", ++ "Rollout 5942/9766, Reward: 271.790±49.249, Episode_length: 413.500±327.675\n", ++ "Rollout 5943/9766, Reward: 272.591±17.546, Episode_length: 170.200±40.775\n", ++ "Rollout 5944/9766, Reward: 248.754±62.116, Episode_length: 490.000±349.836\n", ++ "Rollout 5945/9766, Reward: 274.719±38.834, Episode_length: 361.400±314.858\n", ++ "Rollout 5946/9766, Reward: 271.724±43.487, Episode_length: 261.800±248.031\n", ++ "Rollout 5947/9766, Reward: 276.044±34.388, Episode_length: 251.400±250.274\n", ++ "Rollout 5948/9766, Reward: 272.271±34.803, Episode_length: 247.200±251.596\n", ++ "Rollout 5949/9766, Reward: 287.377±13.194, Episode_length: 245.800±211.726\n", ++ "Rollout 5950/9766, Reward: 265.285±31.499, Episode_length: 321.600±300.144\n", ++ "Rollout 5951/9766, Reward: 274.889±34.035, Episode_length: 287.500±257.232\n", ++ "Rollout 5952/9766, Reward: 270.458±43.431, Episode_length: 342.900±329.697\n", ++ "Rollout 5953/9766, Reward: 253.372±52.699, Episode_length: 336.300±332.670\n", ++ "Rollout 5954/9766, Reward: 263.873±41.956, Episode_length: 332.500±331.633\n", ++ "Rollout 5955/9766, Reward: 288.495±8.861, Episode_length: 178.400±19.840\n", ++ "Rollout 5956/9766, Reward: 230.360±55.757, Episode_length: 495.600±412.081\n", ++ "Rollout 5957/9766, Reward: 257.741±43.438, Episode_length: 326.200±291.093\n", ++ "Rollout 5958/9766, Reward: 235.172±73.554, Episode_length: 428.000±375.774\n", ++ "Rollout 5959/9766, Reward: 255.267±42.530, Episode_length: 301.000±254.141\n", ++ "Rollout 5960/9766, Reward: 200.182±67.348, Episode_length: 675.900±361.817\n", ++ "Rollout 5961/9766, Reward: 252.029±54.354, Episode_length: 252.800±249.627\n", ++ "Rollout 5962/9766, Reward: 272.166±12.590, Episode_length: 170.400±18.837\n", ++ "Rollout 5963/9766, Reward: 249.853±45.823, Episode_length: 393.100±346.186\n", ++ "Rollout 5964/9766, Reward: 255.630±31.797, Episode_length: 187.300±53.790\n", ++ "Rollout 5965/9766, Reward: 273.154±15.286, Episode_length: 185.900±35.481\n", ++ "Rollout 5966/9766, Reward: 228.600±61.345, Episode_length: 540.800±376.280\n", ++ "Rollout 5967/9766, Reward: 255.412±41.091, Episode_length: 264.900±246.668\n", ++ "Rollout 5968/9766, Reward: 237.466±69.378, Episode_length: 344.500±328.013\n", ++ "Rollout 5969/9766, Reward: 280.309±21.858, Episode_length: 174.200±29.956\n", ++ "Rollout 5970/9766, Reward: 264.924±43.789, Episode_length: 317.200±259.301\n", ++ "Rollout 5971/9766, Reward: 257.618±46.654, Episode_length: 294.400±259.001\n", ++ "Rollout 5972/9766, Reward: 272.456±43.066, Episode_length: 266.400±245.735\n", ++ "Rollout 5973/9766, Reward: 264.507±52.590, Episode_length: 352.200±324.202\n", ++ "Rollout 5974/9766, Reward: 275.492±28.899, Episode_length: 340.100±303.620\n", ++ "Rollout 5975/9766, Reward: 280.619±28.617, Episode_length: 201.500±50.429\n", ++ "Rollout 5976/9766, Reward: 263.591±44.797, Episode_length: 289.300±242.022\n", ++ "Rollout 5977/9766, Reward: 279.307±41.318, Episode_length: 259.800±247.410\n", ++ "Rollout 5978/9766, Reward: 284.212±22.374, Episode_length: 190.400±39.218\n", ++ "Rollout 5979/9766, Reward: 267.559±33.209, Episode_length: 265.100±245.285\n", ++ "Rollout 5980/9766, Reward: 287.396±19.095, Episode_length: 261.600±229.954\n", ++ "Rollout 5981/9766, Reward: 286.300±12.889, Episode_length: 178.400±28.650\n", ++ "Rollout 5982/9766, Reward: 281.448±13.709, Episode_length: 182.400±26.654\n", ++ "Rollout 5983/9766, Reward: 279.120±11.930, Episode_length: 178.400±18.980\n", ++ "Rollout 5984/9766, Reward: 287.728±21.650, Episode_length: 179.900±24.550\n", ++ "Rollout 5985/9766, Reward: 282.782±16.895, Episode_length: 201.300±82.406\n", ++ "Rollout 5986/9766, Reward: 268.040±39.558, Episode_length: 247.000±251.329\n", ++ "Rollout 5987/9766, Reward: 284.024±17.929, Episode_length: 214.000±110.876\n", ++ "Rollout 5988/9766, Reward: 277.934±14.930, Episode_length: 170.000±20.518\n", ++ "Rollout 5989/9766, Reward: 281.404±37.888, Episode_length: 249.900±250.381\n", ++ "Rollout 5990/9766, Reward: 290.468±17.018, Episode_length: 175.800±16.993\n", ++ "Rollout 5991/9766, Reward: 290.936±14.812, Episode_length: 183.000±25.271\n", ++ "Rollout 5992/9766, Reward: 291.028±14.850, Episode_length: 198.000±90.203\n", ++ "Rollout 5993/9766, Reward: 276.149±17.702, Episode_length: 199.800±114.834\n", ++ "Rollout 5994/9766, Reward: 291.074±13.898, Episode_length: 179.000±19.365\n", ++ "Rollout 5995/9766, Reward: 284.156±17.192, Episode_length: 163.800±16.259\n", ++ "Rollout 5996/9766, Reward: 273.347±37.902, Episode_length: 260.900±247.105\n", ++ "Rollout 5997/9766, Reward: 291.381±13.037, Episode_length: 161.000±22.570\n", ++ "Rollout 5998/9766, Reward: 287.541±18.515, Episode_length: 166.500±23.428\n", ++ "Rollout 5999/9766, Reward: 292.089±36.054, Episode_length: 255.700±249.204\n", ++ "Rollout 6000/9766, Reward: 288.478±22.244, Episode_length: 264.600±240.853\n", ++ "Rollout 6001/9766, Reward: 268.237±35.171, Episode_length: 243.500±252.616\n", ++ "Rollout 6002/9766, Reward: 251.025±48.574, Episode_length: 625.600±380.777\n", ++ "Rollout 6003/9766, Reward: 297.468±15.109, Episode_length: 178.400±13.101\n", ++ "Rollout 6004/9766, Reward: 280.015±34.451, Episode_length: 257.900±249.068\n", ++ "Rollout 6005/9766, Reward: 271.251±30.811, Episode_length: 250.500±250.316\n", ++ "Rollout 6006/9766, Reward: 215.681±198.176, Episode_length: 272.600±200.193\n", ++ "Rollout 6007/9766, Reward: 287.937±10.518, Episode_length: 192.800±90.404\n", ++ "Rollout 6008/9766, Reward: 291.162±12.009, Episode_length: 177.200±44.364\n", ++ "Rollout 6009/9766, Reward: 292.359±14.442, Episode_length: 185.900±18.582\n", ++ "Rollout 6010/9766, Reward: 284.296±14.067, Episode_length: 166.600±21.001\n", ++ "Rollout 6011/9766, Reward: 248.391±49.745, Episode_length: 711.100±346.910\n", ++ "Rollout 6012/9766, Reward: 179.531±39.040, Episode_length: 916.400±250.800\n", ++ "Rollout 6013/9766, Reward: 271.193±12.915, Episode_length: 629.000±151.814\n", ++ "Rollout 6014/9766, Reward: 278.924±36.137, Episode_length: 348.500±326.204\n", ++ "Rollout 6015/9766, Reward: 292.570±19.184, Episode_length: 174.900±24.213\n", ++ "Rollout 6016/9766, Reward: 289.263±19.274, Episode_length: 178.300±19.566\n", ++ "Rollout 6017/9766, Reward: 288.514±18.211, Episode_length: 169.200±17.566\n", ++ "Rollout 6018/9766, Reward: 285.829±17.849, Episode_length: 176.800±18.176\n", ++ "Rollout 6019/9766, Reward: 294.382±15.334, Episode_length: 173.300±21.776\n", ++ "Rollout 6020/9766, Reward: 288.731±15.807, Episode_length: 201.300±54.443\n", ++ "Rollout 6021/9766, Reward: 289.884±14.019, Episode_length: 174.300±46.540\n", ++ "Rollout 6022/9766, Reward: 267.080±35.653, Episode_length: 400.200±359.755\n", ++ "Rollout 6023/9766, Reward: 251.937±50.242, Episode_length: 656.900±382.603\n", ++ "Rollout 6024/9766, Reward: 210.046±52.845, Episode_length: 780.700±341.247\n", ++ "Rollout 6025/9766, Reward: 189.877±47.206, Episode_length: 991.800±17.122\n", ++ "Rollout 6026/9766, Reward: 230.325±61.916, Episode_length: 725.400±359.964\n", ++ "Rollout 6027/9766, Reward: 291.697±20.927, Episode_length: 166.700±22.145\n", ++ "Rollout 6028/9766, Reward: 289.542±15.992, Episode_length: 186.700±37.850\n", ++ "Rollout 6029/9766, Reward: 278.929±14.953, Episode_length: 170.100±35.708\n", ++ "Rollout 6030/9766, Reward: 294.281±18.752, Episode_length: 168.300±27.532\n", ++ "Rollout 6031/9766, Reward: 292.088±14.351, Episode_length: 244.000±231.103\n", ++ "Rollout 6032/9766, Reward: 279.228±39.468, Episode_length: 260.600±246.889\n", ++ "Rollout 6033/9766, Reward: 280.809±19.795, Episode_length: 178.800±24.445\n", ++ "Rollout 6034/9766, Reward: 299.579±14.600, Episode_length: 183.500±32.346\n", ++ "Rollout 6035/9766, Reward: 288.842±16.866, Episode_length: 255.100±243.769\n", ++ "Rollout 6036/9766, Reward: 295.394±13.325, Episode_length: 169.600±20.456\n", ++ "Rollout 6037/9766, Reward: 289.034±17.121, Episode_length: 177.100±20.574\n", ++ "Rollout 6038/9766, Reward: 283.226±13.496, Episode_length: 162.900±15.953\n", ++ "Rollout 6039/9766, Reward: 294.838±14.380, Episode_length: 175.800±12.057\n", ++ "Rollout 6040/9766, Reward: 286.297±11.893, Episode_length: 180.100±12.778\n", ++ "Rollout 6041/9766, Reward: 276.826±21.936, Episode_length: 160.000±22.521\n", ++ "Rollout 6042/9766, Reward: 284.446±14.752, Episode_length: 169.700±24.146\n", ++ "Rollout 6043/9766, Reward: 288.857±19.597, Episode_length: 175.100±27.747\n", ++ "Rollout 6044/9766, Reward: 278.623±15.433, Episode_length: 159.400±20.723\n", ++ "Rollout 6045/9766, Reward: 277.852±16.976, Episode_length: 165.200±19.338\n", ++ "Rollout 6046/9766, Reward: 274.319±30.044, Episode_length: 326.900±304.348\n", ++ "Rollout 6047/9766, Reward: 285.252±38.433, Episode_length: 252.600±249.604\n", ++ "Rollout 6048/9766, Reward: 286.093±18.932, Episode_length: 249.800±227.912\n", ++ "Rollout 6049/9766, Reward: 288.894±16.249, Episode_length: 237.100±182.599\n", ++ "Rollout 6050/9766, Reward: 297.257±10.774, Episode_length: 176.500±19.033\n", ++ "Rollout 6051/9766, Reward: 276.762±38.873, Episode_length: 420.500±349.199\n", ++ "Rollout 6052/9766, Reward: 216.482±46.013, Episode_length: 859.200±286.348\n", ++ "Rollout 6053/9766, Reward: 196.960±47.183, Episode_length: 866.600±278.809\n", ++ "Rollout 6054/9766, Reward: 263.810±51.971, Episode_length: 415.500±382.969\n", ++ "Rollout 6055/9766, Reward: 289.907±21.671, Episode_length: 269.400±214.549\n", ++ "Rollout 6056/9766, Reward: 266.221±49.316, Episode_length: 328.400±336.274\n", ++ "Rollout 6057/9766, Reward: 281.575±14.700, Episode_length: 168.200±17.954\n", ++ "Rollout 6058/9766, Reward: 294.072±9.526, Episode_length: 173.700±19.152\n", ++ "Rollout 6059/9766, Reward: 273.854±40.326, Episode_length: 248.700±250.766\n", ++ "Rollout 6060/9766, Reward: 264.202±33.304, Episode_length: 387.100±343.162\n", ++ "Rollout 6061/9766, Reward: 215.134±52.671, Episode_length: 759.600±354.817\n", ++ "Rollout 6062/9766, Reward: 248.699±74.720, Episode_length: 379.000±301.982\n", ++ "Rollout 6063/9766, Reward: 277.515±33.610, Episode_length: 254.900±248.678\n", ++ "Rollout 6064/9766, Reward: 294.921±19.844, Episode_length: 177.100±25.339\n", ++ "Rollout 6065/9766, Reward: 283.950±39.605, Episode_length: 262.400±246.684\n", ++ "Rollout 6066/9766, Reward: 277.712±10.877, Episode_length: 165.500±14.445\n", ++ "Rollout 6067/9766, Reward: 265.973±83.570, Episode_length: 170.400±32.797\n", ++ "Rollout 6068/9766, Reward: 286.384±15.635, Episode_length: 175.600±20.318\n", ++ "Rollout 6069/9766, Reward: 286.487±10.449, Episode_length: 171.200±15.886\n", ++ "Rollout 6070/9766, Reward: 292.089±14.426, Episode_length: 161.200±17.915\n", ++ "Rollout 6071/9766, Reward: 283.015±17.508, Episode_length: 170.800±22.640\n", ++ "Rollout 6072/9766, Reward: 291.245±11.266, Episode_length: 171.600±17.744\n", ++ "Rollout 6073/9766, Reward: 296.652±19.821, Episode_length: 177.700±23.117\n", ++ "Rollout 6074/9766, Reward: 294.147±13.688, Episode_length: 174.200±20.624\n", ++ "Rollout 6075/9766, Reward: 277.720±20.701, Episode_length: 168.500±16.919\n", ++ "Rollout 6076/9766, Reward: 285.138±20.741, Episode_length: 173.800±16.558\n", ++ "Rollout 6077/9766, Reward: 279.065±19.388, Episode_length: 167.400±22.455\n", ++ "Rollout 6078/9766, Reward: 278.899±29.878, Episode_length: 248.900±250.972\n", ++ "Rollout 6079/9766, Reward: 288.028±15.705, Episode_length: 181.500±15.564\n", ++ "Rollout 6080/9766, Reward: 287.700±8.406, Episode_length: 168.600±14.354\n", ++ "Rollout 6081/9766, Reward: 281.425±22.242, Episode_length: 176.700±25.362\n", ++ "Rollout 6082/9766, Reward: 269.548±61.150, Episode_length: 175.500±33.601\n", ++ "Rollout 6083/9766, Reward: 282.267±30.116, Episode_length: 205.600±61.690\n", ++ "Rollout 6084/9766, Reward: 282.014±7.414, Episode_length: 160.500±17.699\n", ++ "Rollout 6085/9766, Reward: 291.531±15.798, Episode_length: 175.300±28.146\n", ++ "Rollout 6086/9766, Reward: 283.698±8.951, Episode_length: 174.100±24.259\n", ++ "Rollout 6087/9766, Reward: 288.336±20.759, Episode_length: 182.300±25.012\n", ++ "Rollout 6088/9766, Reward: 288.498±10.300, Episode_length: 180.200±23.314\n", ++ "Rollout 6089/9766, Reward: 282.518±15.455, Episode_length: 165.800±11.906\n", ++ "Rollout 6090/9766, Reward: 261.602±69.524, Episode_length: 169.200±35.651\n", ++ "Rollout 6091/9766, Reward: 284.496±21.996, Episode_length: 173.900±19.248\n", ++ "Rollout 6092/9766, Reward: 277.459±20.094, Episode_length: 168.200±13.460\n", ++ "Rollout 6093/9766, Reward: 273.625±15.807, Episode_length: 173.800±15.632\n", ++ "Rollout 6094/9766, Reward: 277.154±27.287, Episode_length: 200.000±79.224\n", ++ "Rollout 6095/9766, Reward: 276.116±16.992, Episode_length: 166.600±23.079\n", ++ "Rollout 6096/9766, Reward: 269.499±15.068, Episode_length: 184.100±32.743\n", ++ "Rollout 6097/9766, Reward: 252.032±49.259, Episode_length: 332.900±333.992\n", ++ "Rollout 6098/9766, Reward: 287.202±14.401, Episode_length: 174.400±30.067\n", ++ "Rollout 6099/9766, Reward: 276.978±29.251, Episode_length: 201.000±44.391\n", ++ "Rollout 6100/9766, Reward: 273.115±7.536, Episode_length: 172.700±20.742\n", ++ "Rollout 6101/9766, Reward: 287.198±13.056, Episode_length: 172.800±21.042\n", ++ "Rollout 6102/9766, Reward: 268.757±15.661, Episode_length: 173.900±22.421\n", ++ "Rollout 6103/9766, Reward: 276.339±17.040, Episode_length: 159.600±22.535\n", ++ "Rollout 6104/9766, Reward: 274.698±14.632, Episode_length: 168.300±22.481\n", ++ "Rollout 6105/9766, Reward: 292.589±15.525, Episode_length: 179.600±32.766\n", ++ "Rollout 6106/9766, Reward: 280.288±13.636, Episode_length: 175.900±27.271\n", ++ "Rollout 6107/9766, Reward: 269.786±23.038, Episode_length: 197.800±58.830\n", ++ "Rollout 6108/9766, Reward: 274.533±18.320, Episode_length: 177.200±19.605\n", ++ "Rollout 6109/9766, Reward: 287.463±23.186, Episode_length: 181.300±28.093\n", ++ "Rollout 6110/9766, Reward: 282.592±14.081, Episode_length: 170.800±20.104\n", ++ "Rollout 6111/9766, Reward: 248.245±74.560, Episode_length: 163.700±17.906\n", ++ "Rollout 6112/9766, Reward: 286.352±17.698, Episode_length: 191.900±25.894\n", ++ "Rollout 6113/9766, Reward: 275.551±23.488, Episode_length: 178.200±39.038\n", ++ "Rollout 6114/9766, Reward: 273.625±20.574, Episode_length: 202.500±66.312\n", ++ "Rollout 6115/9766, Reward: 284.600±12.907, Episode_length: 180.400±16.651\n", ++ "Rollout 6116/9766, Reward: 276.350±10.294, Episode_length: 170.600±14.527\n", ++ "Rollout 6117/9766, Reward: 276.093±41.484, Episode_length: 256.600±248.443\n", ++ "Rollout 6118/9766, Reward: 261.646±60.309, Episode_length: 345.700±327.381\n", ++ "Rollout 6119/9766, Reward: 238.332±81.824, Episode_length: 245.800±253.159\n", ++ "Rollout 6120/9766, Reward: 287.926±19.225, Episode_length: 183.000±24.352\n", ++ "Rollout 6121/9766, Reward: 278.964±22.242, Episode_length: 164.600±22.531\n", ++ "Rollout 6122/9766, Reward: 283.419±16.166, Episode_length: 180.400±14.270\n", ++ "Rollout 6123/9766, Reward: 271.642±27.285, Episode_length: 195.200±76.223\n", ++ "Rollout 6124/9766, Reward: 280.775±13.847, Episode_length: 161.300±19.611\n", ++ "Rollout 6125/9766, Reward: 297.286±7.998, Episode_length: 184.200±23.490\n", ++ "Rollout 6126/9766, Reward: 277.749±15.255, Episode_length: 182.100±41.556\n", ++ "Rollout 6127/9766, Reward: 272.860±50.277, Episode_length: 260.100±247.481\n", ++ "Rollout 6128/9766, Reward: 283.561±23.588, Episode_length: 179.100±18.479\n", ++ "Rollout 6129/9766, Reward: 281.061±14.296, Episode_length: 178.400±19.855\n", ++ "Rollout 6130/9766, Reward: 284.778±20.146, Episode_length: 166.200±26.195\n", ++ "Rollout 6131/9766, Reward: 249.193±73.901, Episode_length: 159.700±25.354\n", ++ "Rollout 6132/9766, Reward: 284.291±13.443, Episode_length: 163.400±20.636\n", ++ "Rollout 6133/9766, Reward: 281.613±12.880, Episode_length: 167.100±15.585\n", ++ "Rollout 6134/9766, Reward: 279.274±19.268, Episode_length: 179.900±22.919\n", ++ "Rollout 6135/9766, Reward: 267.984±16.750, Episode_length: 177.000±43.211\n", ++ "Rollout 6136/9766, Reward: 269.561±18.460, Episode_length: 163.100±10.756\n", ++ "Rollout 6137/9766, Reward: 271.314±21.083, Episode_length: 189.000±53.615\n", ++ "Rollout 6138/9766, Reward: 274.020±23.021, Episode_length: 163.800±19.914\n", ++ "Rollout 6139/9766, Reward: 280.962±16.410, Episode_length: 173.400±19.043\n", ++ "Rollout 6140/9766, Reward: 276.623±11.888, Episode_length: 174.500±36.239\n", ++ "Rollout 6141/9766, Reward: 266.361±19.883, Episode_length: 172.800±26.944\n", ++ "Rollout 6142/9766, Reward: 265.040±65.792, Episode_length: 246.100±252.641\n", ++ "Rollout 6143/9766, Reward: 280.077±19.254, Episode_length: 192.600±63.270\n", ++ "Rollout 6144/9766, Reward: 262.371±39.812, Episode_length: 278.000±245.661\n", ++ "Rollout 6145/9766, Reward: 272.600±21.534, Episode_length: 163.800±17.063\n", ++ "Rollout 6146/9766, Reward: 285.552±20.384, Episode_length: 179.700±43.630\n", ++ "Rollout 6147/9766, Reward: 279.497±20.568, Episode_length: 178.100±37.074\n", ++ "Rollout 6148/9766, Reward: 263.691±43.780, Episode_length: 255.400±248.814\n", ++ "Rollout 6149/9766, Reward: 273.464±23.549, Episode_length: 210.000±62.562\n", ++ "Rollout 6150/9766, Reward: 268.964±42.849, Episode_length: 254.800±248.709\n", ++ "Rollout 6151/9766, Reward: 273.285±19.616, Episode_length: 193.800±57.989\n", ++ "Rollout 6152/9766, Reward: 225.228±170.618, Episode_length: 213.500±56.719\n", ++ "Rollout 6153/9766, Reward: 247.148±133.285, Episode_length: 186.500±22.686\n", ++ "Rollout 6154/9766, Reward: 260.441±35.824, Episode_length: 277.200±182.436\n", ++ "Rollout 6155/9766, Reward: 284.689±17.495, Episode_length: 264.900±230.263\n", ++ "Rollout 6156/9766, Reward: 277.238±18.440, Episode_length: 161.000±19.824\n", ++ "Rollout 6157/9766, Reward: 278.047±10.398, Episode_length: 167.100±22.430\n", ++ "Rollout 6158/9766, Reward: 278.904±21.901, Episode_length: 169.600±24.524\n", ++ "Rollout 6159/9766, Reward: 275.552±17.697, Episode_length: 174.300±21.508\n", ++ "Rollout 6160/9766, Reward: 282.919±18.895, Episode_length: 189.500±38.195\n", ++ "Rollout 6161/9766, Reward: 243.763±63.731, Episode_length: 179.100±53.046\n", ++ "Rollout 6162/9766, Reward: 279.318±18.562, Episode_length: 173.800±23.735\n", ++ "Rollout 6163/9766, Reward: 282.023±16.469, Episode_length: 178.000±23.247\n", ++ "Rollout 6164/9766, Reward: 259.257±23.792, Episode_length: 265.500±249.032\n", ++ "Rollout 6165/9766, Reward: 280.174±30.579, Episode_length: 192.300±60.473\n", ++ "Rollout 6166/9766, Reward: 280.429±15.925, Episode_length: 165.700±17.675\n", ++ "Rollout 6167/9766, Reward: 287.866±12.460, Episode_length: 186.400±18.189\n", ++ "Rollout 6168/9766, Reward: 287.004±26.968, Episode_length: 197.600±53.172\n", ++ "Rollout 6169/9766, Reward: 250.270±66.536, Episode_length: 161.700±19.484\n", ++ "Rollout 6170/9766, Reward: 268.309±35.106, Episode_length: 233.100±100.927\n", ++ "Rollout 6171/9766, Reward: 243.443±66.841, Episode_length: 253.100±250.512\n", ++ "Rollout 6172/9766, Reward: 267.181±20.224, Episode_length: 174.900±30.425\n", ++ "Rollout 6173/9766, Reward: 248.810±42.729, Episode_length: 297.200±248.897\n", ++ "Rollout 6174/9766, Reward: 226.117±60.141, Episode_length: 572.900±361.829\n", ++ "Rollout 6175/9766, Reward: 258.305±38.959, Episode_length: 351.200±262.809\n", ++ "Rollout 6176/9766, Reward: 240.778±46.821, Episode_length: 332.500±239.070\n", ++ "Rollout 6177/9766, Reward: 258.040±23.166, Episode_length: 312.400±97.664\n", ++ "Rollout 6178/9766, Reward: 262.726±27.832, Episode_length: 261.200±60.957\n", ++ "Rollout 6179/9766, Reward: 235.733±44.078, Episode_length: 453.100±268.339\n", ++ "Rollout 6180/9766, Reward: 232.229±54.797, Episode_length: 420.900±303.275\n", ++ "Rollout 6181/9766, Reward: 264.779±30.861, Episode_length: 278.400±67.312\n", ++ "Rollout 6182/9766, Reward: 246.170±39.969, Episode_length: 380.000±287.373\n", ++ "Rollout 6183/9766, Reward: 256.987±21.777, Episode_length: 356.100±228.522\n", ++ "Rollout 6184/9766, Reward: 257.368±23.512, Episode_length: 241.700±59.377\n", ++ "Rollout 6185/9766, Reward: 265.617±20.773, Episode_length: 279.400±155.621\n", ++ "Rollout 6186/9766, Reward: 157.368±236.222, Episode_length: 401.000±363.673\n", ++ "Rollout 6187/9766, Reward: 246.320±40.599, Episode_length: 221.100±80.842\n", ++ "Rollout 6188/9766, Reward: 93.256±295.895, Episode_length: 168.200±67.358\n", ++ "Rollout 6189/9766, Reward: 262.215±28.701, Episode_length: 199.800±47.803\n", ++ "Rollout 6190/9766, Reward: 252.127±21.277, Episode_length: 256.900±248.013\n", ++ "Rollout 6191/9766, Reward: 244.771±47.167, Episode_length: 322.800±284.221\n", ++ "Rollout 6192/9766, Reward: 268.673±20.255, Episode_length: 182.700±31.074\n", ++ "Rollout 6193/9766, Reward: 245.371±45.165, Episode_length: 286.900±246.443\n", ++ "Rollout 6194/9766, Reward: 266.870±27.262, Episode_length: 202.700±55.066\n", ++ "Rollout 6195/9766, Reward: 262.381±37.704, Episode_length: 209.200±84.383\n", ++ "Rollout 6196/9766, Reward: 273.873±26.782, Episode_length: 213.700±68.399\n", ++ "Rollout 6197/9766, Reward: 243.364±35.129, Episode_length: 322.700±239.598\n", ++ "Rollout 6198/9766, Reward: 182.922±216.302, Episode_length: 194.900±61.922\n", ++ "Rollout 6199/9766, Reward: 256.729±41.788, Episode_length: 228.200±71.094\n", ++ "Rollout 6200/9766, Reward: 256.841±38.059, Episode_length: 224.100±81.147\n", ++ "Rollout 6201/9766, Reward: 264.390±28.983, Episode_length: 215.700±72.218\n", ++ "Rollout 6202/9766, Reward: 257.552±40.018, Episode_length: 275.300±244.375\n", ++ "Rollout 6203/9766, Reward: 237.770±83.831, Episode_length: 251.000±253.168\n", ++ "Rollout 6204/9766, Reward: 266.824±22.141, Episode_length: 215.200±61.237\n", ++ "Rollout 6205/9766, Reward: 238.959±56.494, Episode_length: 335.700±332.746\n", ++ "Rollout 6206/9766, Reward: 272.320±21.977, Episode_length: 193.200±50.070\n", ++ "Rollout 6207/9766, Reward: 249.821±44.531, Episode_length: 314.800±239.657\n", ++ "Rollout 6208/9766, Reward: 239.698±47.947, Episode_length: 245.100±56.887\n", ++ "Rollout 6209/9766, Reward: 253.066±31.722, Episode_length: 210.600±63.663\n", ++ "Rollout 6210/9766, Reward: 286.630±16.593, Episode_length: 267.600±198.370\n", ++ "Rollout 6211/9766, Reward: 230.488±81.180, Episode_length: 275.900±183.734\n", ++ "Rollout 6212/9766, Reward: 262.242±35.255, Episode_length: 258.300±247.847\n", ++ "Rollout 6213/9766, Reward: 220.101±66.128, Episode_length: 223.000±118.902\n", ++ "Rollout 6214/9766, Reward: 243.105±92.153, Episode_length: 267.100±245.229\n", ++ "Rollout 6215/9766, Reward: 255.668±41.064, Episode_length: 349.200±316.971\n", ++ "Rollout 6216/9766, Reward: 281.470±14.460, Episode_length: 179.200±21.794\n", ++ "Rollout 6217/9766, Reward: 278.369±14.876, Episode_length: 174.800±18.851\n", ++ "Rollout 6218/9766, Reward: 240.050±35.452, Episode_length: 454.600±370.832\n", ++ "Rollout 6219/9766, Reward: 254.532±32.968, Episode_length: 296.900±214.527\n", ++ "Rollout 6220/9766, Reward: 244.685±41.399, Episode_length: 283.100±122.982\n", ++ "Rollout 6221/9766, Reward: 239.876±43.144, Episode_length: 349.400±328.910\n", ++ "Rollout 6222/9766, Reward: 243.581±51.635, Episode_length: 421.800±349.286\n", ++ "Rollout 6223/9766, Reward: 215.599±83.050, Episode_length: 371.600±339.099\n", ++ "Rollout 6224/9766, Reward: 209.015±132.124, Episode_length: 333.400±309.225\n", ++ "Rollout 6225/9766, Reward: 270.353±16.449, Episode_length: 262.800±228.556\n", ++ "Rollout 6226/9766, Reward: 266.260±25.160, Episode_length: 195.900±72.825\n", ++ "Rollout 6227/9766, Reward: 227.512±78.209, Episode_length: 477.100±397.268\n", ++ "Rollout 6228/9766, Reward: 254.722±26.271, Episode_length: 276.600±249.737\n", ++ "Rollout 6229/9766, Reward: 261.491±17.575, Episode_length: 174.500±20.578\n", ++ "Rollout 6230/9766, Reward: 246.530±34.109, Episode_length: 273.800±107.514\n", ++ "Rollout 6231/9766, Reward: 255.801±20.443, Episode_length: 193.400±72.610\n", ++ "Rollout 6232/9766, Reward: 269.165±35.667, Episode_length: 315.300±245.031\n", ++ "Rollout 6233/9766, Reward: 237.287±78.417, Episode_length: 199.100±72.739\n", ++ "Rollout 6234/9766, Reward: 276.857±15.036, Episode_length: 192.800±43.363\n", ++ "Rollout 6235/9766, Reward: 181.544±103.277, Episode_length: 535.000±383.658\n", ++ "Rollout 6236/9766, Reward: 243.678±47.986, Episode_length: 395.200±309.878\n", ++ "Rollout 6237/9766, Reward: 270.674±16.861, Episode_length: 171.300±22.208\n", ++ "Rollout 6238/9766, Reward: 277.435±28.992, Episode_length: 174.600±22.362\n", ++ "Rollout 6239/9766, Reward: 260.496±43.265, Episode_length: 254.300±249.334\n", ++ "Rollout 6240/9766, Reward: 272.075±16.769, Episode_length: 216.800±128.873\n", ++ "Rollout 6241/9766, Reward: 263.286±57.254, Episode_length: 255.000±249.805\n", ++ "Rollout 6242/9766, Reward: 280.170±16.731, Episode_length: 181.800±22.158\n", ++ "Rollout 6243/9766, Reward: 274.529±40.021, Episode_length: 294.600±250.305\n", ++ "Rollout 6244/9766, Reward: 272.349±29.532, Episode_length: 181.100±33.658\n", ++ "Rollout 6245/9766, Reward: 280.074±31.318, Episode_length: 217.000±88.448\n", ++ "Rollout 6246/9766, Reward: 282.885±18.577, Episode_length: 190.700±24.413\n", ++ "Rollout 6247/9766, Reward: 271.249±39.117, Episode_length: 276.300±242.117\n", ++ "Rollout 6248/9766, Reward: 262.605±43.027, Episode_length: 256.400±248.601\n", ++ "Rollout 6249/9766, Reward: 265.142±45.504, Episode_length: 258.500±248.376\n", ++ "Rollout 6250/9766, Reward: 265.763±13.267, Episode_length: 192.600±23.075\n", ++ "Rollout 6251/9766, Reward: 256.597±36.389, Episode_length: 263.900±246.547\n", ++ "Rollout 6252/9766, Reward: 277.678±16.609, Episode_length: 197.200±23.765\n", ++ "Rollout 6253/9766, Reward: 199.246±49.745, Episode_length: 714.100±357.544\n", ++ "Rollout 6254/9766, Reward: 190.417±49.268, Episode_length: 836.900±262.384\n", ++ "Rollout 6255/9766, Reward: 141.219±21.797, Episode_length: 1000.000±0.000\n", ++ "Rollout 6256/9766, Reward: 182.626±59.808, Episode_length: 793.500±320.123\n", ++ "Rollout 6257/9766, Reward: 190.886±48.664, Episode_length: 844.800±312.455\n", ++ "Rollout 6258/9766, Reward: 204.468±70.698, Episode_length: 740.900±328.127\n", ++ "Rollout 6259/9766, Reward: 174.650±52.157, Episode_length: 890.200±238.664\n", ++ "Rollout 6260/9766, Reward: 269.397±34.831, Episode_length: 259.600±248.628\n", ++ "Rollout 6261/9766, Reward: 281.914±14.693, Episode_length: 176.300±14.690\n", ++ "Rollout 6262/9766, Reward: 190.676±54.721, Episode_length: 759.900±367.801\n", ++ "Rollout 6263/9766, Reward: 203.168±63.807, Episode_length: 670.500±403.900\n", ++ "Rollout 6264/9766, Reward: 190.512±65.227, Episode_length: 748.900±316.809\n", ++ "Rollout 6265/9766, Reward: 203.613±59.528, Episode_length: 663.400±361.835\n", ++ "Rollout 6266/9766, Reward: 181.194±46.069, Episode_length: 753.300±314.310\n", ++ "Rollout 6267/9766, Reward: 281.536±18.261, Episode_length: 236.400±123.517\n", ++ "Rollout 6268/9766, Reward: 253.891±46.458, Episode_length: 331.000±334.804\n", ++ "Rollout 6269/9766, Reward: 288.233±28.433, Episode_length: 305.300±276.550\n", ++ "Rollout 6270/9766, Reward: 271.849±38.678, Episode_length: 342.800±315.210\n", ++ "Rollout 6271/9766, Reward: 266.626±57.754, Episode_length: 427.600±374.632\n", ++ "Rollout 6272/9766, Reward: 270.797±46.763, Episode_length: 284.100±248.463\n", ++ "Rollout 6273/9766, Reward: 238.382±62.843, Episode_length: 423.700±377.650\n", ++ "Rollout 6274/9766, Reward: 293.436±12.662, Episode_length: 192.100±20.511\n", ++ "Rollout 6275/9766, Reward: 230.628±65.911, Episode_length: 515.400±397.315\n", ++ "Rollout 6276/9766, Reward: 249.189±43.372, Episode_length: 413.200±373.764\n", ++ "Rollout 6277/9766, Reward: 223.703±131.592, Episode_length: 254.100±250.601\n", ++ "Rollout 6278/9766, Reward: 254.984±57.756, Episode_length: 419.700±371.404\n", ++ "Rollout 6279/9766, Reward: 141.888±354.458, Episode_length: 255.500±248.992\n", ++ "Rollout 6280/9766, Reward: 245.573±55.341, Episode_length: 326.600±257.397\n", ++ "Rollout 6281/9766, Reward: 230.083±77.895, Episode_length: 440.600±290.204\n", ++ "Rollout 6282/9766, Reward: 290.438±15.113, Episode_length: 264.100±225.275\n", ++ "Rollout 6283/9766, Reward: 274.875±21.091, Episode_length: 196.700±15.258\n", ++ "Rollout 6284/9766, Reward: 207.743±141.257, Episode_length: 335.900±332.497\n", ++ "Rollout 6285/9766, Reward: 214.992±65.444, Episode_length: 620.400±387.676\n", ++ "Rollout 6286/9766, Reward: 254.062±61.698, Episode_length: 463.000±358.787\n", ++ "Rollout 6287/9766, Reward: 276.469±19.843, Episode_length: 257.900±245.904\n", ++ "Rollout 6288/9766, Reward: 267.472±51.108, Episode_length: 263.200±246.878\n", ++ "Rollout 6289/9766, Reward: 264.661±34.877, Episode_length: 271.500±244.076\n", ++ "Rollout 6290/9766, Reward: 150.426±238.339, Episode_length: 431.100±377.342\n", ++ "Rollout 6291/9766, Reward: 227.427±51.483, Episode_length: 602.600±400.011\n", ++ "Rollout 6292/9766, Reward: 230.373±85.530, Episode_length: 333.700±334.556\n", ++ "Rollout 6293/9766, Reward: 220.173±57.886, Episode_length: 588.500±411.598\n", ++ "Rollout 6294/9766, Reward: 265.243±30.942, Episode_length: 316.700±248.152\n", ++ "Rollout 6295/9766, Reward: 256.586±38.932, Episode_length: 340.100±315.760\n", ++ "Rollout 6296/9766, Reward: 256.109±87.793, Episode_length: 252.000±251.740\n", ++ "Rollout 6297/9766, Reward: 236.256±63.848, Episode_length: 484.300±389.157\n", ++ "Rollout 6298/9766, Reward: 264.542±45.699, Episode_length: 259.800±246.894\n", ++ "Rollout 6299/9766, Reward: 278.726±16.344, Episode_length: 180.500±22.042\n", ++ "Rollout 6300/9766, Reward: 268.015±41.974, Episode_length: 268.800±246.593\n", ++ "Rollout 6301/9766, Reward: 214.384±68.484, Episode_length: 584.100±416.150\n", ++ "Rollout 6302/9766, Reward: 179.524±142.988, Episode_length: 484.500±369.292\n", ++ "Rollout 6303/9766, Reward: 254.119±54.861, Episode_length: 421.700±375.115\n", ++ "Rollout 6304/9766, Reward: 247.113±59.596, Episode_length: 357.500±322.314\n", ++ "Rollout 6305/9766, Reward: 262.649±42.589, Episode_length: 249.900±251.056\n", ++ "Rollout 6306/9766, Reward: 266.949±38.112, Episode_length: 338.300±312.148\n", ++ "Rollout 6307/9766, Reward: 231.645±61.294, Episode_length: 566.700±402.418\n", ++ "Rollout 6308/9766, Reward: 275.041±13.020, Episode_length: 263.800±231.603\n", ++ "Rollout 6309/9766, Reward: 283.569±13.707, Episode_length: 357.000±174.242\n", ++ "Rollout 6310/9766, Reward: 245.159±50.975, Episode_length: 556.400±349.153\n", ++ "Rollout 6311/9766, Reward: 238.364±62.992, Episode_length: 424.600±377.063\n", ++ "Rollout 6312/9766, Reward: 264.656±40.296, Episode_length: 364.600±316.118\n", ++ "Rollout 6313/9766, Reward: 264.849±40.209, Episode_length: 253.400±249.877\n", ++ "Rollout 6314/9766, Reward: 283.423±17.601, Episode_length: 235.900±219.992\n", ++ "Rollout 6315/9766, Reward: 253.671±50.206, Episode_length: 328.200±298.673\n", ++ "Rollout 6316/9766, Reward: 271.716±50.211, Episode_length: 261.700±246.717\n", ++ "Rollout 6317/9766, Reward: 262.935±38.615, Episode_length: 254.600±248.949\n", ++ "Rollout 6318/9766, Reward: 269.235±30.198, Episode_length: 258.100±243.611\n", ++ "Rollout 6319/9766, Reward: 262.265±44.836, Episode_length: 261.700±247.178\n", ++ "Rollout 6320/9766, Reward: 181.749±33.753, Episode_length: 955.100±90.579\n", ++ "Rollout 6321/9766, Reward: 222.143±64.745, Episode_length: 713.500±355.020\n", ++ "Rollout 6322/9766, Reward: 275.411±32.605, Episode_length: 617.300±351.970\n", ++ "Rollout 6323/9766, Reward: 256.049±47.741, Episode_length: 480.400±388.016\n", ++ "Rollout 6324/9766, Reward: 170.447±32.041, Episode_length: 966.800±99.600\n", ++ "Rollout 6325/9766, Reward: 161.788±45.558, Episode_length: 918.900±243.300\n", ++ "Rollout 6326/9766, Reward: 210.366±52.822, Episode_length: 832.400±322.567\n", ++ "Rollout 6327/9766, Reward: 287.941±12.692, Episode_length: 186.200±44.699\n", ++ "Rollout 6328/9766, Reward: 269.231±38.020, Episode_length: 307.000±272.942\n", ++ "Rollout 6329/9766, Reward: 176.135±15.131, Episode_length: 1000.000±0.000\n", ++ "Rollout 6330/9766, Reward: 214.610±51.914, Episode_length: 789.100±332.322\n", ++ "Rollout 6331/9766, Reward: 172.843±25.032, Episode_length: 1000.000±0.000\n", ++ "Rollout 6332/9766, Reward: 237.084±59.362, Episode_length: 574.700±413.973\n", ++ "Rollout 6333/9766, Reward: 189.877±47.183, Episode_length: 915.500±253.500\n", ++ "Rollout 6334/9766, Reward: 297.621±16.078, Episode_length: 167.100±12.308\n", ++ "Rollout 6335/9766, Reward: 291.910±5.030, Episode_length: 178.900±17.609\n", ++ "Rollout 6336/9766, Reward: 271.486±45.298, Episode_length: 331.000±334.783\n", ++ "Rollout 6337/9766, Reward: 267.325±49.911, Episode_length: 337.700±331.529\n", ++ "Rollout 6338/9766, Reward: 289.847±15.689, Episode_length: 170.200±15.184\n", ++ "Rollout 6339/9766, Reward: 280.011±38.878, Episode_length: 256.100±248.194\n", ++ "Rollout 6340/9766, Reward: 295.228±14.421, Episode_length: 169.000±15.537\n", ++ "Rollout 6341/9766, Reward: 291.726±17.760, Episode_length: 176.900±16.477\n", ++ "Rollout 6342/9766, Reward: 283.422±20.032, Episode_length: 175.100±17.501\n", ++ "Rollout 6343/9766, Reward: 280.315±33.167, Episode_length: 324.200±323.233\n", ++ "Rollout 6344/9766, Reward: 279.492±15.582, Episode_length: 164.400±13.973\n", ++ "Rollout 6345/9766, Reward: 290.284±18.400, Episode_length: 171.800±16.327\n", ++ "Rollout 6346/9766, Reward: 278.261±19.126, Episode_length: 166.100±21.454\n", ++ "Rollout 6347/9766, Reward: 283.322±16.315, Episode_length: 159.200±10.796\n", ++ "Rollout 6348/9766, Reward: 293.574±19.651, Episode_length: 176.500±17.345\n", ++ "Rollout 6349/9766, Reward: 210.753±205.615, Episode_length: 260.600±247.734\n", ++ "Rollout 6350/9766, Reward: 280.569±37.409, Episode_length: 256.300±248.825\n", ++ "Rollout 6351/9766, Reward: 289.606±8.759, Episode_length: 181.400±24.134\n", ++ "Rollout 6352/9766, Reward: 292.916±21.733, Episode_length: 174.700±20.871\n", ++ "Rollout 6353/9766, Reward: 253.038±89.082, Episode_length: 164.800±26.769\n", ++ "Rollout 6354/9766, Reward: 280.407±14.723, Episode_length: 159.600±23.572\n", ++ "Rollout 6355/9766, Reward: 292.647±21.023, Episode_length: 175.800±28.474\n", ++ "Rollout 6356/9766, Reward: 276.083±37.291, Episode_length: 246.500±251.654\n", ++ "Rollout 6357/9766, Reward: 271.527±40.154, Episode_length: 400.500±364.613\n", ++ "Rollout 6358/9766, Reward: 264.356±36.049, Episode_length: 245.000±251.844\n", ++ "Rollout 6359/9766, Reward: 282.003±14.887, Episode_length: 272.100±215.440\n", ++ "Rollout 6360/9766, Reward: 157.050±257.800, Episode_length: 324.300±333.493\n", ++ "Rollout 6361/9766, Reward: 284.427±27.782, Episode_length: 194.600±78.734\n", ++ "Rollout 6362/9766, Reward: 144.064±126.235, Episode_length: 945.300±147.283\n", ++ "Rollout 6363/9766, Reward: 113.371±203.741, Episode_length: 416.400±382.237\n", ++ "Rollout 6364/9766, Reward: 290.151±17.587, Episode_length: 179.200±21.080\n", ++ "Rollout 6365/9766, Reward: 189.487±147.580, Episode_length: 507.700±402.494\n", ++ "Rollout 6366/9766, Reward: 181.596±102.559, Episode_length: 855.100±277.969\n", ++ "Rollout 6367/9766, Reward: 143.629±88.368, Episode_length: 1000.000±0.000\n", ++ "Rollout 6368/9766, Reward: 189.514±59.609, Episode_length: 839.700±320.613\n", ++ "Rollout 6369/9766, Reward: 280.570±31.191, Episode_length: 529.900±352.714\n", ++ "Rollout 6370/9766, Reward: 281.658±38.704, Episode_length: 257.700±249.151\n", ++ "Rollout 6371/9766, Reward: 285.732±15.829, Episode_length: 174.800±19.768\n", ++ "Rollout 6372/9766, Reward: 279.870±46.476, Episode_length: 344.600±307.281\n", ++ "Rollout 6373/9766, Reward: 295.284±18.733, Episode_length: 178.100±32.688\n", ++ "Rollout 6374/9766, Reward: 282.481±18.363, Episode_length: 171.300±22.878\n", ++ "Rollout 6375/9766, Reward: 261.715±111.786, Episode_length: 260.600±246.904\n", ++ "Rollout 6376/9766, Reward: 283.839±18.816, Episode_length: 158.900±14.829\n", ++ "Rollout 6377/9766, Reward: 291.399±15.767, Episode_length: 176.800±23.899\n", ++ "Rollout 6378/9766, Reward: 288.189±12.867, Episode_length: 163.700±23.686\n", ++ "Rollout 6379/9766, Reward: 290.485±14.852, Episode_length: 178.300±17.141\n", ++ "Rollout 6380/9766, Reward: 285.890±16.257, Episode_length: 161.800±12.023\n", ++ "Rollout 6381/9766, Reward: 294.420±14.745, Episode_length: 185.600±25.711\n", ++ "Rollout 6382/9766, Reward: 275.914±39.074, Episode_length: 254.500±249.195\n", ++ "Rollout 6383/9766, Reward: 290.975±13.006, Episode_length: 175.500±19.674\n", ++ "Rollout 6384/9766, Reward: 285.015±21.757, Episode_length: 171.300±16.432\n", ++ "Rollout 6385/9766, Reward: 280.237±17.729, Episode_length: 169.700±26.393\n", ++ "Rollout 6386/9766, Reward: 282.090±21.015, Episode_length: 173.100±33.204\n", ++ "Rollout 6387/9766, Reward: 291.282±14.745, Episode_length: 171.000±16.087\n", ++ "Rollout 6388/9766, Reward: 273.437±12.158, Episode_length: 192.100±38.347\n", ++ "Rollout 6389/9766, Reward: 282.879±17.133, Episode_length: 191.700±35.009\n", ++ "Rollout 6390/9766, Reward: 288.689±17.154, Episode_length: 201.100±40.143\n", ++ "Rollout 6391/9766, Reward: 282.949±17.736, Episode_length: 188.000±40.247\n", ++ "Rollout 6392/9766, Reward: 278.934±20.226, Episode_length: 176.300±33.043\n", ++ "Rollout 6393/9766, Reward: 280.957±6.988, Episode_length: 180.000±34.377\n", ++ "Rollout 6394/9766, Reward: 297.932±11.421, Episode_length: 193.700±26.844\n", ++ "Rollout 6395/9766, Reward: 289.243±23.158, Episode_length: 170.500±23.389\n", ++ "Rollout 6396/9766, Reward: 168.942±356.187, Episode_length: 180.200±20.760\n", ++ "Rollout 6397/9766, Reward: 291.806±18.330, Episode_length: 178.500±16.409\n", ++ "Rollout 6398/9766, Reward: 290.525±12.007, Episode_length: 180.400±34.511\n", ++ "Rollout 6399/9766, Reward: 288.345±6.586, Episode_length: 211.500±76.851\n", ++ "Rollout 6400/9766, Reward: 289.332±18.365, Episode_length: 163.400±23.963\n", ++ "Rollout 6401/9766, Reward: 278.864±30.237, Episode_length: 251.000±250.050\n", ++ "Rollout 6402/9766, Reward: 286.244±18.111, Episode_length: 167.000±18.714\n", ++ "Rollout 6403/9766, Reward: 280.762±31.207, Episode_length: 243.600±252.853\n", ++ "Rollout 6404/9766, Reward: 283.708±13.495, Episode_length: 292.400±265.306\n", ++ "Rollout 6405/9766, Reward: 294.017±14.767, Episode_length: 427.400±321.973\n", ++ "Rollout 6406/9766, Reward: 263.854±39.598, Episode_length: 482.800±399.069\n", ++ "Rollout 6407/9766, Reward: 211.966±56.651, Episode_length: 889.600±253.988\n", ++ "Rollout 6408/9766, Reward: 228.359±55.073, Episode_length: 804.800±329.284\n", ++ "Rollout 6409/9766, Reward: 249.898±58.884, Episode_length: 729.200±367.502\n", ++ "Rollout 6410/9766, Reward: 256.443±51.843, Episode_length: 601.900±352.877\n", ++ "Rollout 6411/9766, Reward: 280.035±17.030, Episode_length: 213.200±130.497\n", ++ "Rollout 6412/9766, Reward: 284.456±30.309, Episode_length: 372.800±298.527\n", ++ "Rollout 6413/9766, Reward: 295.650±12.011, Episode_length: 263.100±245.498\n", ++ "Rollout 6414/9766, Reward: 283.623±32.080, Episode_length: 298.900±287.523\n", ++ "Rollout 6415/9766, Reward: 278.440±17.006, Episode_length: 150.700±10.149\n", ++ "Rollout 6416/9766, Reward: 292.732±17.205, Episode_length: 169.100±15.050\n", ++ "Rollout 6417/9766, Reward: 295.875±18.415, Episode_length: 174.900±25.591\n", ++ "Rollout 6418/9766, Reward: 287.794±26.832, Episode_length: 167.400±21.082\n", ++ "Rollout 6419/9766, Reward: 301.116±13.114, Episode_length: 171.900±23.902\n", ++ "Rollout 6420/9766, Reward: 295.987±16.507, Episode_length: 170.900±21.691\n", ++ "Rollout 6421/9766, Reward: 288.431±12.504, Episode_length: 163.400±14.908\n", ++ "Rollout 6422/9766, Reward: 299.621±11.078, Episode_length: 172.400±18.216\n", ++ "Rollout 6423/9766, Reward: 281.958±18.186, Episode_length: 162.600±32.472\n", ++ "Rollout 6424/9766, Reward: 291.461±19.153, Episode_length: 164.800±21.526\n", ++ "Rollout 6425/9766, Reward: 277.740±16.894, Episode_length: 169.400±20.771\n", ++ "Rollout 6426/9766, Reward: 300.958±13.784, Episode_length: 178.400±17.591\n", ++ "Rollout 6427/9766, Reward: 283.035±23.041, Episode_length: 164.200±14.330\n", ++ "Rollout 6428/9766, Reward: 282.438±22.325, Episode_length: 174.800±36.891\n", ++ "Rollout 6429/9766, Reward: 298.516±13.693, Episode_length: 173.600±29.142\n", ++ "Rollout 6430/9766, Reward: 291.606±18.335, Episode_length: 171.000±17.228\n", ++ "Rollout 6431/9766, Reward: 284.915±16.664, Episode_length: 165.800±20.629\n", ++ "Rollout 6432/9766, Reward: 288.771±19.668, Episode_length: 172.600±17.962\n", ++ "Rollout 6433/9766, Reward: 290.892±16.690, Episode_length: 173.100±17.352\n", ++ "Rollout 6434/9766, Reward: 284.594±14.451, Episode_length: 164.400±15.357\n", ++ "Rollout 6435/9766, Reward: 287.106±11.330, Episode_length: 178.200±33.469\n", ++ "Rollout 6436/9766, Reward: 291.913±17.441, Episode_length: 202.900±102.989\n", ++ "Rollout 6437/9766, Reward: 290.754±11.501, Episode_length: 163.900±15.972\n", ++ "Rollout 6438/9766, Reward: 300.868±16.322, Episode_length: 177.900±22.862\n", ++ "Rollout 6439/9766, Reward: 287.141±35.988, Episode_length: 254.200±249.171\n", ++ "Rollout 6440/9766, Reward: 283.444±14.144, Episode_length: 168.900±16.580\n", ++ "Rollout 6441/9766, Reward: 282.491±14.239, Episode_length: 169.000±17.070\n", ++ "Rollout 6442/9766, Reward: 263.618±30.903, Episode_length: 239.200±253.731\n", ++ "Rollout 6443/9766, Reward: 282.244±16.101, Episode_length: 181.100±37.721\n", ++ "Rollout 6444/9766, Reward: 288.147±16.273, Episode_length: 174.000±19.606\n", ++ "Rollout 6445/9766, Reward: 297.658±13.772, Episode_length: 175.600±15.200\n", ++ "Rollout 6446/9766, Reward: 290.653±13.707, Episode_length: 174.300±24.063\n", ++ "Rollout 6447/9766, Reward: 289.111±19.665, Episode_length: 169.600±20.991\n", ++ "Rollout 6448/9766, Reward: 291.148±11.683, Episode_length: 174.900±10.124\n", ++ "Rollout 6449/9766, Reward: 279.937±21.892, Episode_length: 169.100±15.990\n", ++ "Rollout 6450/9766, Reward: 275.932±37.508, Episode_length: 255.600±249.454\n", ++ "Rollout 6451/9766, Reward: 287.605±21.351, Episode_length: 183.200±26.472\n", ++ "Rollout 6452/9766, Reward: 283.634±18.986, Episode_length: 200.900±121.891\n", ++ "Rollout 6453/9766, Reward: 281.665±25.725, Episode_length: 176.700±15.014\n", ++ "Rollout 6454/9766, Reward: 276.589±30.862, Episode_length: 253.100±249.464\n", ++ "Rollout 6455/9766, Reward: 293.383±8.840, Episode_length: 255.700±247.021\n", ++ "Rollout 6456/9766, Reward: 266.868±42.202, Episode_length: 255.200±248.807\n", ++ "Rollout 6457/9766, Reward: 275.998±51.122, Episode_length: 342.900±328.790\n", ++ "Rollout 6458/9766, Reward: 269.445±37.976, Episode_length: 252.200±249.780\n", ++ "Rollout 6459/9766, Reward: 276.956±15.594, Episode_length: 164.300±20.562\n", ++ "Rollout 6460/9766, Reward: 288.725±20.951, Episode_length: 174.400±20.456\n", ++ "Rollout 6461/9766, Reward: 278.006±20.026, Episode_length: 215.600±161.501\n", ++ "Rollout 6462/9766, Reward: 267.517±36.433, Episode_length: 318.400±308.541\n", ++ "Rollout 6463/9766, Reward: 287.338±19.561, Episode_length: 174.800±25.424\n", ++ "Rollout 6464/9766, Reward: 273.200±13.673, Episode_length: 174.900±33.137\n", ++ "Rollout 6465/9766, Reward: 291.835±10.814, Episode_length: 220.200±154.504\n", ++ "Rollout 6466/9766, Reward: 279.305±37.009, Episode_length: 249.400±251.207\n", ++ "Rollout 6467/9766, Reward: 280.108±39.745, Episode_length: 248.800±251.238\n", ++ "Rollout 6468/9766, Reward: 277.557±39.433, Episode_length: 261.600±246.913\n", ++ "Rollout 6469/9766, Reward: 275.656±16.261, Episode_length: 155.300±12.530\n", ++ "Rollout 6470/9766, Reward: 282.770±12.590, Episode_length: 174.700±17.088\n", ++ "Rollout 6471/9766, Reward: 268.027±42.664, Episode_length: 258.400±247.462\n", ++ "Rollout 6472/9766, Reward: 272.528±49.297, Episode_length: 336.300±321.578\n", ++ "Rollout 6473/9766, Reward: 287.774±17.942, Episode_length: 175.400±17.437\n", ++ "Rollout 6474/9766, Reward: 270.112±52.434, Episode_length: 261.700±246.822\n", ++ "Rollout 6475/9766, Reward: 288.318±17.488, Episode_length: 179.100±19.295\n", ++ "Rollout 6476/9766, Reward: 258.506±47.550, Episode_length: 325.600±309.612\n", ++ "Rollout 6477/9766, Reward: 287.307±14.571, Episode_length: 170.400±22.743\n", ++ "Rollout 6478/9766, Reward: 283.346±16.904, Episode_length: 178.000±15.767\n", ++ "Rollout 6479/9766, Reward: 283.041±19.515, Episode_length: 174.900±24.789\n", ++ "Rollout 6480/9766, Reward: 285.268±21.847, Episode_length: 170.300±22.575\n", ++ "Rollout 6481/9766, Reward: 289.908±19.016, Episode_length: 184.100±18.338\n", ++ "Rollout 6482/9766, Reward: 257.585±67.635, Episode_length: 167.700±23.013\n", ++ "Rollout 6483/9766, Reward: 287.580±18.675, Episode_length: 223.600±151.379\n", ++ "Rollout 6484/9766, Reward: 271.711±31.142, Episode_length: 333.500±314.472\n", ++ "Rollout 6485/9766, Reward: 279.945±36.928, Episode_length: 251.900±250.060\n", ++ "Rollout 6486/9766, Reward: 284.026±41.729, Episode_length: 254.000±249.971\n", ++ "Rollout 6487/9766, Reward: 280.363±40.953, Episode_length: 253.800±249.276\n", ++ "Rollout 6488/9766, Reward: 265.580±48.973, Episode_length: 340.100±330.562\n", ++ "Rollout 6489/9766, Reward: 275.267±39.016, Episode_length: 420.700±337.506\n", ++ "Rollout 6490/9766, Reward: 282.237±8.792, Episode_length: 170.000±24.323\n", ++ "Rollout 6491/9766, Reward: 266.635±55.073, Episode_length: 469.800±362.132\n", ++ "Rollout 6492/9766, Reward: 287.688±21.092, Episode_length: 181.500±15.253\n", ++ "Rollout 6493/9766, Reward: 274.820±31.774, Episode_length: 252.600±250.737\n", ++ "Rollout 6494/9766, Reward: 273.728±37.161, Episode_length: 245.200±252.401\n", ++ "Rollout 6495/9766, Reward: 290.520±15.154, Episode_length: 239.600±182.618\n", ++ "Rollout 6496/9766, Reward: 280.339±35.841, Episode_length: 268.600±244.839\n", ++ "Rollout 6497/9766, Reward: 282.788±18.942, Episode_length: 181.700±22.681\n", ++ "Rollout 6498/9766, Reward: 274.610±14.200, Episode_length: 192.800±102.346\n", ++ "Rollout 6499/9766, Reward: 278.563±18.365, Episode_length: 165.000±16.959\n", ++ "Rollout 6500/9766, Reward: 270.505±55.801, Episode_length: 264.400±246.360\n", ++ "Rollout 6501/9766, Reward: 268.992±34.813, Episode_length: 254.900±248.721\n", ++ "Rollout 6502/9766, Reward: 279.652±14.277, Episode_length: 236.900±207.399\n", ++ "Rollout 6503/9766, Reward: 272.860±41.373, Episode_length: 243.900±252.859\n", ++ "Rollout 6504/9766, Reward: 280.249±18.227, Episode_length: 170.800±18.148\n", ++ "Rollout 6505/9766, Reward: 272.892±19.155, Episode_length: 161.100±13.881\n", ++ "Rollout 6506/9766, Reward: 294.284±14.079, Episode_length: 175.400±24.723\n", ++ "Rollout 6507/9766, Reward: 285.132±15.564, Episode_length: 227.700±227.990\n", ++ "Rollout 6508/9766, Reward: 289.780±17.940, Episode_length: 235.300±176.320\n", ++ "Rollout 6509/9766, Reward: 289.577±19.345, Episode_length: 169.400±21.846\n", ++ "Rollout 6510/9766, Reward: 293.282±15.038, Episode_length: 174.900±17.461\n", ++ "Rollout 6511/9766, Reward: 292.704±17.314, Episode_length: 164.300±24.767\n", ++ "Rollout 6512/9766, Reward: 280.991±15.083, Episode_length: 171.600±18.380\n", ++ "Rollout 6513/9766, Reward: 287.263±18.972, Episode_length: 170.800±19.620\n", ++ "Rollout 6514/9766, Reward: 279.309±15.251, Episode_length: 165.400±19.941\n", ++ "Rollout 6515/9766, Reward: 294.903±14.075, Episode_length: 170.200±18.654\n", ++ "Rollout 6516/9766, Reward: 288.346±17.818, Episode_length: 171.700±22.330\n", ++ "Rollout 6517/9766, Reward: 301.052±12.670, Episode_length: 186.100±31.558\n", ++ "Rollout 6518/9766, Reward: 280.104±18.322, Episode_length: 155.900±16.028\n", ++ "Rollout 6519/9766, Reward: 285.696±18.141, Episode_length: 169.900±26.805\n", ++ "Rollout 6520/9766, Reward: 271.035±18.306, Episode_length: 172.300±27.111\n", ++ "Rollout 6521/9766, Reward: 279.206±15.037, Episode_length: 165.300±16.408\n", ++ "Rollout 6522/9766, Reward: 297.680±16.189, Episode_length: 179.300±19.468\n", ++ "Rollout 6523/9766, Reward: 281.783±38.332, Episode_length: 252.100±249.774\n", ++ "Rollout 6524/9766, Reward: 286.518±14.496, Episode_length: 167.100±15.827\n", ++ "Rollout 6525/9766, Reward: 289.346±20.354, Episode_length: 157.000±10.305\n", ++ "Rollout 6526/9766, Reward: 296.543±15.142, Episode_length: 167.000±15.582\n", ++ "Rollout 6527/9766, Reward: 287.441±16.348, Episode_length: 169.400±19.006\n", ++ "Rollout 6528/9766, Reward: 299.590±14.561, Episode_length: 168.000±21.964\n", ++ "Rollout 6529/9766, Reward: 287.108±24.469, Episode_length: 169.700±19.774\n", ++ "Rollout 6530/9766, Reward: 287.629±18.478, Episode_length: 171.500±27.152\n", ++ "Rollout 6531/9766, Reward: 297.943±14.264, Episode_length: 168.800±16.461\n", ++ "Rollout 6532/9766, Reward: 251.403±47.797, Episode_length: 483.200±367.346\n", ++ "Rollout 6533/9766, Reward: 233.207±49.828, Episode_length: 568.200±407.393\n", ++ "Rollout 6534/9766, Reward: 300.451±9.906, Episode_length: 172.800±21.400\n", ++ "Rollout 6535/9766, Reward: 269.806±25.792, Episode_length: 307.000±279.279\n", ++ "Rollout 6536/9766, Reward: 276.138±42.772, Episode_length: 254.000±249.527\n", ++ "Rollout 6537/9766, Reward: 286.524±15.767, Episode_length: 167.700±15.640\n", ++ "Rollout 6538/9766, Reward: 287.766±19.350, Episode_length: 170.400±16.506\n", ++ "Rollout 6539/9766, Reward: 289.444±23.482, Episode_length: 227.100±138.969\n", ++ "Rollout 6540/9766, Reward: 288.157±16.101, Episode_length: 164.000±20.538\n", ++ "Rollout 6541/9766, Reward: 289.641±18.067, Episode_length: 175.000±20.460\n", ++ "Rollout 6542/9766, Reward: 286.452±22.697, Episode_length: 169.900±18.657\n", ++ "Rollout 6543/9766, Reward: 283.321±19.070, Episode_length: 169.100±22.439\n", ++ "Rollout 6544/9766, Reward: 283.963±18.399, Episode_length: 174.100±16.134\n", ++ "Rollout 6545/9766, Reward: 280.412±14.037, Episode_length: 157.700±19.204\n", ++ "Rollout 6546/9766, Reward: 279.704±16.635, Episode_length: 163.400±20.660\n", ++ "Rollout 6547/9766, Reward: 274.779±44.575, Episode_length: 256.100±249.105\n", ++ "Rollout 6548/9766, Reward: 281.528±14.869, Episode_length: 166.500±21.500\n", ++ "Rollout 6549/9766, Reward: 289.402±16.177, Episode_length: 183.900±25.785\n", ++ "Rollout 6550/9766, Reward: 284.483±11.971, Episode_length: 176.500±17.066\n", ++ "Rollout 6551/9766, Reward: 282.247±13.516, Episode_length: 175.200±14.400\n", ++ "Rollout 6552/9766, Reward: 291.106±16.850, Episode_length: 175.100±19.367\n", ++ "Rollout 6553/9766, Reward: 292.985±12.858, Episode_length: 178.200±20.173\n", ++ "Rollout 6554/9766, Reward: 275.277±16.279, Episode_length: 167.200±25.455\n", ++ "Rollout 6555/9766, Reward: 276.032±21.584, Episode_length: 171.000±14.711\n", ++ "Rollout 6556/9766, Reward: 284.665±12.836, Episode_length: 170.200±12.229\n", ++ "Rollout 6557/9766, Reward: 283.539±21.401, Episode_length: 178.200±20.089\n", ++ "Rollout 6558/9766, Reward: 290.275±22.018, Episode_length: 181.500±18.975\n", ++ "Rollout 6559/9766, Reward: 293.176±11.716, Episode_length: 175.200±18.745\n", ++ "Rollout 6560/9766, Reward: 289.887±10.546, Episode_length: 170.400±18.424\n", ++ "Rollout 6561/9766, Reward: 280.342±12.992, Episode_length: 170.600±19.216\n", ++ "Rollout 6562/9766, Reward: 286.118±21.747, Episode_length: 178.000±16.715\n", ++ "Rollout 6563/9766, Reward: 289.685±12.983, Episode_length: 178.200±15.497\n", ++ "Rollout 6564/9766, Reward: 275.745±10.676, Episode_length: 158.200±17.966\n", ++ "Rollout 6565/9766, Reward: 280.713±15.302, Episode_length: 166.500±18.156\n", ++ "Rollout 6566/9766, Reward: 291.916±12.763, Episode_length: 174.800±17.600\n", ++ "Rollout 6567/9766, Reward: 284.967±19.887, Episode_length: 172.400±32.794\n", ++ "Rollout 6568/9766, Reward: 274.701±35.707, Episode_length: 247.200±251.371\n", ++ "Rollout 6569/9766, Reward: 289.495±19.926, Episode_length: 157.800±19.135\n", ++ "Rollout 6570/9766, Reward: 282.127±17.986, Episode_length: 167.900±11.291\n", ++ "Rollout 6571/9766, Reward: 286.055±15.357, Episode_length: 161.000±21.298\n", ++ "Rollout 6572/9766, Reward: 287.807±23.354, Episode_length: 174.900±23.192\n", ++ "Rollout 6573/9766, Reward: 279.471±32.284, Episode_length: 243.400±253.025\n", ++ "Rollout 6574/9766, Reward: 269.390±45.879, Episode_length: 282.800±258.085\n", ++ "Rollout 6575/9766, Reward: 241.142±61.716, Episode_length: 728.600±319.820\n", ++ "Rollout 6576/9766, Reward: 153.303±16.724, Episode_length: 1000.000±0.000\n", ++ "Rollout 6577/9766, Reward: 229.791±54.232, Episode_length: 695.500±276.368\n", ++ "Rollout 6578/9766, Reward: 280.924±12.381, Episode_length: 239.300±37.205\n", ++ "Rollout 6579/9766, Reward: 274.504±17.586, Episode_length: 350.700±197.179\n", ++ "Rollout 6580/9766, Reward: 222.165±53.505, Episode_length: 724.300±366.195\n", ++ "Rollout 6581/9766, Reward: 274.481±47.123, Episode_length: 257.100±248.335\n", ++ "Rollout 6582/9766, Reward: 265.656±36.851, Episode_length: 245.800±251.799\n", ++ "Rollout 6583/9766, Reward: 283.359±13.564, Episode_length: 159.600±20.180\n", ++ "Rollout 6584/9766, Reward: 277.306±16.879, Episode_length: 158.000±16.959\n", ++ "Rollout 6585/9766, Reward: 283.342±21.335, Episode_length: 177.500±23.682\n", ++ "Rollout 6586/9766, Reward: 272.802±15.766, Episode_length: 166.700±15.736\n", ++ "Rollout 6587/9766, Reward: 284.957±18.349, Episode_length: 171.700±21.476\n", ++ "Rollout 6588/9766, Reward: 277.990±16.503, Episode_length: 251.600±223.907\n", ++ "Rollout 6589/9766, Reward: 265.972±53.571, Episode_length: 258.000±248.011\n", ++ "Rollout 6590/9766, Reward: 275.969±18.770, Episode_length: 174.700±18.006\n", ++ "Rollout 6591/9766, Reward: 262.936±49.774, Episode_length: 254.500±248.980\n", ++ "Rollout 6592/9766, Reward: 256.459±50.840, Episode_length: 325.800±337.312\n", ++ "Rollout 6593/9766, Reward: 269.702±12.222, Episode_length: 186.300±33.909\n", ++ "Rollout 6594/9766, Reward: 265.721±47.658, Episode_length: 372.800±270.758\n", ++ "Rollout 6595/9766, Reward: 286.977±18.220, Episode_length: 214.000±114.211\n", ++ "Rollout 6596/9766, Reward: 267.441±34.544, Episode_length: 367.500±313.199\n", ++ "Rollout 6597/9766, Reward: 266.058±28.951, Episode_length: 240.400±197.257\n", ++ "Rollout 6598/9766, Reward: 262.803±28.061, Episode_length: 284.400±243.505\n", ++ "Rollout 6599/9766, Reward: 255.063±43.399, Episode_length: 327.200±271.334\n", ++ "Rollout 6600/9766, Reward: 229.738±53.177, Episode_length: 483.800±363.067\n", ++ "Rollout 6601/9766, Reward: 246.151±46.359, Episode_length: 287.400±242.126\n", ++ "Rollout 6602/9766, Reward: 250.324±59.945, Episode_length: 432.000±326.619\n", ++ "Rollout 6603/9766, Reward: 249.078±34.790, Episode_length: 270.800±250.918\n", ++ "Rollout 6604/9766, Reward: 256.320±30.855, Episode_length: 332.200±249.354\n", ++ "Rollout 6605/9766, Reward: 247.723±54.755, Episode_length: 328.000±236.733\n", ++ "Rollout 6606/9766, Reward: 265.120±34.548, Episode_length: 217.500±83.245\n", ++ "Rollout 6607/9766, Reward: 250.146±33.602, Episode_length: 364.500±268.918\n", ++ "Rollout 6608/9766, Reward: 264.442±26.452, Episode_length: 223.100±76.245\n", ++ "Rollout 6609/9766, Reward: 228.365±50.478, Episode_length: 336.900±251.377\n", ++ "Rollout 6610/9766, Reward: 238.877±56.061, Episode_length: 341.100±330.677\n", ++ "Rollout 6611/9766, Reward: 229.914±94.713, Episode_length: 273.500±246.472\n", ++ "Rollout 6612/9766, Reward: 269.368±29.803, Episode_length: 225.700±68.140\n", ++ "Rollout 6613/9766, Reward: 266.112±39.288, Episode_length: 199.900±73.173\n", ++ "Rollout 6614/9766, Reward: 247.837±70.880, Episode_length: 174.800±71.650\n", ++ "Rollout 6615/9766, Reward: 259.525±38.060, Episode_length: 307.000±225.198\n", ++ "Rollout 6616/9766, Reward: 245.765±34.356, Episode_length: 241.700±94.268\n", ++ "Rollout 6617/9766, Reward: 284.353±16.529, Episode_length: 199.000±40.080\n", ++ "Rollout 6618/9766, Reward: 255.874±21.764, Episode_length: 212.900±98.673\n", ++ "Rollout 6619/9766, Reward: 281.922±15.906, Episode_length: 182.000±40.804\n", ++ "Rollout 6620/9766, Reward: 256.769±28.834, Episode_length: 206.900±59.728\n", ++ "Rollout 6621/9766, Reward: 266.676±27.284, Episode_length: 221.400±70.823\n", ++ "Rollout 6622/9766, Reward: 259.516±28.664, Episode_length: 270.000±157.401\n", ++ "Rollout 6623/9766, Reward: 261.640±41.948, Episode_length: 229.100±89.621\n", ++ "Rollout 6624/9766, Reward: 213.869±60.674, Episode_length: 574.700±364.098\n", ++ "Rollout 6625/9766, Reward: 237.920±45.934, Episode_length: 479.600±249.379\n", ++ "Rollout 6626/9766, Reward: 218.681±56.548, Episode_length: 636.700±379.387\n", ++ "Rollout 6627/9766, Reward: 230.300±55.712, Episode_length: 473.000±349.858\n", ++ "Rollout 6628/9766, Reward: 246.471±47.887, Episode_length: 337.600±283.902\n", ++ "Rollout 6629/9766, Reward: 211.615±83.506, Episode_length: 528.100±258.645\n", ++ "Rollout 6630/9766, Reward: 268.596±14.019, Episode_length: 410.900±184.318\n", ++ "Rollout 6631/9766, Reward: 229.465±56.689, Episode_length: 453.500±324.026\n", ++ "Rollout 6632/9766, Reward: 256.983±30.379, Episode_length: 254.600±102.853\n", ++ "Rollout 6633/9766, Reward: 225.966±52.015, Episode_length: 451.500±290.681\n", ++ "Rollout 6634/9766, Reward: 255.360±43.106, Episode_length: 335.900±240.930\n", ++ "Rollout 6635/9766, Reward: 245.151±30.910, Episode_length: 356.300±265.976\n", ++ "Rollout 6636/9766, Reward: 201.201±97.288, Episode_length: 528.500±385.406\n", ++ "Rollout 6637/9766, Reward: 206.447±55.832, Episode_length: 626.700±329.719\n", ++ "Rollout 6638/9766, Reward: 222.771±68.686, Episode_length: 567.300±347.494\n", ++ "Rollout 6639/9766, Reward: 223.759±57.257, Episode_length: 490.400±345.912\n", ++ "Rollout 6640/9766, Reward: 252.566±46.132, Episode_length: 294.300±243.312\n", ++ "Rollout 6641/9766, Reward: 254.839±53.000, Episode_length: 396.900±305.263\n", ++ "Rollout 6642/9766, Reward: 231.364±51.889, Episode_length: 439.000±295.677\n", ++ "Rollout 6643/9766, Reward: 232.424±56.760, Episode_length: 538.500±337.718\n", ++ "Rollout 6644/9766, Reward: 263.163±21.803, Episode_length: 328.400±181.777\n", ++ "Rollout 6645/9766, Reward: 243.721±37.328, Episode_length: 335.300±246.714\n", ++ "Rollout 6646/9766, Reward: 264.665±18.472, Episode_length: 247.200±36.696\n", ++ "Rollout 6647/9766, Reward: 257.907±37.379, Episode_length: 446.700±253.217\n", ++ "Rollout 6648/9766, Reward: 223.839±55.068, Episode_length: 714.300±373.039\n", ++ "Rollout 6649/9766, Reward: 265.985±22.448, Episode_length: 283.900±215.535\n", ++ "Rollout 6650/9766, Reward: 275.831±33.958, Episode_length: 314.400±239.109\n", ++ "Rollout 6651/9766, Reward: 273.744±18.036, Episode_length: 198.400±30.706\n", ++ "Rollout 6652/9766, Reward: 258.008±50.212, Episode_length: 325.200±245.424\n", ++ "Rollout 6653/9766, Reward: 255.460±29.481, Episode_length: 287.200±245.871\n", ++ "Rollout 6654/9766, Reward: 266.204±21.719, Episode_length: 216.700±43.407\n", ++ "Rollout 6655/9766, Reward: 159.494±27.308, Episode_length: 982.400±52.800\n", ++ "Rollout 6656/9766, Reward: 257.131±42.268, Episode_length: 457.400±191.417\n", ++ "Rollout 6657/9766, Reward: 195.467±52.570, Episode_length: 869.200±257.644\n", ++ "Rollout 6658/9766, Reward: 194.507±57.200, Episode_length: 825.000±310.320\n", ++ "Rollout 6659/9766, Reward: 186.893±58.877, Episode_length: 881.000±247.906\n", ++ "Rollout 6660/9766, Reward: 188.999±49.082, Episode_length: 813.600±326.367\n", ++ "Rollout 6661/9766, Reward: 246.897±29.307, Episode_length: 348.800±253.727\n", ++ "Rollout 6662/9766, Reward: 255.728±45.058, Episode_length: 379.600±218.136\n", ++ "Rollout 6663/9766, Reward: 224.666±56.537, Episode_length: 506.800±352.238\n", ++ "Rollout 6664/9766, Reward: 236.665±49.457, Episode_length: 462.200±314.297\n", ++ "Rollout 6665/9766, Reward: 230.551±72.924, Episode_length: 468.900±349.667\n", ++ "Rollout 6666/9766, Reward: 227.383±59.890, Episode_length: 496.900±344.209\n", ++ "Rollout 6667/9766, Reward: 243.853±47.602, Episode_length: 509.300±258.957\n", ++ "Rollout 6668/9766, Reward: 226.090±59.276, Episode_length: 463.600±358.524\n", ++ "Rollout 6669/9766, Reward: 263.226±15.240, Episode_length: 297.900±174.418\n", ++ "Rollout 6670/9766, Reward: 236.087±60.337, Episode_length: 506.300±310.393\n", ++ "Rollout 6671/9766, Reward: 213.835±61.511, Episode_length: 616.100±336.996\n", ++ "Rollout 6672/9766, Reward: 217.186±89.914, Episode_length: 408.900±310.481\n", ++ "Rollout 6673/9766, Reward: 219.866±50.420, Episode_length: 526.600±282.812\n", ++ "Rollout 6674/9766, Reward: 216.131±51.944, Episode_length: 436.300±295.381\n", ++ "Rollout 6675/9766, Reward: 246.915±47.174, Episode_length: 319.300±234.179\n", ++ "Rollout 6676/9766, Reward: 208.159±60.519, Episode_length: 461.600±359.553\n", ++ "Rollout 6677/9766, Reward: 237.371±46.289, Episode_length: 356.900±259.448\n", ++ "Rollout 6678/9766, Reward: 213.801±52.882, Episode_length: 452.900±296.570\n", ++ "Rollout 6679/9766, Reward: 197.926±51.071, Episode_length: 571.900±328.751\n", ++ "Rollout 6680/9766, Reward: 214.008±55.040, Episode_length: 417.000±298.310\n", ++ "Rollout 6681/9766, Reward: 210.494±49.503, Episode_length: 426.300±297.155\n", ++ "Rollout 6682/9766, Reward: 210.184±56.396, Episode_length: 460.400±284.394\n", ++ "Rollout 6683/9766, Reward: 242.922±45.246, Episode_length: 453.000±274.298\n", ++ "Rollout 6684/9766, Reward: 211.181±57.167, Episode_length: 406.100±308.669\n", ++ "Rollout 6685/9766, Reward: 211.264±47.381, Episode_length: 506.200±221.409\n", ++ "Rollout 6686/9766, Reward: 251.671±29.704, Episode_length: 365.700±230.795\n", ++ "Rollout 6687/9766, Reward: 225.349±52.584, Episode_length: 391.600±297.230\n", ++ "Rollout 6688/9766, Reward: 236.876±47.946, Episode_length: 418.900±308.890\n", ++ "Rollout 6689/9766, Reward: 214.185±50.284, Episode_length: 423.800±296.380\n", ++ "Rollout 6690/9766, Reward: 202.748±129.724, Episode_length: 423.700±336.438\n", ++ "Rollout 6691/9766, Reward: 236.438±35.554, Episode_length: 371.500±234.783\n", ++ "Rollout 6692/9766, Reward: 201.699±64.807, Episode_length: 540.500±379.895\n", ++ "Rollout 6693/9766, Reward: 218.575±56.317, Episode_length: 500.500±338.556\n", ++ "Rollout 6694/9766, Reward: 234.453±26.399, Episode_length: 337.300±114.253\n", ++ "Rollout 6695/9766, Reward: 222.015±50.173, Episode_length: 589.000±290.090\n", ++ "Rollout 6696/9766, Reward: 239.759±51.962, Episode_length: 415.000±295.918\n", ++ "Rollout 6697/9766, Reward: 257.705±20.647, Episode_length: 348.300±199.901\n", ++ "Rollout 6698/9766, Reward: 230.244±30.000, Episode_length: 352.800±265.655\n", ++ "Rollout 6699/9766, Reward: 219.267±49.378, Episode_length: 440.900±227.127\n", ++ "Rollout 6700/9766, Reward: 221.858±47.710, Episode_length: 497.700±340.905\n", ++ "Rollout 6701/9766, Reward: 187.707±79.378, Episode_length: 518.800±326.217\n", ++ "Rollout 6702/9766, Reward: 258.807±43.132, Episode_length: 368.400±297.730\n", ++ "Rollout 6703/9766, Reward: 218.514±40.684, Episode_length: 406.300±318.413\n", ++ "Rollout 6704/9766, Reward: 233.276±38.038, Episode_length: 347.900±304.226\n", ++ "Rollout 6705/9766, Reward: 235.905±33.861, Episode_length: 244.700±130.998\n", ++ "Rollout 6706/9766, Reward: 242.935±30.291, Episode_length: 237.400±81.804\n", ++ "Rollout 6707/9766, Reward: 208.266±46.540, Episode_length: 492.600±357.202\n", ++ "Rollout 6708/9766, Reward: 245.585±25.475, Episode_length: 362.800±145.638\n", ++ "Rollout 6709/9766, Reward: 228.079±49.074, Episode_length: 480.800±327.803\n", ++ "Rollout 6710/9766, Reward: 223.438±42.845, Episode_length: 280.600±98.123\n", ++ "Rollout 6711/9766, Reward: 226.992±41.402, Episode_length: 420.900±313.476\n", ++ "Rollout 6712/9766, Reward: 242.440±42.817, Episode_length: 298.100±241.144\n", ++ "Rollout 6713/9766, Reward: 202.927±43.170, Episode_length: 463.500±281.308\n", ++ "Rollout 6714/9766, Reward: 219.476±30.261, Episode_length: 310.800±93.122\n", ++ "Rollout 6715/9766, Reward: 211.788±43.136, Episode_length: 455.500±290.010\n", ++ "Rollout 6716/9766, Reward: 183.442±118.165, Episode_length: 390.600±318.862\n", ++ "Rollout 6717/9766, Reward: 221.555±48.391, Episode_length: 378.800±304.973\n", ++ "Rollout 6718/9766, Reward: 228.400±36.387, Episode_length: 359.500±211.246\n", ++ "Rollout 6719/9766, Reward: 242.655±41.654, Episode_length: 317.800±256.434\n", ++ "Rollout 6720/9766, Reward: 241.796±25.953, Episode_length: 199.800±71.309\n", ++ "Rollout 6721/9766, Reward: 242.168±24.848, Episode_length: 217.800±83.715\n", ++ "Rollout 6722/9766, Reward: 218.130±78.620, Episode_length: 261.100±197.611\n", ++ "Rollout 6723/9766, Reward: 224.686±51.672, Episode_length: 492.800±343.581\n", ++ "Rollout 6724/9766, Reward: 259.287±47.470, Episode_length: 272.500±243.445\n", ++ "Rollout 6725/9766, Reward: 224.277±66.620, Episode_length: 488.700±366.514\n", ++ "Rollout 6726/9766, Reward: 261.923±39.981, Episode_length: 262.800±247.394\n", ++ "Rollout 6727/9766, Reward: 215.441±73.133, Episode_length: 515.600±396.155\n", ++ "Rollout 6728/9766, Reward: 200.750±71.905, Episode_length: 617.200±390.158\n", ++ "Rollout 6729/9766, Reward: 218.752±73.152, Episode_length: 439.300±368.860\n", ++ "Rollout 6730/9766, Reward: 242.935±58.183, Episode_length: 385.300±309.435\n", ++ "Rollout 6731/9766, Reward: 254.776±33.643, Episode_length: 297.000±145.236\n", ++ "Rollout 6732/9766, Reward: 246.908±50.786, Episode_length: 351.900±244.649\n", ++ "Rollout 6733/9766, Reward: 231.802±66.185, Episode_length: 465.200±298.899\n", ++ "Rollout 6734/9766, Reward: 234.736±44.803, Episode_length: 278.000±102.205\n", ++ "Rollout 6735/9766, Reward: 237.909±41.640, Episode_length: 337.400±234.419\n", ++ "Rollout 6736/9766, Reward: 247.733±38.279, Episode_length: 328.700±234.102\n", ++ "Rollout 6737/9766, Reward: 249.856±35.216, Episode_length: 308.100±162.979\n", ++ "Rollout 6738/9766, Reward: 266.535±18.257, Episode_length: 239.500±77.505\n", ++ "Rollout 6739/9766, Reward: 226.641±23.530, Episode_length: 244.600±46.567\n", ++ "Rollout 6740/9766, Reward: 234.427±53.265, Episode_length: 373.900±264.481\n", ++ "Rollout 6741/9766, Reward: 209.821±76.663, Episode_length: 359.600±255.293\n", ++ "Rollout 6742/9766, Reward: 231.827±49.175, Episode_length: 340.400±322.090\n", ++ "Rollout 6743/9766, Reward: 219.952±79.916, Episode_length: 330.200±233.818\n", ++ "Rollout 6744/9766, Reward: 256.258±24.673, Episode_length: 199.400±55.947\n", ++ "Rollout 6745/9766, Reward: 229.143±46.414, Episode_length: 377.400±315.822\n", ++ "Rollout 6746/9766, Reward: 260.905±18.530, Episode_length: 197.900±79.164\n", ++ "Rollout 6747/9766, Reward: 222.172±52.270, Episode_length: 383.800±272.480\n", ++ "Rollout 6748/9766, Reward: 263.586±23.756, Episode_length: 295.400±175.514\n", ++ "Rollout 6749/9766, Reward: 261.276±42.733, Episode_length: 317.000±251.487\n", ++ "Rollout 6750/9766, Reward: 206.520±58.122, Episode_length: 607.000±391.640\n", ++ "Rollout 6751/9766, Reward: 199.494±60.387, Episode_length: 578.500±351.396\n", ++ "Rollout 6752/9766, Reward: 217.497±64.962, Episode_length: 520.700±330.274\n", ++ "Rollout 6753/9766, Reward: 211.645±59.353, Episode_length: 574.900±299.103\n", ++ "Rollout 6754/9766, Reward: 214.762±55.951, Episode_length: 515.700±365.549\n", ++ "Rollout 6755/9766, Reward: 235.575±48.385, Episode_length: 428.100±313.451\n", ++ "Rollout 6756/9766, Reward: 237.932±25.543, Episode_length: 280.000±90.684\n", ++ "Rollout 6757/9766, Reward: 247.859±41.446, Episode_length: 333.700±250.895\n", ++ "Rollout 6758/9766, Reward: 202.586±63.610, Episode_length: 491.300±343.183\n", ++ "Rollout 6759/9766, Reward: 208.189±90.673, Episode_length: 489.900±348.282\n", ++ "Rollout 6760/9766, Reward: 99.609±321.666, Episode_length: 493.800±358.881\n", ++ "Rollout 6761/9766, Reward: 240.372±48.165, Episode_length: 349.800±326.917\n", ++ "Rollout 6762/9766, Reward: 63.766±344.063, Episode_length: 269.900±253.861\n", ++ "Rollout 6763/9766, Reward: 224.723±74.437, Episode_length: 343.400±283.038\n", ++ "Rollout 6764/9766, Reward: 220.025±59.490, Episode_length: 418.500±330.332\n", ++ "Rollout 6765/9766, Reward: 249.265±31.425, Episode_length: 274.900±179.957\n", ++ "Rollout 6766/9766, Reward: 217.227±54.740, Episode_length: 517.700±347.011\n", ++ "Rollout 6767/9766, Reward: 204.597±54.598, Episode_length: 585.900±364.143\n", ++ "Rollout 6768/9766, Reward: 211.802±55.121, Episode_length: 437.800±303.462\n", ++ "Rollout 6769/9766, Reward: 236.177±43.206, Episode_length: 292.400±241.414\n", ++ "Rollout 6770/9766, Reward: 214.490±81.162, Episode_length: 410.400±284.574\n", ++ "Rollout 6771/9766, Reward: 251.089±23.789, Episode_length: 199.200±59.821\n", ++ "Rollout 6772/9766, Reward: 204.705±69.674, Episode_length: 579.500±367.075\n", ++ "Rollout 6773/9766, Reward: 237.080±41.293, Episode_length: 350.300±287.971\n", ++ "Rollout 6774/9766, Reward: 211.991±48.838, Episode_length: 481.700±336.474\n", ++ "Rollout 6775/9766, Reward: 221.060±51.729, Episode_length: 354.300±309.379\n", ++ "Rollout 6776/9766, Reward: 189.769±94.670, Episode_length: 493.800±377.909\n", ++ "Rollout 6777/9766, Reward: 220.280±58.288, Episode_length: 416.600±323.549\n", ++ "Rollout 6778/9766, Reward: 237.391±47.058, Episode_length: 418.400±271.353\n", ++ "Rollout 6779/9766, Reward: 211.793±54.846, Episode_length: 379.900±314.229\n", ++ "Rollout 6780/9766, Reward: 233.613±32.222, Episode_length: 219.700±74.486\n", ++ "Rollout 6781/9766, Reward: 252.759±38.865, Episode_length: 340.200±238.392\n", ++ "Rollout 6782/9766, Reward: 227.808±26.293, Episode_length: 418.100±263.449\n", ++ "Rollout 6783/9766, Reward: 225.548±39.641, Episode_length: 507.600±263.871\n", ++ "Rollout 6784/9766, Reward: 241.016±39.190, Episode_length: 352.400±255.736\n", ++ "Rollout 6785/9766, Reward: 232.892±25.719, Episode_length: 411.500±239.571\n", ++ "Rollout 6786/9766, Reward: 184.332±77.788, Episode_length: 491.900±371.783\n", ++ "Rollout 6787/9766, Reward: 226.582±48.368, Episode_length: 325.200±248.096\n", ++ "Rollout 6788/9766, Reward: 223.224±58.320, Episode_length: 500.200±305.568\n", ++ "Rollout 6789/9766, Reward: 208.544±47.798, Episode_length: 442.600±298.191\n", ++ "Rollout 6790/9766, Reward: 241.339±17.177, Episode_length: 315.500±182.286\n", ++ "Rollout 6791/9766, Reward: 240.332±41.279, Episode_length: 394.200±262.407\n", ++ "Rollout 6792/9766, Reward: 230.786±42.920, Episode_length: 291.300±241.196\n", ++ "Rollout 6793/9766, Reward: 242.655±32.021, Episode_length: 408.400±238.734\n", ++ "Rollout 6794/9766, Reward: 189.841±109.775, Episode_length: 437.200±369.473\n", ++ "Rollout 6795/9766, Reward: 153.307±187.271, Episode_length: 409.200±310.877\n", ++ "Rollout 6796/9766, Reward: 241.793±62.101, Episode_length: 380.900±318.945\n", ++ "Rollout 6797/9766, Reward: 212.509±43.968, Episode_length: 472.600±334.150\n", ++ "Rollout 6798/9766, Reward: 249.956±53.461, Episode_length: 356.100±251.274\n", ++ "Rollout 6799/9766, Reward: 232.896±56.440, Episode_length: 385.300±309.040\n", ++ "Rollout 6800/9766, Reward: 225.388±48.774, Episode_length: 378.100±327.338\n", ++ "Rollout 6801/9766, Reward: 246.065±24.668, Episode_length: 229.700±83.288\n", ++ "Rollout 6802/9766, Reward: 176.098±93.547, Episode_length: 640.400±368.400\n", ++ "Rollout 6803/9766, Reward: 198.864±87.834, Episode_length: 396.600±331.527\n", ++ "Rollout 6804/9766, Reward: 203.638±124.970, Episode_length: 306.100±240.026\n", ++ "Rollout 6805/9766, Reward: 272.747±20.254, Episode_length: 205.200±35.476\n", ++ "Rollout 6806/9766, Reward: 235.254±55.971, Episode_length: 403.800±309.124\n", ++ "Rollout 6807/9766, Reward: 252.615±74.156, Episode_length: 204.000±46.325\n", ++ "Rollout 6808/9766, Reward: 245.993±63.644, Episode_length: 348.800±261.995\n", ++ "Rollout 6809/9766, Reward: 246.989±63.604, Episode_length: 371.800±315.556\n", ++ "Rollout 6810/9766, Reward: 265.119±46.876, Episode_length: 406.900±313.789\n", ++ "Rollout 6811/9766, Reward: 228.529±61.383, Episode_length: 419.700±380.264\n", ++ "Rollout 6812/9766, Reward: 249.584±38.580, Episode_length: 279.900±247.976\n", ++ "Rollout 6813/9766, Reward: 213.110±97.516, Episode_length: 382.900±333.044\n", ++ "Rollout 6814/9766, Reward: 260.813±33.498, Episode_length: 281.800±148.768\n", ++ "Rollout 6815/9766, Reward: 271.907±24.391, Episode_length: 263.100±101.263\n", ++ "Rollout 6816/9766, Reward: 226.555±44.487, Episode_length: 377.400±317.036\n", ++ "Rollout 6817/9766, Reward: 241.116±52.463, Episode_length: 468.500±313.239\n", ++ "Rollout 6818/9766, Reward: 214.412±52.060, Episode_length: 640.000±374.164\n", ++ "Rollout 6819/9766, Reward: 231.076±52.195, Episode_length: 569.100±355.747\n", ++ "Rollout 6820/9766, Reward: 214.649±60.537, Episode_length: 645.500±335.192\n", ++ "Rollout 6821/9766, Reward: 214.586±65.868, Episode_length: 509.500±400.810\n", ++ "Rollout 6822/9766, Reward: 242.565±61.581, Episode_length: 381.000±312.622\n", ++ "Rollout 6823/9766, Reward: 254.394±48.288, Episode_length: 336.100±249.586\n", ++ "Rollout 6824/9766, Reward: 245.232±39.164, Episode_length: 243.000±103.940\n", ++ "Rollout 6825/9766, Reward: 259.771±28.604, Episode_length: 211.800±86.002\n", ++ "Rollout 6826/9766, Reward: 259.808±36.358, Episode_length: 211.600±96.457\n", ++ "Rollout 6827/9766, Reward: 253.874±47.001, Episode_length: 249.200±60.110\n", ++ "Rollout 6828/9766, Reward: 237.773±58.790, Episode_length: 363.300±248.520\n", ++ "Rollout 6829/9766, Reward: 251.674±44.515, Episode_length: 269.000±127.777\n", ++ "Rollout 6830/9766, Reward: 112.005±438.680, Episode_length: 298.200±159.207\n", ++ "Rollout 6831/9766, Reward: 273.466±25.798, Episode_length: 186.600±41.195\n", ++ "Rollout 6832/9766, Reward: 268.281±19.248, Episode_length: 182.400±12.476\n", ++ "Rollout 6833/9766, Reward: 267.917±27.993, Episode_length: 195.800±53.931\n", ++ "Rollout 6834/9766, Reward: 262.735±44.175, Episode_length: 227.000±76.620\n", ++ "Rollout 6835/9766, Reward: 282.698±19.190, Episode_length: 186.400±23.118\n", ++ "Rollout 6836/9766, Reward: 276.826±20.963, Episode_length: 176.200±24.580\n", ++ "Rollout 6837/9766, Reward: 281.770±21.948, Episode_length: 190.200±16.011\n", ++ "Rollout 6838/9766, Reward: 154.249±394.424, Episode_length: 227.400±147.740\n", ++ "Rollout 6839/9766, Reward: 291.756±11.891, Episode_length: 186.300±19.406\n", ++ "Rollout 6840/9766, Reward: 274.547±33.329, Episode_length: 239.400±198.453\n", ++ "Rollout 6841/9766, Reward: 274.995±23.609, Episode_length: 170.800±21.075\n", ++ "Rollout 6842/9766, Reward: 263.420±32.763, Episode_length: 258.400±172.786\n", ++ "Rollout 6843/9766, Reward: 271.639±28.946, Episode_length: 246.000±130.960\n", ++ "Rollout 6844/9766, Reward: 287.688±24.869, Episode_length: 226.800±124.047\n", ++ "Rollout 6845/9766, Reward: 271.298±24.686, Episode_length: 195.000±112.380\n", ++ "Rollout 6846/9766, Reward: 277.418±15.605, Episode_length: 186.800±38.157\n", ++ "Rollout 6847/9766, Reward: 277.210±21.402, Episode_length: 200.800±99.362\n", ++ "Rollout 6848/9766, Reward: 274.269±9.123, Episode_length: 164.800±17.377\n", ++ "Rollout 6849/9766, Reward: 269.232±20.868, Episode_length: 184.600±66.521\n", ++ "Rollout 6850/9766, Reward: 267.648±27.076, Episode_length: 218.300±143.549\n", ++ "Rollout 6851/9766, Reward: 283.305±23.068, Episode_length: 183.100±21.598\n", ++ "Rollout 6852/9766, Reward: 282.500±16.752, Episode_length: 178.000±23.533\n", ++ "Rollout 6853/9766, Reward: 241.971±72.997, Episode_length: 284.500±266.005\n", ++ "Rollout 6854/9766, Reward: 256.889±49.954, Episode_length: 253.400±249.281\n", ++ "Rollout 6855/9766, Reward: 262.556±51.121, Episode_length: 256.100±248.235\n", ++ "Rollout 6856/9766, Reward: 254.614±37.750, Episode_length: 258.600±127.991\n", ++ "Rollout 6857/9766, Reward: 259.772±44.025, Episode_length: 306.000±259.892\n", ++ "Rollout 6858/9766, Reward: 252.825±27.831, Episode_length: 185.000±82.902\n", ++ "Rollout 6859/9766, Reward: 271.559±19.672, Episode_length: 187.500±44.055\n", ++ "Rollout 6860/9766, Reward: 267.151±22.707, Episode_length: 182.800±50.408\n", ++ "Rollout 6861/9766, Reward: 282.998±21.901, Episode_length: 200.700±46.176\n", ++ "Rollout 6862/9766, Reward: 271.181±26.386, Episode_length: 230.200±84.028\n", ++ "Rollout 6863/9766, Reward: 253.739±44.798, Episode_length: 282.100±246.330\n", ++ "Rollout 6864/9766, Reward: 264.633±37.045, Episode_length: 291.100±240.364\n", ++ "Rollout 6865/9766, Reward: 258.565±35.096, Episode_length: 197.200±49.036\n", ++ "Rollout 6866/9766, Reward: 277.200±34.762, Episode_length: 208.700±71.867\n", ++ "Rollout 6867/9766, Reward: 258.730±41.003, Episode_length: 224.100±46.621\n", ++ "Rollout 6868/9766, Reward: 259.564±28.632, Episode_length: 253.600±249.222\n", ++ "Rollout 6869/9766, Reward: 268.418±75.930, Episode_length: 270.700±244.720\n", ++ "Rollout 6870/9766, Reward: 269.756±24.053, Episode_length: 254.000±207.321\n", ++ "Rollout 6871/9766, Reward: -109.030±582.999, Episode_length: 344.600±240.474\n", ++ "Rollout 6872/9766, Reward: 274.389±21.710, Episode_length: 178.900±25.022\n", ++ "Rollout 6873/9766, Reward: 278.860±22.229, Episode_length: 174.500±33.257\n", ++ "Rollout 6874/9766, Reward: 283.032±17.332, Episode_length: 185.600±19.299\n", ++ "Rollout 6875/9766, Reward: 250.070±77.624, Episode_length: 191.500±90.130\n", ++ "Rollout 6876/9766, Reward: 269.140±28.660, Episode_length: 201.600±31.302\n", ++ "Rollout 6877/9766, Reward: 279.946±27.153, Episode_length: 196.500±28.980\n", ++ "Rollout 6878/9766, Reward: 253.051±33.225, Episode_length: 228.000±80.466\n", ++ "Rollout 6879/9766, Reward: 274.258±30.938, Episode_length: 200.400±39.825\n", ++ "Rollout 6880/9766, Reward: 253.667±43.161, Episode_length: 293.300±239.130\n", ++ "Rollout 6881/9766, Reward: 256.333±27.083, Episode_length: 237.400±75.905\n", ++ "Rollout 6882/9766, Reward: 279.885±15.878, Episode_length: 189.600±13.306\n", ++ "Rollout 6883/9766, Reward: 261.263±32.932, Episode_length: 213.300±92.887\n", ++ "Rollout 6884/9766, Reward: 275.584±17.185, Episode_length: 207.100±72.815\n", ++ "Rollout 6885/9766, Reward: 271.786±22.563, Episode_length: 177.900±29.361\n", ++ "Rollout 6886/9766, Reward: 265.227±28.365, Episode_length: 175.500±39.523\n", ++ "Rollout 6887/9766, Reward: 277.711±30.621, Episode_length: 267.400±191.399\n", ++ "Rollout 6888/9766, Reward: 258.590±35.086, Episode_length: 205.500±52.889\n", ++ "Rollout 6889/9766, Reward: 279.803±29.921, Episode_length: 203.500±26.489\n", ++ "Rollout 6890/9766, Reward: 274.028±23.172, Episode_length: 201.300±28.695\n", ++ "Rollout 6891/9766, Reward: 239.942±84.653, Episode_length: 273.000±185.023\n", ++ "Rollout 6892/9766, Reward: 270.243±19.722, Episode_length: 197.400±27.030\n", ++ "Rollout 6893/9766, Reward: 264.160±24.279, Episode_length: 228.400±48.173\n", ++ "Rollout 6894/9766, Reward: 257.069±33.327, Episode_length: 213.200±82.377\n", ++ "Rollout 6895/9766, Reward: 254.755±30.546, Episode_length: 184.800±29.498\n", ++ "Rollout 6896/9766, Reward: 278.765±33.010, Episode_length: 209.500±39.581\n", ++ "Rollout 6897/9766, Reward: 269.617±31.230, Episode_length: 196.400±27.915\n", ++ "Rollout 6898/9766, Reward: 275.149±36.645, Episode_length: 220.700±52.881\n", ++ "Rollout 6899/9766, Reward: 283.531±19.452, Episode_length: 189.600±20.343\n", ++ "Rollout 6900/9766, Reward: 274.160±19.047, Episode_length: 245.700±152.744\n", ++ "Rollout 6901/9766, Reward: 219.466±174.259, Episode_length: 199.900±73.693\n", ++ "Rollout 6902/9766, Reward: 277.566±29.554, Episode_length: 213.100±75.953\n", ++ "Rollout 6903/9766, Reward: 270.643±44.146, Episode_length: 227.200±89.658\n", ++ "Rollout 6904/9766, Reward: 270.052±37.797, Episode_length: 213.500±63.784\n", ++ "Rollout 6905/9766, Reward: 254.710±25.859, Episode_length: 191.300±42.970\n", ++ "Rollout 6906/9766, Reward: 273.705±27.013, Episode_length: 219.100±56.989\n", ++ "Rollout 6907/9766, Reward: 286.650±20.914, Episode_length: 193.300±20.234\n", ++ "Rollout 6908/9766, Reward: 204.060±68.038, Episode_length: 513.400±396.466\n", ++ "Rollout 6909/9766, Reward: 256.828±34.409, Episode_length: 311.100±240.096\n", ++ "Rollout 6910/9766, Reward: 251.893±34.415, Episode_length: 289.500±240.475\n", ++ "Rollout 6911/9766, Reward: 254.081±32.926, Episode_length: 246.600±85.491\n", ++ "Rollout 6912/9766, Reward: 272.795±30.909, Episode_length: 197.100±65.835\n", ++ "Rollout 6913/9766, Reward: 246.018±41.487, Episode_length: 292.200±246.085\n", ++ "Rollout 6914/9766, Reward: 275.141±15.532, Episode_length: 225.400±135.261\n", ++ "Rollout 6915/9766, Reward: 265.767±19.913, Episode_length: 199.300±48.415\n", ++ "Rollout 6916/9766, Reward: 222.689±83.295, Episode_length: 183.500±51.110\n", ++ "Rollout 6917/9766, Reward: 268.306±28.598, Episode_length: 214.900±131.182\n", ++ "Rollout 6918/9766, Reward: 285.586±16.057, Episode_length: 167.600±20.689\n", ++ "Rollout 6919/9766, Reward: 272.320±15.677, Episode_length: 170.600±17.351\n", ++ "Rollout 6920/9766, Reward: 280.589±31.081, Episode_length: 186.300±29.635\n", ++ "Rollout 6921/9766, Reward: 291.664±16.945, Episode_length: 186.400±26.609\n", ++ "Rollout 6922/9766, Reward: 273.879±20.425, Episode_length: 184.400±45.189\n", ++ "Rollout 6923/9766, Reward: 269.050±12.381, Episode_length: 165.400±12.101\n", ++ "Rollout 6924/9766, Reward: 270.425±27.622, Episode_length: 188.400±62.992\n", ++ "Rollout 6925/9766, Reward: 271.131±20.177, Episode_length: 183.800±31.099\n", ++ "Rollout 6926/9766, Reward: 291.198±11.407, Episode_length: 189.300±39.805\n", ++ "Rollout 6927/9766, Reward: 284.256±13.270, Episode_length: 190.100±36.820\n", ++ "Rollout 6928/9766, Reward: 282.529±19.887, Episode_length: 177.300±17.077\n", ++ "Rollout 6929/9766, Reward: 270.248±21.586, Episode_length: 194.400±62.934\n", ++ "Rollout 6930/9766, Reward: 275.080±34.995, Episode_length: 200.700±88.335\n", ++ "Rollout 6931/9766, Reward: 275.624±14.586, Episode_length: 175.500±16.735\n", ++ "Rollout 6932/9766, Reward: 273.451±22.391, Episode_length: 191.700±52.171\n", ++ "Rollout 6933/9766, Reward: 285.252±17.362, Episode_length: 195.300±29.846\n", ++ "Rollout 6934/9766, Reward: 277.234±20.894, Episode_length: 182.100±29.412\n", ++ "Rollout 6935/9766, Reward: 269.700±31.911, Episode_length: 189.600±53.412\n", ++ "Rollout 6936/9766, Reward: 265.581±18.772, Episode_length: 195.600±69.957\n", ++ "Rollout 6937/9766, Reward: 273.734±44.269, Episode_length: 268.300±247.138\n", ++ "Rollout 6938/9766, Reward: 293.699±21.517, Episode_length: 185.300±21.795\n", ++ "Rollout 6939/9766, Reward: 265.078±52.732, Episode_length: 252.400±250.304\n", ++ "Rollout 6940/9766, Reward: 288.200±40.892, Episode_length: 264.300±245.462\n", ++ "Rollout 6941/9766, Reward: 281.930±17.048, Episode_length: 169.000±18.563\n", ++ "Rollout 6942/9766, Reward: 277.335±29.890, Episode_length: 195.000±56.418\n", ++ "Rollout 6943/9766, Reward: 284.080±18.698, Episode_length: 174.600±18.943\n", ++ "Rollout 6944/9766, Reward: 287.320±18.992, Episode_length: 172.200±20.341\n", ++ "Rollout 6945/9766, Reward: 279.097±16.983, Episode_length: 156.500±20.210\n", ++ "Rollout 6946/9766, Reward: 268.974±36.041, Episode_length: 238.400±144.668\n", ++ "Rollout 6947/9766, Reward: 283.993±21.725, Episode_length: 199.400±59.760\n", ++ "Rollout 6948/9766, Reward: 275.404±17.499, Episode_length: 198.600±66.938\n", ++ "Rollout 6949/9766, Reward: 272.700±32.602, Episode_length: 214.100±61.534\n", ++ "Rollout 6950/9766, Reward: 273.156±25.782, Episode_length: 198.000±69.981\n", ++ "Rollout 6951/9766, Reward: 267.142±32.810, Episode_length: 191.000±56.434\n", ++ "Rollout 6952/9766, Reward: 278.039±19.688, Episode_length: 163.400±21.393\n", ++ "Rollout 6953/9766, Reward: 264.468±26.853, Episode_length: 206.100±105.927\n", ++ "Rollout 6954/9766, Reward: 269.682±36.685, Episode_length: 219.500±75.228\n", ++ "Rollout 6955/9766, Reward: 296.163±15.451, Episode_length: 177.000±18.105\n", ++ "Rollout 6956/9766, Reward: 293.457±8.247, Episode_length: 167.200±18.941\n", ++ "Rollout 6957/9766, Reward: 283.508±16.383, Episode_length: 160.600±19.090\n", ++ "Rollout 6958/9766, Reward: 279.566±27.543, Episode_length: 208.600±66.286\n", ++ "Rollout 6959/9766, Reward: 289.688±17.247, Episode_length: 173.200±19.884\n", ++ "Rollout 6960/9766, Reward: 253.428±76.706, Episode_length: 184.300±64.343\n", ++ "Rollout 6961/9766, Reward: 281.198±14.733, Episode_length: 164.400±20.141\n", ++ "Rollout 6962/9766, Reward: 285.271±16.425, Episode_length: 168.700±19.027\n", ++ "Rollout 6963/9766, Reward: 252.532±73.898, Episode_length: 196.300±73.264\n", ++ "Rollout 6964/9766, Reward: 287.099±16.689, Episode_length: 181.100±17.055\n", ++ "Rollout 6965/9766, Reward: 280.310±28.359, Episode_length: 191.100±58.690\n", ++ "Rollout 6966/9766, Reward: 270.149±37.413, Episode_length: 196.800±84.186\n", ++ "Rollout 6967/9766, Reward: 294.474±16.624, Episode_length: 175.900±20.181\n", ++ "Rollout 6968/9766, Reward: 278.747±10.215, Episode_length: 153.300±14.940\n", ++ "Rollout 6969/9766, Reward: 272.399±47.401, Episode_length: 249.100±251.234\n", ++ "Rollout 6970/9766, Reward: 290.373±17.120, Episode_length: 172.900±20.359\n", ++ "Rollout 6971/9766, Reward: 293.367±21.863, Episode_length: 180.800±23.379\n", ++ "Rollout 6972/9766, Reward: 274.993±18.668, Episode_length: 157.200±15.270\n", ++ "Rollout 6973/9766, Reward: 279.973±21.812, Episode_length: 169.200±25.087\n", ++ "Rollout 6974/9766, Reward: 288.590±20.343, Episode_length: 175.600±25.354\n", ++ "Rollout 6975/9766, Reward: 290.071±20.937, Episode_length: 185.100±21.622\n", ++ "Rollout 6976/9766, Reward: 290.433±25.043, Episode_length: 194.600±22.870\n", ++ "Rollout 6977/9766, Reward: 276.751±27.525, Episode_length: 197.100±70.375\n", ++ "Rollout 6978/9766, Reward: 267.750±32.149, Episode_length: 180.300±47.837\n", ++ "Rollout 6979/9766, Reward: 256.144±75.684, Episode_length: 164.600±28.640\n", ++ "Rollout 6980/9766, Reward: 280.475±23.393, Episode_length: 206.100±78.068\n", ++ "Rollout 6981/9766, Reward: 275.596±22.568, Episode_length: 170.600±15.551\n", ++ "Rollout 6982/9766, Reward: 263.606±51.955, Episode_length: 210.700±96.987\n", ++ "Rollout 6983/9766, Reward: 252.033±43.810, Episode_length: 234.000±91.310\n", ++ "Rollout 6984/9766, Reward: 278.613±13.240, Episode_length: 171.600±19.525\n", ++ "Rollout 6985/9766, Reward: 278.555±13.191, Episode_length: 175.500±13.411\n", ++ "Rollout 6986/9766, Reward: 283.377±15.610, Episode_length: 174.000±23.753\n", ++ "Rollout 6987/9766, Reward: 286.838±18.250, Episode_length: 174.000±11.054\n", ++ "Rollout 6988/9766, Reward: 283.413±22.364, Episode_length: 198.200±99.085\n", ++ "Rollout 6989/9766, Reward: 251.662±40.638, Episode_length: 240.300±253.754\n", ++ "Rollout 6990/9766, Reward: 286.192±22.452, Episode_length: 171.400±13.735\n", ++ "Rollout 6991/9766, Reward: 282.390±18.782, Episode_length: 177.800±12.536\n", ++ "Rollout 6992/9766, Reward: 282.383±17.712, Episode_length: 180.900±22.327\n", ++ "Rollout 6993/9766, Reward: 282.849±19.687, Episode_length: 176.500±22.914\n", ++ "Rollout 6994/9766, Reward: 287.723±22.568, Episode_length: 181.700±19.617\n", ++ "Rollout 6995/9766, Reward: 267.085±36.827, Episode_length: 400.000±364.005\n", ++ "Rollout 6996/9766, Reward: 238.069±53.148, Episode_length: 642.600±402.366\n", ++ "Rollout 6997/9766, Reward: 274.969±30.310, Episode_length: 197.100±72.098\n", ++ "Rollout 6998/9766, Reward: 287.062±21.076, Episode_length: 170.500±17.043\n", ++ "Rollout 6999/9766, Reward: 289.360±18.050, Episode_length: 165.000±24.674\n", ++ "Rollout 7000/9766, Reward: 279.918±20.293, Episode_length: 161.500±13.851\n", ++ "Rollout 7001/9766, Reward: 289.240±20.915, Episode_length: 166.000±21.392\n", ++ "Rollout 7002/9766, Reward: 291.181±11.706, Episode_length: 181.100±19.305\n", ++ "Rollout 7003/9766, Reward: 284.768±30.242, Episode_length: 193.100±47.429\n", ++ "Rollout 7004/9766, Reward: 268.723±36.516, Episode_length: 282.500±245.872\n", ++ "Rollout 7005/9766, Reward: 282.906±18.895, Episode_length: 174.500±19.755\n", ++ "Rollout 7006/9766, Reward: 277.811±32.743, Episode_length: 244.800±252.302\n", ++ "Rollout 7007/9766, Reward: 275.209±37.269, Episode_length: 249.900±250.844\n", ++ "Rollout 7008/9766, Reward: 261.900±46.707, Episode_length: 525.500±370.160\n", ++ "Rollout 7009/9766, Reward: 284.844±20.265, Episode_length: 170.900±21.408\n", ++ "Rollout 7010/9766, Reward: 274.645±23.147, Episode_length: 174.000±49.729\n", ++ "Rollout 7011/9766, Reward: 286.237±14.661, Episode_length: 163.500±24.602\n", ++ "Rollout 7012/9766, Reward: 286.706±22.129, Episode_length: 179.500±10.395\n", ++ "Rollout 7013/9766, Reward: 281.001±9.237, Episode_length: 172.500±17.212\n", ++ "Rollout 7014/9766, Reward: 251.266±72.883, Episode_length: 158.600±23.863\n", ++ "Rollout 7015/9766, Reward: 272.396±36.163, Episode_length: 210.200±67.953\n", ++ "Rollout 7016/9766, Reward: 286.656±20.479, Episode_length: 175.600±20.131\n", ++ "Rollout 7017/9766, Reward: 286.044±20.869, Episode_length: 242.200±187.583\n", ++ "Rollout 7018/9766, Reward: 282.075±13.216, Episode_length: 170.300±15.000\n", ++ "Rollout 7019/9766, Reward: 290.932±13.690, Episode_length: 173.400±16.663\n", ++ "Rollout 7020/9766, Reward: 278.904±21.948, Episode_length: 170.200±24.024\n", ++ "Rollout 7021/9766, Reward: 281.252±17.633, Episode_length: 171.500±18.747\n", ++ "Rollout 7022/9766, Reward: 279.694±11.950, Episode_length: 180.700±14.192\n", ++ "Rollout 7023/9766, Reward: 275.695±12.849, Episode_length: 172.400±13.403\n", ++ "Rollout 7024/9766, Reward: 255.692±82.334, Episode_length: 157.300±27.416\n", ++ "Rollout 7025/9766, Reward: 283.788±20.395, Episode_length: 178.700±22.046\n", ++ "Rollout 7026/9766, Reward: 244.173±123.825, Episode_length: 177.700±16.181\n", ++ "Rollout 7027/9766, Reward: 286.354±21.271, Episode_length: 163.200±19.894\n", ++ "Rollout 7028/9766, Reward: 289.575±18.792, Episode_length: 162.800±15.432\n", ++ "Rollout 7029/9766, Reward: 295.387±13.433, Episode_length: 175.100±25.406\n", ++ "Rollout 7030/9766, Reward: 267.158±74.989, Episode_length: 165.800±27.546\n", ++ "Rollout 7031/9766, Reward: 279.132±15.405, Episode_length: 167.600±16.716\n", ++ "Rollout 7032/9766, Reward: 273.960±18.659, Episode_length: 160.800±14.662\n", ++ "Rollout 7033/9766, Reward: 283.996±30.982, Episode_length: 191.900±63.332\n", ++ "Rollout 7034/9766, Reward: 266.451±16.451, Episode_length: 182.300±63.018\n", ++ "Rollout 7035/9766, Reward: 282.029±11.471, Episode_length: 171.900±21.718\n", ++ "Rollout 7036/9766, Reward: 275.136±12.111, Episode_length: 167.000±14.443\n", ++ "Rollout 7037/9766, Reward: 259.449±78.961, Episode_length: 153.500±27.951\n", ++ "Rollout 7038/9766, Reward: 283.573±19.788, Episode_length: 169.400±15.008\n", ++ "Rollout 7039/9766, Reward: 286.565±18.686, Episode_length: 166.400±18.440\n", ++ "Rollout 7040/9766, Reward: 274.671±27.767, Episode_length: 210.600±112.996\n", ++ "Rollout 7041/9766, Reward: 276.135±15.835, Episode_length: 169.400±22.509\n", ++ "Rollout 7042/9766, Reward: 272.865±7.870, Episode_length: 158.900±13.663\n", ++ "Rollout 7043/9766, Reward: 278.156±23.356, Episode_length: 169.600±22.743\n", ++ "Rollout 7044/9766, Reward: 269.964±23.148, Episode_length: 201.500±68.884\n", ++ "Rollout 7045/9766, Reward: 275.957±20.353, Episode_length: 163.900±21.375\n", ++ "Rollout 7046/9766, Reward: 284.349±17.868, Episode_length: 172.800±23.920\n", ++ "Rollout 7047/9766, Reward: 281.182±22.624, Episode_length: 191.300±34.097\n", ++ "Rollout 7048/9766, Reward: 276.023±29.073, Episode_length: 205.700±109.505\n", ++ "Rollout 7049/9766, Reward: 271.896±24.922, Episode_length: 207.700±107.449\n", ++ "Rollout 7050/9766, Reward: 273.870±25.409, Episode_length: 237.300±108.458\n", ++ "Rollout 7051/9766, Reward: 270.072±26.303, Episode_length: 198.000±50.337\n", ++ "Rollout 7052/9766, Reward: 266.785±44.828, Episode_length: 261.800±163.273\n", ++ "Rollout 7053/9766, Reward: 256.966±39.557, Episode_length: 228.100±71.604\n", ++ "Rollout 7054/9766, Reward: 184.037±205.748, Episode_length: 304.900±232.837\n", ++ "Rollout 7055/9766, Reward: 242.416±57.281, Episode_length: 326.400±234.634\n", ++ "Rollout 7056/9766, Reward: 250.020±30.002, Episode_length: 217.300±88.005\n", ++ "Rollout 7057/9766, Reward: 245.681±37.222, Episode_length: 211.100±44.604\n", ++ "Rollout 7058/9766, Reward: 204.102±91.666, Episode_length: 339.800±228.564\n", ++ "Rollout 7059/9766, Reward: 235.775±33.710, Episode_length: 248.700±82.253\n", ++ "Rollout 7060/9766, Reward: 247.615±39.482, Episode_length: 257.000±98.530\n", ++ "Rollout 7061/9766, Reward: 216.918±35.085, Episode_length: 293.800±53.482\n", ++ "Rollout 7062/9766, Reward: 238.957±58.999, Episode_length: 307.500±240.479\n", ++ "Rollout 7063/9766, Reward: 243.119±38.537, Episode_length: 340.000±194.083\n", ++ "Rollout 7064/9766, Reward: 245.478±41.304, Episode_length: 380.000±273.150\n", ++ "Rollout 7065/9766, Reward: 267.893±15.908, Episode_length: 188.800±42.061\n", ++ "Rollout 7066/9766, Reward: 247.805±43.130, Episode_length: 247.500±90.072\n", ++ "Rollout 7067/9766, Reward: 272.671±33.932, Episode_length: 337.300±238.450\n", ++ "Rollout 7068/9766, Reward: 255.061±25.138, Episode_length: 222.700±51.400\n", ++ "Rollout 7069/9766, Reward: 237.849±40.102, Episode_length: 328.900±147.644\n", ++ "Rollout 7070/9766, Reward: 253.698±35.663, Episode_length: 246.200±88.213\n", ++ "Rollout 7071/9766, Reward: 257.898±26.261, Episode_length: 209.100±50.607\n", ++ "Rollout 7072/9766, Reward: 244.316±25.636, Episode_length: 228.600±50.640\n", ++ "Rollout 7073/9766, Reward: 252.308±32.409, Episode_length: 232.400±42.332\n", ++ "Rollout 7074/9766, Reward: 255.654±40.812, Episode_length: 243.800±106.006\n", ++ "Rollout 7075/9766, Reward: 240.828±60.716, Episode_length: 201.300±45.824\n", ++ "Rollout 7076/9766, Reward: 236.708±73.525, Episode_length: 210.000±61.410\n", ++ "Rollout 7077/9766, Reward: 258.190±68.494, Episode_length: 203.600±35.288\n", ++ "Rollout 7078/9766, Reward: 248.005±42.435, Episode_length: 322.700±238.301\n", ++ "Rollout 7079/9766, Reward: 262.712±40.204, Episode_length: 228.300±70.163\n", ++ "Rollout 7080/9766, Reward: 260.504±31.355, Episode_length: 200.700±35.071\n", ++ "Rollout 7081/9766, Reward: 254.554±30.308, Episode_length: 217.100±50.157\n", ++ "Rollout 7082/9766, Reward: 254.127±24.578, Episode_length: 193.500±42.889\n", ++ "Rollout 7083/9766, Reward: 267.583±24.814, Episode_length: 227.800±87.415\n", ++ "Rollout 7084/9766, Reward: 260.673±34.706, Episode_length: 220.600±71.711\n", ++ "Rollout 7085/9766, Reward: 253.609±33.081, Episode_length: 220.900±83.395\n", ++ "Rollout 7086/9766, Reward: 252.079±53.193, Episode_length: 290.900±240.345\n", ++ "Rollout 7087/9766, Reward: 279.385±17.057, Episode_length: 185.000±13.557\n", ++ "Rollout 7088/9766, Reward: 264.475±32.255, Episode_length: 219.200±73.741\n", ++ "Rollout 7089/9766, Reward: 255.772±71.526, Episode_length: 249.500±127.999\n", ++ "Rollout 7090/9766, Reward: 260.113±32.448, Episode_length: 230.400±102.051\n", ++ "Rollout 7091/9766, Reward: 244.740±65.391, Episode_length: 233.000±168.969\n", ++ "Rollout 7092/9766, Reward: 269.115±33.895, Episode_length: 279.400±161.328\n", ++ "Rollout 7093/9766, Reward: 254.657±41.853, Episode_length: 299.000±135.935\n", ++ "Rollout 7094/9766, Reward: 265.221±24.476, Episode_length: 247.200±151.928\n", ++ "Rollout 7095/9766, Reward: 275.755±18.859, Episode_length: 237.800±147.723\n", ++ "Rollout 7096/9766, Reward: 259.036±49.031, Episode_length: 260.500±246.616\n", ++ "Rollout 7097/9766, Reward: 244.096±45.207, Episode_length: 373.500±255.836\n", ++ "Rollout 7098/9766, Reward: 233.399±74.039, Episode_length: 448.700±338.266\n", ++ "Rollout 7099/9766, Reward: 292.528±15.947, Episode_length: 198.300±24.952\n", ++ "Rollout 7100/9766, Reward: 264.536±56.266, Episode_length: 328.200±292.187\n", ++ "Rollout 7101/9766, Reward: 277.498±17.134, Episode_length: 180.400±22.051\n", ++ "Rollout 7102/9766, Reward: 286.151±16.323, Episode_length: 181.500±14.705\n", ++ "Rollout 7103/9766, Reward: 256.541±56.194, Episode_length: 340.900±329.858\n", ++ "Rollout 7104/9766, Reward: 285.844±15.515, Episode_length: 174.700±13.046\n", ++ "Rollout 7105/9766, Reward: 282.868±17.833, Episode_length: 178.200±16.810\n", ++ "Rollout 7106/9766, Reward: 273.979±53.877, Episode_length: 264.400±246.000\n", ++ "Rollout 7107/9766, Reward: 279.907±21.160, Episode_length: 166.100±12.872\n", ++ "Rollout 7108/9766, Reward: 250.863±60.339, Episode_length: 341.300±323.299\n", ++ "Rollout 7109/9766, Reward: 267.432±53.720, Episode_length: 255.300±248.755\n", ++ "Rollout 7110/9766, Reward: 283.936±20.514, Episode_length: 174.600±19.459\n", ++ "Rollout 7111/9766, Reward: 269.375±53.994, Episode_length: 266.100±245.547\n", ++ "Rollout 7112/9766, Reward: 274.884±26.427, Episode_length: 218.300±142.815\n", ++ "Rollout 7113/9766, Reward: 272.383±21.404, Episode_length: 174.400±17.631\n", ++ "Rollout 7114/9766, Reward: 289.126±20.318, Episode_length: 186.300±13.799\n", ++ "Rollout 7115/9766, Reward: 254.742±36.766, Episode_length: 286.100±161.781\n", ++ "Rollout 7116/9766, Reward: 281.208±24.481, Episode_length: 188.100±18.080\n", ++ "Rollout 7117/9766, Reward: 280.964±17.751, Episode_length: 178.700±17.053\n", ++ "Rollout 7118/9766, Reward: 269.382±15.182, Episode_length: 169.200±15.309\n", ++ "Rollout 7119/9766, Reward: 268.476±25.419, Episode_length: 197.300±82.444\n", ++ "Rollout 7120/9766, Reward: 263.034±25.410, Episode_length: 228.900±111.296\n", ++ "Rollout 7121/9766, Reward: 251.560±38.457, Episode_length: 341.100±274.574\n", ++ "Rollout 7122/9766, Reward: 254.968±52.027, Episode_length: 285.200±255.089\n", ++ "Rollout 7123/9766, Reward: 242.620±54.474, Episode_length: 293.800±276.281\n", ++ "Rollout 7124/9766, Reward: 261.093±54.004, Episode_length: 256.100±248.538\n", ++ "Rollout 7125/9766, Reward: 261.188±36.279, Episode_length: 295.200±260.715\n", ++ "Rollout 7126/9766, Reward: 282.513±20.602, Episode_length: 197.800±55.279\n", ++ "Rollout 7127/9766, Reward: 281.642±10.687, Episode_length: 179.000±12.190\n", ++ "Rollout 7128/9766, Reward: 237.356±77.674, Episode_length: 279.400±264.021\n", ++ "Rollout 7129/9766, Reward: 277.614±34.468, Episode_length: 261.500±223.747\n", ++ "Rollout 7130/9766, Reward: 276.198±13.856, Episode_length: 186.900±27.355\n", ++ "Rollout 7131/9766, Reward: 258.726±31.311, Episode_length: 218.000±83.466\n", ++ "Rollout 7132/9766, Reward: 257.597±42.373, Episode_length: 253.400±249.965\n", ++ "Rollout 7133/9766, Reward: 268.871±28.466, Episode_length: 221.500±112.838\n", ++ "Rollout 7134/9766, Reward: 263.328±22.093, Episode_length: 177.700±21.359\n", ++ "Rollout 7135/9766, Reward: 269.074±18.637, Episode_length: 218.000±138.068\n", ++ "Rollout 7136/9766, Reward: 263.857±31.592, Episode_length: 257.600±134.280\n", ++ "Rollout 7137/9766, Reward: 278.103±13.500, Episode_length: 181.000±19.616\n", ++ "Rollout 7138/9766, Reward: 276.485±34.908, Episode_length: 201.200±72.639\n", ++ "Rollout 7139/9766, Reward: 276.573±19.096, Episode_length: 178.600±32.184\n", ++ "Rollout 7140/9766, Reward: 277.002±21.660, Episode_length: 168.500±18.118\n", ++ "Rollout 7141/9766, Reward: 270.317±15.359, Episode_length: 200.800±79.881\n", ++ "Rollout 7142/9766, Reward: 251.350±31.959, Episode_length: 222.800±76.063\n", ++ "Rollout 7143/9766, Reward: 240.005±58.400, Episode_length: 375.800±321.002\n", ++ "Rollout 7144/9766, Reward: 278.654±14.820, Episode_length: 183.100±27.657\n", ++ "Rollout 7145/9766, Reward: 104.801±358.994, Episode_length: 305.900±181.658\n", ++ "Rollout 7146/9766, Reward: 229.006±57.005, Episode_length: 368.800±238.001\n", ++ "Rollout 7147/9766, Reward: 237.353±36.094, Episode_length: 381.300±260.730\n", ++ "Rollout 7148/9766, Reward: 235.304±102.820, Episode_length: 226.700±89.730\n", ++ "Rollout 7149/9766, Reward: 236.637±43.274, Episode_length: 364.200±219.734\n", ++ "Rollout 7150/9766, Reward: 253.041±45.916, Episode_length: 228.700±70.297\n", ++ "Rollout 7151/9766, Reward: 252.972±37.339, Episode_length: 197.400±51.546\n", ++ "Rollout 7152/9766, Reward: 242.064±56.254, Episode_length: 300.800±243.274\n", ++ "Rollout 7153/9766, Reward: 241.942±54.058, Episode_length: 292.000±117.979\n", ++ "Rollout 7154/9766, Reward: 246.395±39.440, Episode_length: 237.700±81.742\n", ++ "Rollout 7155/9766, Reward: 185.176±237.961, Episode_length: 369.000±276.032\n", ++ "Rollout 7156/9766, Reward: 245.527±32.924, Episode_length: 238.000±68.930\n", ++ "Rollout 7157/9766, Reward: 281.506±22.545, Episode_length: 243.600±167.298\n", ++ "Rollout 7158/9766, Reward: 162.580±236.669, Episode_length: 338.600±262.052\n", ++ "Rollout 7159/9766, Reward: 255.640±72.522, Episode_length: 206.100±45.434\n", ++ "Rollout 7160/9766, Reward: 273.448±20.785, Episode_length: 205.800±69.446\n", ++ "Rollout 7161/9766, Reward: 242.463±46.513, Episode_length: 241.600±94.126\n", ++ "Rollout 7162/9766, Reward: 265.986±25.806, Episode_length: 190.300±60.417\n", ++ "Rollout 7163/9766, Reward: 268.335±43.697, Episode_length: 265.400±245.944\n", ++ "Rollout 7164/9766, Reward: 273.229±33.209, Episode_length: 206.300±69.390\n", ++ "Rollout 7165/9766, Reward: 282.274±22.993, Episode_length: 176.200±15.478\n", ++ "Rollout 7166/9766, Reward: 275.511±28.980, Episode_length: 196.100±53.826\n", ++ "Rollout 7167/9766, Reward: 289.334±14.026, Episode_length: 199.000±40.706\n", ++ "Rollout 7168/9766, Reward: 261.569±47.443, Episode_length: 231.100±115.769\n", ++ "Rollout 7169/9766, Reward: 275.050±16.022, Episode_length: 196.400±66.260\n", ++ "Rollout 7170/9766, Reward: 262.172±31.101, Episode_length: 195.500±51.484\n", ++ "Rollout 7171/9766, Reward: 157.290±317.991, Episode_length: 238.300±143.413\n", ++ "Rollout 7172/9766, Reward: 286.842±11.425, Episode_length: 184.500±29.783\n", ++ "Rollout 7173/9766, Reward: 261.716±23.078, Episode_length: 257.400±244.769\n", ++ "Rollout 7174/9766, Reward: 176.703±255.534, Episode_length: 260.700±158.828\n", ++ "Rollout 7175/9766, Reward: 262.179±30.834, Episode_length: 189.300±63.811\n", ++ "Rollout 7176/9766, Reward: 276.260±37.090, Episode_length: 223.000±88.867\n", ++ "Rollout 7177/9766, Reward: 284.711±13.834, Episode_length: 180.700±19.698\n", ++ "Rollout 7178/9766, Reward: 265.712±30.867, Episode_length: 252.400±116.654\n", ++ "Rollout 7179/9766, Reward: 280.036±24.199, Episode_length: 204.100±52.068\n", ++ "Rollout 7180/9766, Reward: 279.026±24.895, Episode_length: 206.800±37.365\n", ++ "Rollout 7181/9766, Reward: 263.254±50.689, Episode_length: 217.500±96.770\n", ++ "Rollout 7182/9766, Reward: 273.537±27.031, Episode_length: 192.900±35.826\n", ++ "Rollout 7183/9766, Reward: 266.138±41.489, Episode_length: 269.900±246.623\n", ++ "Rollout 7184/9766, Reward: 269.183±27.307, Episode_length: 187.000±49.703\n", ++ "Rollout 7185/9766, Reward: 284.489±31.814, Episode_length: 205.600±55.924\n", ++ "Rollout 7186/9766, Reward: 268.368±19.366, Episode_length: 186.400±45.625\n", ++ "Rollout 7187/9766, Reward: 276.447±23.662, Episode_length: 259.800±188.647\n", ++ "Rollout 7188/9766, Reward: 122.588±411.951, Episode_length: 298.000±195.214\n", ++ "Rollout 7189/9766, Reward: 203.078±210.983, Episode_length: 203.800±76.563\n", ++ "Rollout 7190/9766, Reward: 283.623±21.192, Episode_length: 187.400±18.467\n", ++ "Rollout 7191/9766, Reward: 271.633±14.077, Episode_length: 184.600±31.882\n", ++ "Rollout 7192/9766, Reward: 250.475±16.207, Episode_length: 224.900±106.466\n", ++ "Rollout 7193/9766, Reward: 261.942±20.153, Episode_length: 201.600±64.837\n", ++ "Rollout 7194/9766, Reward: 284.929±26.006, Episode_length: 204.000±71.903\n", ++ "Rollout 7195/9766, Reward: 281.766±19.567, Episode_length: 189.700±22.321\n", ++ "Rollout 7196/9766, Reward: 281.600±23.218, Episode_length: 209.600±57.296\n", ++ "Rollout 7197/9766, Reward: 274.506±18.558, Episode_length: 171.100±30.095\n", ++ "Rollout 7198/9766, Reward: 277.239±34.575, Episode_length: 190.400±36.650\n", ++ "Rollout 7199/9766, Reward: 274.475±23.130, Episode_length: 267.600±240.786\n", ++ "Rollout 7200/9766, Reward: 275.968±23.528, Episode_length: 215.300±67.612\n", ++ "Rollout 7201/9766, Reward: 277.119±22.701, Episode_length: 179.000±17.618\n", ++ "Rollout 7202/9766, Reward: 272.360±8.795, Episode_length: 164.100±19.170\n", ++ "Rollout 7203/9766, Reward: 277.994±30.791, Episode_length: 197.100±36.314\n", ++ "Rollout 7204/9766, Reward: 262.904±19.204, Episode_length: 192.800±62.874\n", ++ "Rollout 7205/9766, Reward: 277.445±21.590, Episode_length: 177.400±23.988\n", ++ "Rollout 7206/9766, Reward: 271.119±35.564, Episode_length: 199.300±43.460\n", ++ "Rollout 7207/9766, Reward: 273.746±27.948, Episode_length: 249.100±178.010\n", ++ "Rollout 7208/9766, Reward: 245.176±82.458, Episode_length: 199.100±96.651\n", ++ "Rollout 7209/9766, Reward: 267.569±36.027, Episode_length: 202.900±50.514\n", ++ "Rollout 7210/9766, Reward: 260.953±40.647, Episode_length: 239.600±147.176\n", ++ "Rollout 7211/9766, Reward: 273.182±35.605, Episode_length: 199.500±58.758\n", ++ "Rollout 7212/9766, Reward: 272.191±15.781, Episode_length: 171.100±21.533\n", ++ "Rollout 7213/9766, Reward: 275.774±27.106, Episode_length: 207.100±105.830\n", ++ "Rollout 7214/9766, Reward: 281.652±18.359, Episode_length: 166.100±16.349\n", ++ "Rollout 7215/9766, Reward: 277.515±17.109, Episode_length: 155.900±15.877\n", ++ "Rollout 7216/9766, Reward: 282.597±32.592, Episode_length: 232.000±67.713\n", ++ "Rollout 7217/9766, Reward: 265.707±38.680, Episode_length: 228.500±106.383\n", ++ "Rollout 7218/9766, Reward: 271.029±20.989, Episode_length: 204.800±121.572\n", ++ "Rollout 7219/9766, Reward: 268.854±31.861, Episode_length: 191.100±78.327\n", ++ "Rollout 7220/9766, Reward: 280.479±19.955, Episode_length: 179.400±19.174\n", ++ "Rollout 7221/9766, Reward: 264.236±23.464, Episode_length: 237.400±133.282\n", ++ "Rollout 7222/9766, Reward: 268.154±20.256, Episode_length: 172.700±18.937\n", ++ "Rollout 7223/9766, Reward: 292.343±18.203, Episode_length: 198.700±22.654\n", ++ "Rollout 7224/9766, Reward: 275.662±12.892, Episode_length: 154.800±16.928\n", ++ "Rollout 7225/9766, Reward: 275.235±18.163, Episode_length: 175.200±19.266\n", ++ "Rollout 7226/9766, Reward: 276.359±15.658, Episode_length: 190.200±58.210\n", ++ "Rollout 7227/9766, Reward: 280.297±19.973, Episode_length: 191.900±51.479\n", ++ "Rollout 7228/9766, Reward: 280.961±21.213, Episode_length: 185.000±20.981\n", ++ "Rollout 7229/9766, Reward: 274.137±20.972, Episode_length: 167.200±18.335\n", ++ "Rollout 7230/9766, Reward: 270.594±19.329, Episode_length: 171.000±20.060\n", ++ "Rollout 7231/9766, Reward: 249.845±51.316, Episode_length: 280.400±245.855\n", ++ "Rollout 7232/9766, Reward: 255.933±23.708, Episode_length: 218.100±88.823\n", ++ "Rollout 7233/9766, Reward: 243.210±93.114, Episode_length: 282.900±258.669\n", ++ "Rollout 7234/9766, Reward: 279.745±16.792, Episode_length: 185.300±12.232\n", ++ "Rollout 7235/9766, Reward: 274.982±22.180, Episode_length: 177.000±26.405\n", ++ "Rollout 7236/9766, Reward: 286.244±20.662, Episode_length: 182.800±18.038\n", ++ "Rollout 7237/9766, Reward: 284.946±15.053, Episode_length: 183.300±17.945\n", ++ "Rollout 7238/9766, Reward: 274.288±24.827, Episode_length: 181.800±41.883\n", ++ "Rollout 7239/9766, Reward: 267.706±29.984, Episode_length: 200.300±87.400\n", ++ "Rollout 7240/9766, Reward: 280.118±14.375, Episode_length: 180.400±18.195\n", ++ "Rollout 7241/9766, Reward: 280.354±14.379, Episode_length: 185.800±16.351\n", ++ "Rollout 7242/9766, Reward: 217.506±79.947, Episode_length: 404.500±314.323\n", ++ "Rollout 7243/9766, Reward: 273.744±17.067, Episode_length: 217.800±82.590\n", ++ "Rollout 7244/9766, Reward: 248.637±55.218, Episode_length: 300.200±238.302\n", ++ "Rollout 7245/9766, Reward: 271.105±25.484, Episode_length: 199.200±40.647\n", ++ "Rollout 7246/9766, Reward: 246.853±41.383, Episode_length: 314.500±196.168\n", ++ "Rollout 7247/9766, Reward: 272.560±13.962, Episode_length: 175.700±27.713\n", ++ "Rollout 7248/9766, Reward: 267.955±22.215, Episode_length: 237.500±121.345\n", ++ "Rollout 7249/9766, Reward: 270.804±19.221, Episode_length: 209.700±87.669\n", ++ "Rollout 7250/9766, Reward: 282.202±18.711, Episode_length: 194.000±22.064\n", ++ "Rollout 7251/9766, Reward: 255.515±36.129, Episode_length: 223.500±65.238\n", ++ "Rollout 7252/9766, Reward: 206.982±96.574, Episode_length: 380.200±238.474\n", ++ "Rollout 7253/9766, Reward: 250.215±50.816, Episode_length: 336.300±249.201\n", ++ "Rollout 7254/9766, Reward: 220.735±53.291, Episode_length: 422.500±324.750\n", ++ "Rollout 7255/9766, Reward: 214.860±52.140, Episode_length: 446.200±336.223\n", ++ "Rollout 7256/9766, Reward: 251.012±28.401, Episode_length: 253.700±117.393\n", ++ "Rollout 7257/9766, Reward: 214.829±59.120, Episode_length: 402.900±309.343\n", ++ "Rollout 7258/9766, Reward: 236.932±35.226, Episode_length: 297.300±180.787\n", ++ "Rollout 7259/9766, Reward: 205.570±52.803, Episode_length: 449.400±288.821\n", ++ "Rollout 7260/9766, Reward: 197.455±52.848, Episode_length: 549.700±370.894\n", ++ "Rollout 7261/9766, Reward: 210.469±83.911, Episode_length: 378.000±323.174\n", ++ "Rollout 7262/9766, Reward: 237.991±55.240, Episode_length: 357.300±323.181\n", ++ "Rollout 7263/9766, Reward: 185.867±45.565, Episode_length: 517.200±323.200\n", ++ "Rollout 7264/9766, Reward: 178.253±96.003, Episode_length: 468.400±353.907\n", ++ "Rollout 7265/9766, Reward: 182.191±98.111, Episode_length: 475.800±347.757\n", ++ "Rollout 7266/9766, Reward: 223.311±58.189, Episode_length: 319.700±240.924\n", ++ "Rollout 7267/9766, Reward: 206.669±67.447, Episode_length: 468.100±352.470\n", ++ "Rollout 7268/9766, Reward: 185.196±93.202, Episode_length: 488.800±346.252\n", ++ "Rollout 7269/9766, Reward: 178.604±76.778, Episode_length: 576.100±357.310\n", ++ "Rollout 7270/9766, Reward: 211.410±54.132, Episode_length: 396.500±308.874\n", ++ "Rollout 7271/9766, Reward: 227.815±27.465, Episode_length: 345.000±225.235\n", ++ "Rollout 7272/9766, Reward: 238.357±37.452, Episode_length: 319.200±259.868\n", ++ "Rollout 7273/9766, Reward: 245.040±18.257, Episode_length: 379.100±262.712\n", ++ "Rollout 7274/9766, Reward: 223.277±43.443, Episode_length: 338.900±176.660\n", ++ "Rollout 7275/9766, Reward: 215.090±52.911, Episode_length: 593.400±366.352\n", ++ "Rollout 7276/9766, Reward: 190.889±59.632, Episode_length: 757.500±371.262\n", ++ "Rollout 7277/9766, Reward: 205.650±56.669, Episode_length: 653.400±363.364\n", ++ "Rollout 7278/9766, Reward: 276.874±12.943, Episode_length: 215.600±64.834\n", ++ "Rollout 7279/9766, Reward: 268.545±38.150, Episode_length: 303.500±227.804\n", ++ "Rollout 7280/9766, Reward: 268.878±40.685, Episode_length: 261.300±190.895\n", ++ "Rollout 7281/9766, Reward: 273.164±39.042, Episode_length: 261.100±247.222\n", ++ "Rollout 7282/9766, Reward: 285.444±12.482, Episode_length: 173.500±19.075\n", ++ "Rollout 7283/9766, Reward: 280.107±27.122, Episode_length: 295.100±254.650\n", ++ "Rollout 7284/9766, Reward: 262.366±49.709, Episode_length: 320.200±264.748\n", ++ "Rollout 7285/9766, Reward: 272.726±18.436, Episode_length: 175.500±20.061\n", ++ "Rollout 7286/9766, Reward: 246.001±50.987, Episode_length: 275.500±257.404\n", ++ "Rollout 7287/9766, Reward: 273.445±14.917, Episode_length: 165.700±19.509\n", ++ "Rollout 7288/9766, Reward: 247.747±81.958, Episode_length: 167.400±27.471\n", ++ "Rollout 7289/9766, Reward: 269.348±22.621, Episode_length: 216.400±120.135\n", ++ "Rollout 7290/9766, Reward: 272.513±12.310, Episode_length: 166.300±9.078\n", ++ "Rollout 7291/9766, Reward: 276.273±12.311, Episode_length: 171.000±14.269\n", ++ "Rollout 7292/9766, Reward: 249.958±68.049, Episode_length: 165.500±23.892\n", ++ "Rollout 7293/9766, Reward: 245.109±79.482, Episode_length: 180.900±62.353\n", ++ "Rollout 7294/9766, Reward: 269.007±24.420, Episode_length: 207.000±76.824\n", ++ "Rollout 7295/9766, Reward: 285.223±24.086, Episode_length: 176.000±16.947\n", ++ "Rollout 7296/9766, Reward: 278.901±36.103, Episode_length: 226.200±90.831\n", ++ "Rollout 7297/9766, Reward: 284.256±36.979, Episode_length: 215.900±95.249\n", ++ "Rollout 7298/9766, Reward: 289.105±16.516, Episode_length: 165.800±28.819\n", ++ "Rollout 7299/9766, Reward: 263.111±19.765, Episode_length: 204.400±87.732\n", ++ "Rollout 7300/9766, Reward: 276.797±18.040, Episode_length: 314.300±215.107\n", ++ "Rollout 7301/9766, Reward: 284.600±32.817, Episode_length: 258.300±248.593\n", ++ "Rollout 7302/9766, Reward: 284.803±16.753, Episode_length: 164.800±17.434\n", ++ "Rollout 7303/9766, Reward: 289.044±14.092, Episode_length: 173.900±14.167\n", ++ "Rollout 7304/9766, Reward: 275.369±21.717, Episode_length: 188.600±86.447\n", ++ "Rollout 7305/9766, Reward: 291.088±21.272, Episode_length: 165.700±17.228\n", ++ "Rollout 7306/9766, Reward: 247.988±124.968, Episode_length: 180.700±14.164\n", ++ "Rollout 7307/9766, Reward: 291.987±18.657, Episode_length: 175.200±13.790\n", ++ "Rollout 7308/9766, Reward: 271.723±53.722, Episode_length: 330.200±305.932\n", ++ "Rollout 7309/9766, Reward: 281.916±17.913, Episode_length: 202.700±83.236\n", ++ "Rollout 7310/9766, Reward: 278.857±22.172, Episode_length: 209.900±116.172\n", ++ "Rollout 7311/9766, Reward: 292.270±15.895, Episode_length: 222.500±135.945\n", ++ "Rollout 7312/9766, Reward: 286.799±18.782, Episode_length: 172.300±18.106\n", ++ "Rollout 7313/9766, Reward: 274.195±28.269, Episode_length: 165.000±20.362\n", ++ "Rollout 7314/9766, Reward: 277.137±25.712, Episode_length: 169.200±19.833\n", ++ "Rollout 7315/9766, Reward: 265.556±35.250, Episode_length: 243.100±151.979\n", ++ "Rollout 7316/9766, Reward: 282.046±15.032, Episode_length: 169.800±15.854\n", ++ "Rollout 7317/9766, Reward: 266.004±30.707, Episode_length: 232.300±83.200\n", ++ "Rollout 7318/9766, Reward: 279.270±18.091, Episode_length: 200.400±58.262\n", ++ "Rollout 7319/9766, Reward: 249.848±17.010, Episode_length: 221.500±110.749\n", ++ "Rollout 7320/9766, Reward: 271.860±27.677, Episode_length: 214.600±92.868\n", ++ "Rollout 7321/9766, Reward: 270.940±35.239, Episode_length: 286.600±245.244\n", ++ "Rollout 7322/9766, Reward: 273.249±18.609, Episode_length: 211.800±66.716\n", ++ "Rollout 7323/9766, Reward: 280.657±16.670, Episode_length: 211.700±70.870\n", ++ "Rollout 7324/9766, Reward: 269.590±32.771, Episode_length: 214.600±136.099\n", ++ "Rollout 7325/9766, Reward: 292.195±12.475, Episode_length: 177.100±18.102\n", ++ "Rollout 7326/9766, Reward: 289.516±20.493, Episode_length: 191.700±16.081\n", ++ "Rollout 7327/9766, Reward: 271.138±25.611, Episode_length: 203.600±56.518\n", ++ "Rollout 7328/9766, Reward: 276.412±16.017, Episode_length: 160.800±18.713\n", ++ "Rollout 7329/9766, Reward: 281.020±23.761, Episode_length: 175.200±21.949\n", ++ "Rollout 7330/9766, Reward: 264.765±28.119, Episode_length: 226.700±134.876\n", ++ "Rollout 7331/9766, Reward: 285.697±23.699, Episode_length: 182.800±11.382\n", ++ "Rollout 7332/9766, Reward: 258.241±34.718, Episode_length: 222.500±86.392\n", ++ "Rollout 7333/9766, Reward: 245.892±65.675, Episode_length: 162.500±25.508\n", ++ "Rollout 7334/9766, Reward: 264.182±24.258, Episode_length: 196.800±59.356\n", ++ "Rollout 7335/9766, Reward: 266.584±16.341, Episode_length: 164.100±17.666\n", ++ "Rollout 7336/9766, Reward: 274.092±32.876, Episode_length: 203.200±37.298\n", ++ "Rollout 7337/9766, Reward: 261.392±39.772, Episode_length: 220.400±101.455\n", ++ "Rollout 7338/9766, Reward: 255.180±24.272, Episode_length: 205.800±46.445\n", ++ "Rollout 7339/9766, Reward: 271.252±14.108, Episode_length: 169.700±23.938\n", ++ "Rollout 7340/9766, Reward: 262.292±23.837, Episode_length: 243.800±139.445\n", ++ "Rollout 7341/9766, Reward: 267.752±31.432, Episode_length: 207.900±59.097\n", ++ "Rollout 7342/9766, Reward: 270.704±34.396, Episode_length: 260.400±96.114\n", ++ "Rollout 7343/9766, Reward: 282.773±19.022, Episode_length: 173.700±16.608\n", ++ "Rollout 7344/9766, Reward: 272.211±19.716, Episode_length: 199.200±42.955\n", ++ "Rollout 7345/9766, Reward: 230.034±61.539, Episode_length: 302.700±246.717\n", ++ "Rollout 7346/9766, Reward: 255.829±36.533, Episode_length: 229.200±83.270\n", ++ "Rollout 7347/9766, Reward: 270.661±26.187, Episode_length: 197.300±51.500\n", ++ "Rollout 7348/9766, Reward: 267.441±29.338, Episode_length: 199.700±48.283\n", ++ "Rollout 7349/9766, Reward: 276.636±15.029, Episode_length: 201.000±38.512\n", ++ "Rollout 7350/9766, Reward: 236.667±57.085, Episode_length: 335.600±254.508\n", ++ "Rollout 7351/9766, Reward: 268.851±20.876, Episode_length: 187.900±28.550\n", ++ "Rollout 7352/9766, Reward: 233.059±56.487, Episode_length: 317.600±238.917\n", ++ "Rollout 7353/9766, Reward: 263.133±60.308, Episode_length: 290.200±238.166\n", ++ "Rollout 7354/9766, Reward: 270.333±29.911, Episode_length: 196.700±22.760\n", ++ "Rollout 7355/9766, Reward: 271.346±21.789, Episode_length: 203.800±52.065\n", ++ "Rollout 7356/9766, Reward: 278.726±18.026, Episode_length: 183.300±25.432\n", ++ "Rollout 7357/9766, Reward: 273.603±24.805, Episode_length: 197.000±31.394\n", ++ "Rollout 7358/9766, Reward: 202.729±69.356, Episode_length: 348.900±245.914\n", ++ "Rollout 7359/9766, Reward: 241.927±58.940, Episode_length: 379.700±315.809\n", ++ "Rollout 7360/9766, Reward: 221.608±87.908, Episode_length: 266.000±248.307\n", ++ "Rollout 7361/9766, Reward: 265.839±17.947, Episode_length: 182.500±27.904\n", ++ "Rollout 7362/9766, Reward: 269.892±25.274, Episode_length: 193.400±39.231\n", ++ "Rollout 7363/9766, Reward: 245.886±60.445, Episode_length: 294.200±248.700\n", ++ "Rollout 7364/9766, Reward: 263.920±35.860, Episode_length: 274.200±207.978\n", ++ "Rollout 7365/9766, Reward: 250.932±55.529, Episode_length: 307.900±253.870\n", ++ "Rollout 7366/9766, Reward: 265.529±48.958, Episode_length: 270.900±243.233\n", ++ "Rollout 7367/9766, Reward: 236.760±57.986, Episode_length: 298.300±244.256\n", ++ "Rollout 7368/9766, Reward: 273.974±32.780, Episode_length: 190.200±42.534\n", ++ "Rollout 7369/9766, Reward: 247.436±34.451, Episode_length: 197.500±52.610\n", ++ "Rollout 7370/9766, Reward: 264.238±37.190, Episode_length: 206.000±64.365\n", ++ "Rollout 7371/9766, Reward: 266.254±33.954, Episode_length: 223.000±95.127\n", ++ "Rollout 7372/9766, Reward: 273.542±42.108, Episode_length: 190.300±71.048\n", ++ "Rollout 7373/9766, Reward: 273.059±27.865, Episode_length: 198.400±54.498\n", ++ "Rollout 7374/9766, Reward: 280.919±30.320, Episode_length: 199.400±58.396\n", ++ "Rollout 7375/9766, Reward: 285.339±11.654, Episode_length: 177.300±18.537\n", ++ "Rollout 7376/9766, Reward: 265.578±33.981, Episode_length: 190.100±38.555\n", ++ "Rollout 7377/9766, Reward: 273.417±21.968, Episode_length: 182.600±34.889\n", ++ "Rollout 7378/9766, Reward: 273.186±26.617, Episode_length: 183.500±42.549\n", ++ "Rollout 7379/9766, Reward: 283.085±19.046, Episode_length: 173.800±19.281\n", ++ "Rollout 7380/9766, Reward: 279.448±29.373, Episode_length: 198.700±35.225\n", ++ "Rollout 7381/9766, Reward: 266.178±30.394, Episode_length: 196.700±47.075\n", ++ "Rollout 7382/9766, Reward: 278.104±26.491, Episode_length: 192.500±59.773\n", ++ "Rollout 7383/9766, Reward: 267.792±40.688, Episode_length: 242.100±87.547\n", ++ "Rollout 7384/9766, Reward: 253.895±61.152, Episode_length: 201.300±51.137\n", ++ "Rollout 7385/9766, Reward: 278.281±28.381, Episode_length: 213.900±60.682\n", ++ "Rollout 7386/9766, Reward: 260.555±35.464, Episode_length: 219.800±68.991\n", ++ "Rollout 7387/9766, Reward: 270.944±41.524, Episode_length: 227.500±80.793\n", ++ "Rollout 7388/9766, Reward: 289.434±23.419, Episode_length: 190.100±22.304\n", ++ "Rollout 7389/9766, Reward: 276.666±13.933, Episode_length: 179.800±19.848\n", ++ "Rollout 7390/9766, Reward: 271.870±23.486, Episode_length: 179.700±21.053\n", ++ "Rollout 7391/9766, Reward: 266.578±29.690, Episode_length: 202.000±57.093\n", ++ "Rollout 7392/9766, Reward: 276.250±22.407, Episode_length: 190.400±36.398\n", ++ "Rollout 7393/9766, Reward: 251.545±44.916, Episode_length: 220.900±100.793\n", ++ "Rollout 7394/9766, Reward: 264.954±33.268, Episode_length: 295.200±246.435\n", ++ "Rollout 7395/9766, Reward: 280.372±21.616, Episode_length: 192.000±33.163\n", ++ "Rollout 7396/9766, Reward: 274.899±34.315, Episode_length: 199.000±60.133\n", ++ "Rollout 7397/9766, Reward: 278.728±16.498, Episode_length: 190.300±40.195\n", ++ "Rollout 7398/9766, Reward: 276.730±19.156, Episode_length: 253.700±213.376\n", ++ "Rollout 7399/9766, Reward: 248.083±34.887, Episode_length: 253.500±99.460\n", ++ "Rollout 7400/9766, Reward: 275.545±17.820, Episode_length: 178.600±27.522\n", ++ "Rollout 7401/9766, Reward: 278.339±18.774, Episode_length: 189.200±33.828\n", ++ "Rollout 7402/9766, Reward: 270.976±17.297, Episode_length: 175.100±18.234\n", ++ "Rollout 7403/9766, Reward: 287.793±14.911, Episode_length: 182.700±19.960\n", ++ "Rollout 7404/9766, Reward: 269.463±29.226, Episode_length: 184.100±43.887\n", ++ "Rollout 7405/9766, Reward: 288.951±18.682, Episode_length: 181.200±13.585\n", ++ "Rollout 7406/9766, Reward: 255.537±17.346, Episode_length: 182.900±59.668\n", ++ "Rollout 7407/9766, Reward: 261.105±31.491, Episode_length: 197.700±81.317\n", ++ "Rollout 7408/9766, Reward: 262.328±31.964, Episode_length: 202.900±68.353\n", ++ "Rollout 7409/9766, Reward: 288.047±35.051, Episode_length: 202.700±65.695\n", ++ "Rollout 7410/9766, Reward: 275.882±23.408, Episode_length: 202.800±77.816\n", ++ "Rollout 7411/9766, Reward: 276.360±15.561, Episode_length: 172.600±15.035\n", ++ "Rollout 7412/9766, Reward: 295.896±15.279, Episode_length: 238.300±131.403\n", ++ "Rollout 7413/9766, Reward: 275.633±11.093, Episode_length: 154.500±20.205\n", ++ "Rollout 7414/9766, Reward: 289.593±20.131, Episode_length: 177.700±34.000\n", ++ "Rollout 7415/9766, Reward: 281.618±16.820, Episode_length: 160.200±22.480\n", ++ "Rollout 7416/9766, Reward: 282.117±20.723, Episode_length: 167.800±15.387\n", ++ "Rollout 7417/9766, Reward: 279.342±27.859, Episode_length: 203.000±81.281\n", ++ "Rollout 7418/9766, Reward: 286.664±20.283, Episode_length: 179.700±15.402\n", ++ "Rollout 7419/9766, Reward: 273.173±28.373, Episode_length: 250.400±129.280\n", ++ "Rollout 7420/9766, Reward: 286.256±12.662, Episode_length: 171.400±15.500\n", ++ "Rollout 7421/9766, Reward: 282.665±18.520, Episode_length: 181.300±58.995\n", ++ "Rollout 7422/9766, Reward: 278.863±36.005, Episode_length: 208.500±78.778\n", ++ "Rollout 7423/9766, Reward: 290.950±10.239, Episode_length: 179.800±20.341\n", ++ "Rollout 7424/9766, Reward: 278.850±17.476, Episode_length: 174.500±13.216\n", ++ "Rollout 7425/9766, Reward: 272.851±16.322, Episode_length: 172.900±21.952\n", ++ "Rollout 7426/9766, Reward: 282.766±10.482, Episode_length: 166.300±14.192\n", ++ "Rollout 7427/9766, Reward: 279.087±16.828, Episode_length: 170.500±27.060\n", ++ "Rollout 7428/9766, Reward: 263.568±33.061, Episode_length: 225.600±118.337\n", ++ "Rollout 7429/9766, Reward: 266.929±35.083, Episode_length: 216.500±137.795\n", ++ "Rollout 7430/9766, Reward: 272.806±14.189, Episode_length: 217.400±151.798\n", ++ "Rollout 7431/9766, Reward: 286.959±18.866, Episode_length: 174.100±10.802\n", ++ "Rollout 7432/9766, Reward: 269.650±15.958, Episode_length: 183.700±56.390\n", ++ "Rollout 7433/9766, Reward: 271.606±29.234, Episode_length: 204.200±55.364\n", ++ "Rollout 7434/9766, Reward: 265.418±13.470, Episode_length: 160.200±17.285\n", ++ "Rollout 7435/9766, Reward: 280.282±20.429, Episode_length: 175.100±13.187\n", ++ "Rollout 7436/9766, Reward: 267.865±31.079, Episode_length: 274.400±189.004\n", ++ "Rollout 7437/9766, Reward: 276.250±24.888, Episode_length: 228.500±148.001\n", ++ "Rollout 7438/9766, Reward: 283.090±18.095, Episode_length: 164.100±18.376\n", ++ "Rollout 7439/9766, Reward: 280.920±22.909, Episode_length: 211.900±105.848\n", ++ "Rollout 7440/9766, Reward: 282.069±12.340, Episode_length: 162.300±15.179\n", ++ "Rollout 7441/9766, Reward: 274.652±18.455, Episode_length: 170.600±26.043\n", ++ "Rollout 7442/9766, Reward: 275.555±19.320, Episode_length: 166.700±18.596\n", ++ "Rollout 7443/9766, Reward: 279.103±13.997, Episode_length: 159.600±17.614\n", ++ "Rollout 7444/9766, Reward: 284.414±12.128, Episode_length: 167.000±19.162\n", ++ "Rollout 7445/9766, Reward: 264.344±61.371, Episode_length: 260.100±247.439\n", ++ "Rollout 7446/9766, Reward: 271.357±31.289, Episode_length: 327.900±296.176\n", ++ "Rollout 7447/9766, Reward: 284.446±26.084, Episode_length: 246.600±198.294\n", ++ "Rollout 7448/9766, Reward: 260.657±24.503, Episode_length: 221.400±102.749\n", ++ "Rollout 7449/9766, Reward: 275.931±35.088, Episode_length: 212.800±93.835\n", ++ "Rollout 7450/9766, Reward: 255.179±34.885, Episode_length: 207.000±102.393\n", ++ "Rollout 7451/9766, Reward: 278.103±28.745, Episode_length: 234.300±167.814\n", ++ "Rollout 7452/9766, Reward: 276.620±20.772, Episode_length: 216.600±132.704\n", ++ "Rollout 7453/9766, Reward: 266.912±29.805, Episode_length: 260.700±183.630\n", ++ "Rollout 7454/9766, Reward: 275.558±24.433, Episode_length: 166.200±14.127\n", ++ "Rollout 7455/9766, Reward: 254.873±69.924, Episode_length: 305.200±265.421\n", ++ "Rollout 7456/9766, Reward: 220.670±128.093, Episode_length: 210.100±78.166\n", ++ "Rollout 7457/9766, Reward: 252.069±68.905, Episode_length: 191.400±79.621\n", ++ "Rollout 7458/9766, Reward: 260.439±23.773, Episode_length: 203.200±65.282\n", ++ "Rollout 7459/9766, Reward: 283.534±15.919, Episode_length: 190.600±19.262\n", ++ "Rollout 7460/9766, Reward: 275.054±19.870, Episode_length: 177.700±59.825\n", ++ "Rollout 7461/9766, Reward: 240.728±71.997, Episode_length: 260.400±148.010\n", ++ "Rollout 7462/9766, Reward: 282.314±21.119, Episode_length: 178.700±17.805\n", ++ "Rollout 7463/9766, Reward: 273.222±24.034, Episode_length: 190.800±44.095\n", ++ "Rollout 7464/9766, Reward: 272.788±29.623, Episode_length: 189.300±58.537\n", ++ "Rollout 7465/9766, Reward: 268.955±24.613, Episode_length: 194.600±87.034\n", ++ "Rollout 7466/9766, Reward: 274.722±20.660, Episode_length: 183.700±23.048\n", ++ "Rollout 7467/9766, Reward: 233.304±61.347, Episode_length: 191.500±98.104\n", ++ "Rollout 7468/9766, Reward: 271.408±21.247, Episode_length: 213.200±109.387\n", ++ "Rollout 7469/9766, Reward: 269.635±31.503, Episode_length: 225.800±130.132\n", ++ "Rollout 7470/9766, Reward: 279.066±20.403, Episode_length: 257.900±67.322\n", ++ "Rollout 7471/9766, Reward: 252.150±37.863, Episode_length: 449.800±334.157\n", ++ "Rollout 7472/9766, Reward: 284.948±10.590, Episode_length: 171.100±29.660\n", ++ "Rollout 7473/9766, Reward: 275.365±30.530, Episode_length: 236.900±254.861\n", ++ "Rollout 7474/9766, Reward: 262.775±53.513, Episode_length: 369.300±321.747\n", ++ "Rollout 7475/9766, Reward: 261.403±34.915, Episode_length: 291.400±280.552\n", ++ "Rollout 7476/9766, Reward: 273.935±29.401, Episode_length: 248.300±251.464\n", ++ "Rollout 7477/9766, Reward: 256.484±50.420, Episode_length: 394.100±349.146\n", ++ "Rollout 7478/9766, Reward: 267.488±40.768, Episode_length: 249.800±250.370\n", ++ "Rollout 7479/9766, Reward: 277.394±16.973, Episode_length: 162.300±11.816\n", ++ "Rollout 7480/9766, Reward: 281.105±14.694, Episode_length: 175.600±25.136\n", ++ "Rollout 7481/9766, Reward: 279.025±33.604, Episode_length: 204.300±96.119\n", ++ "Rollout 7482/9766, Reward: 274.849±19.216, Episode_length: 187.600±65.456\n", ++ "Rollout 7483/9766, Reward: 287.739±21.706, Episode_length: 186.800±54.231\n", ++ "Rollout 7484/9766, Reward: 278.895±20.676, Episode_length: 166.000±23.912\n", ++ "Rollout 7485/9766, Reward: 267.027±29.426, Episode_length: 236.000±132.053\n", ++ "Rollout 7486/9766, Reward: 273.541±17.154, Episode_length: 168.500±9.135\n", ++ "Rollout 7487/9766, Reward: 278.929±17.415, Episode_length: 190.300±45.837\n", ++ "Rollout 7488/9766, Reward: 276.387±25.077, Episode_length: 168.300±25.562\n", ++ "Rollout 7489/9766, Reward: 276.160±35.112, Episode_length: 203.500±111.530\n", ++ "Rollout 7490/9766, Reward: 281.219±16.432, Episode_length: 169.100±22.390\n", ++ "Rollout 7491/9766, Reward: 288.678±13.460, Episode_length: 181.400±26.272\n", ++ "Rollout 7492/9766, Reward: 287.191±26.266, Episode_length: 195.400±61.515\n", ++ "Rollout 7493/9766, Reward: 277.816±25.718, Episode_length: 194.100±94.550\n", ++ "Rollout 7494/9766, Reward: 273.554±26.374, Episode_length: 205.100±86.157\n", ++ "Rollout 7495/9766, Reward: 290.764±16.068, Episode_length: 187.000±48.561\n", ++ "Rollout 7496/9766, Reward: 280.507±16.004, Episode_length: 193.500±80.210\n", ++ "Rollout 7497/9766, Reward: 256.668±63.428, Episode_length: 148.400±20.505\n", ++ "Rollout 7498/9766, Reward: 271.704±21.980, Episode_length: 194.900±107.858\n", ++ "Rollout 7499/9766, Reward: 272.828±30.010, Episode_length: 188.900±68.323\n", ++ "Rollout 7500/9766, Reward: 282.809±19.318, Episode_length: 212.600±123.196\n", ++ "Rollout 7501/9766, Reward: 263.858±64.403, Episode_length: 151.100±29.022\n", ++ "Rollout 7502/9766, Reward: 285.856±25.546, Episode_length: 203.300±70.551\n", ++ "Rollout 7503/9766, Reward: 277.053±13.867, Episode_length: 179.600±20.805\n", ++ "Rollout 7504/9766, Reward: 275.319±23.223, Episode_length: 190.100±57.877\n", ++ "Rollout 7505/9766, Reward: 268.712±15.030, Episode_length: 245.000±229.653\n", ++ "Rollout 7506/9766, Reward: 283.569±9.985, Episode_length: 181.600±11.893\n", ++ "Rollout 7507/9766, Reward: 277.530±25.131, Episode_length: 191.000±69.459\n", ++ "Rollout 7508/9766, Reward: 272.761±22.193, Episode_length: 187.400±64.899\n", ++ "Rollout 7509/9766, Reward: 278.178±12.859, Episode_length: 163.400±16.657\n", ++ "Rollout 7510/9766, Reward: 276.556±19.758, Episode_length: 165.200±15.516\n", ++ "Rollout 7511/9766, Reward: 278.076±28.712, Episode_length: 194.200±60.747\n", ++ "Rollout 7512/9766, Reward: 284.108±9.769, Episode_length: 169.100±19.821\n", ++ "Rollout 7513/9766, Reward: 279.613±15.999, Episode_length: 172.000±20.765\n", ++ "Rollout 7514/9766, Reward: 290.945±21.685, Episode_length: 177.400±19.515\n", ++ "Rollout 7515/9766, Reward: 283.393±18.877, Episode_length: 202.600±87.392\n", ++ "Rollout 7516/9766, Reward: 277.931±26.863, Episode_length: 217.300±152.216\n", ++ "Rollout 7517/9766, Reward: 295.490±15.750, Episode_length: 173.300±22.856\n", ++ "Rollout 7518/9766, Reward: 289.842±23.247, Episode_length: 236.400±140.388\n", ++ "Rollout 7519/9766, Reward: 293.251±15.335, Episode_length: 255.100±199.747\n", ++ "Rollout 7520/9766, Reward: 261.507±65.755, Episode_length: 163.500±20.461\n", ++ "Rollout 7521/9766, Reward: 277.039±20.329, Episode_length: 278.600±168.208\n", ++ "Rollout 7522/9766, Reward: 278.900±29.236, Episode_length: 213.500±90.433\n", ++ "Rollout 7523/9766, Reward: 274.564±36.197, Episode_length: 230.700±204.604\n", ++ "Rollout 7524/9766, Reward: 259.760±47.744, Episode_length: 335.100±332.814\n", ++ "Rollout 7525/9766, Reward: 273.214±37.325, Episode_length: 249.800±250.539\n", ++ "Rollout 7526/9766, Reward: 281.939±13.369, Episode_length: 160.400±12.635\n", ++ "Rollout 7527/9766, Reward: 285.616±31.360, Episode_length: 291.000±264.041\n", ++ "Rollout 7528/9766, Reward: 286.933±12.882, Episode_length: 207.200±53.680\n", ++ "Rollout 7529/9766, Reward: 274.064±54.448, Episode_length: 262.600±246.642\n", ++ "Rollout 7530/9766, Reward: 274.479±34.489, Episode_length: 294.000±249.100\n", ++ "Rollout 7531/9766, Reward: 282.203±20.082, Episode_length: 201.900±123.233\n", ++ "Rollout 7532/9766, Reward: 261.185±43.744, Episode_length: 275.100±163.143\n", ++ "Rollout 7533/9766, Reward: 258.202±36.046, Episode_length: 268.700±175.153\n", ++ "Rollout 7534/9766, Reward: 277.314±26.487, Episode_length: 166.800±15.092\n", ++ "Rollout 7535/9766, Reward: 270.729±13.778, Episode_length: 236.800±207.252\n", ++ "Rollout 7536/9766, Reward: 260.000±53.051, Episode_length: 269.600±254.050\n", ++ "Rollout 7537/9766, Reward: 273.796±29.331, Episode_length: 193.300±50.383\n", ++ "Rollout 7538/9766, Reward: 277.044±14.980, Episode_length: 178.200±30.397\n", ++ "Rollout 7539/9766, Reward: 272.175±25.297, Episode_length: 196.400±48.461\n", ++ "Rollout 7540/9766, Reward: 278.788±19.166, Episode_length: 177.400±28.011\n", ++ "Rollout 7541/9766, Reward: 270.366±26.859, Episode_length: 185.200±26.903\n", ++ "Rollout 7542/9766, Reward: 271.188±37.953, Episode_length: 205.700±87.100\n", ++ "Rollout 7543/9766, Reward: 270.197±31.558, Episode_length: 256.500±149.586\n", ++ "Rollout 7544/9766, Reward: 277.828±18.656, Episode_length: 172.400±19.754\n", ++ "Rollout 7545/9766, Reward: 273.036±19.644, Episode_length: 179.000±26.586\n", ++ "Rollout 7546/9766, Reward: 279.670±19.014, Episode_length: 200.700±49.185\n", ++ "Rollout 7547/9766, Reward: 258.294±26.416, Episode_length: 180.900±56.083\n", ++ "Rollout 7548/9766, Reward: 290.882±18.667, Episode_length: 178.400±25.912\n", ++ "Rollout 7549/9766, Reward: 267.290±32.182, Episode_length: 214.500±108.213\n", ++ "Rollout 7550/9766, Reward: 278.781±15.418, Episode_length: 173.200±25.549\n", ++ "Rollout 7551/9766, Reward: 279.097±28.296, Episode_length: 239.500±123.532\n", ++ "Rollout 7552/9766, Reward: 274.810±25.335, Episode_length: 200.500±59.317\n", ++ "Rollout 7553/9766, Reward: 269.586±32.511, Episode_length: 337.400±275.411\n", ++ "Rollout 7554/9766, Reward: 279.317±18.867, Episode_length: 161.500±16.907\n", ++ "Rollout 7555/9766, Reward: 281.890±22.535, Episode_length: 211.700±110.081\n", ++ "Rollout 7556/9766, Reward: 282.243±19.681, Episode_length: 183.900±56.674\n", ++ "Rollout 7557/9766, Reward: 285.863±14.509, Episode_length: 173.300±13.000\n", ++ "Rollout 7558/9766, Reward: 278.801±37.425, Episode_length: 229.200±167.479\n", ++ "Rollout 7559/9766, Reward: 269.317±29.965, Episode_length: 221.600±145.643\n", ++ "Rollout 7560/9766, Reward: 276.493±39.629, Episode_length: 253.100±249.390\n", ++ "Rollout 7561/9766, Reward: 289.006±15.738, Episode_length: 175.600±19.080\n", ++ "Rollout 7562/9766, Reward: 277.612±33.269, Episode_length: 239.300±254.153\n", ++ "Rollout 7563/9766, Reward: 289.206±25.801, Episode_length: 238.700±225.995\n", ++ "Rollout 7564/9766, Reward: 263.021±66.310, Episode_length: 158.400±22.677\n", ++ "Rollout 7565/9766, Reward: 272.600±30.138, Episode_length: 247.700±251.220\n", ++ "Rollout 7566/9766, Reward: 287.332±18.994, Episode_length: 168.400±14.129\n", ++ "Rollout 7567/9766, Reward: 284.573±12.863, Episode_length: 198.600±114.541\n", ++ "Rollout 7568/9766, Reward: 280.708±40.036, Episode_length: 245.000±252.441\n", ++ "Rollout 7569/9766, Reward: 254.737±76.798, Episode_length: 159.100±27.649\n", ++ "Rollout 7570/9766, Reward: 292.838±9.963, Episode_length: 166.600±32.690\n", ++ "Rollout 7571/9766, Reward: 261.409±44.281, Episode_length: 409.500±375.273\n", ++ "Rollout 7572/9766, Reward: 288.017±11.721, Episode_length: 160.200±20.837\n", ++ "Rollout 7573/9766, Reward: 283.173±15.642, Episode_length: 212.000±161.500\n", ++ "Rollout 7574/9766, Reward: 282.575±20.180, Episode_length: 170.900±27.138\n", ++ "Rollout 7575/9766, Reward: 277.401±34.496, Episode_length: 243.900±252.258\n", ++ "Rollout 7576/9766, Reward: 284.888±17.602, Episode_length: 162.700±23.217\n", ++ "Rollout 7577/9766, Reward: 282.739±23.731, Episode_length: 191.000±71.238\n", ++ "Rollout 7578/9766, Reward: 293.114±17.868, Episode_length: 166.000±18.841\n", ++ "Rollout 7579/9766, Reward: 274.673±20.002, Episode_length: 213.300±145.103\n", ++ "Rollout 7580/9766, Reward: 251.312±71.568, Episode_length: 195.900±123.039\n", ++ "Rollout 7581/9766, Reward: 269.764±24.330, Episode_length: 210.000±103.010\n", ++ "Rollout 7582/9766, Reward: 286.326±20.146, Episode_length: 173.700±16.088\n", ++ "Rollout 7583/9766, Reward: 281.573±18.125, Episode_length: 173.500±16.317\n", ++ "Rollout 7584/9766, Reward: 274.648±32.788, Episode_length: 223.000±123.488\n", ++ "Rollout 7585/9766, Reward: 282.097±14.289, Episode_length: 163.600±17.839\n", ++ "Rollout 7586/9766, Reward: 287.119±18.407, Episode_length: 167.000±19.703\n", ++ "Rollout 7587/9766, Reward: 286.086±23.411, Episode_length: 162.500±17.912\n", ++ "Rollout 7588/9766, Reward: 285.061±19.783, Episode_length: 178.600±20.096\n", ++ "Rollout 7589/9766, Reward: 293.422±18.710, Episode_length: 184.100±15.129\n", ++ "Rollout 7590/9766, Reward: 280.593±19.673, Episode_length: 167.000±13.221\n", ++ "Rollout 7591/9766, Reward: 285.978±16.087, Episode_length: 178.500±20.490\n", ++ "Rollout 7592/9766, Reward: 269.411±25.926, Episode_length: 206.400±105.143\n", ++ "Rollout 7593/9766, Reward: 252.161±73.955, Episode_length: 219.900±124.345\n", ++ "Rollout 7594/9766, Reward: 277.732±21.231, Episode_length: 209.800±100.660\n", ++ "Rollout 7595/9766, Reward: 264.976±46.114, Episode_length: 350.400±326.834\n", ++ "Rollout 7596/9766, Reward: 289.718±17.125, Episode_length: 178.600±16.848\n", ++ "Rollout 7597/9766, Reward: 274.961±24.776, Episode_length: 200.000±81.242\n", ++ "Rollout 7598/9766, Reward: 286.044±11.837, Episode_length: 168.300±15.133\n", ++ "Rollout 7599/9766, Reward: 271.582±14.468, Episode_length: 164.900±14.244\n", ++ "Rollout 7600/9766, Reward: 280.072±26.099, Episode_length: 169.700±17.476\n", ++ "Rollout 7601/9766, Reward: 278.257±39.175, Episode_length: 258.000±247.749\n", ++ "Rollout 7602/9766, Reward: 285.237±18.239, Episode_length: 166.600±23.984\n", ++ "Rollout 7603/9766, Reward: 295.255±15.586, Episode_length: 174.500±18.516\n", ++ "Rollout 7604/9766, Reward: 295.119±17.630, Episode_length: 174.200±17.932\n", ++ "Rollout 7605/9766, Reward: 268.581±26.182, Episode_length: 217.800±95.811\n", ++ "Rollout 7606/9766, Reward: 281.195±22.086, Episode_length: 220.800±110.993\n", ++ "Rollout 7607/9766, Reward: 263.198±34.418, Episode_length: 231.900±120.072\n", ++ "Rollout 7608/9766, Reward: 286.816±12.429, Episode_length: 163.600±20.991\n", ++ "Rollout 7609/9766, Reward: 278.763±14.879, Episode_length: 165.200±20.508\n", ++ "Rollout 7610/9766, Reward: 289.118±10.487, Episode_length: 167.700±16.242\n", ++ "Rollout 7611/9766, Reward: 290.271±17.951, Episode_length: 172.100±27.344\n", ++ "Rollout 7612/9766, Reward: 270.756±28.591, Episode_length: 201.600±119.670\n", ++ "Rollout 7613/9766, Reward: 285.591±17.166, Episode_length: 163.100±16.766\n", ++ "Rollout 7614/9766, Reward: 287.226±13.026, Episode_length: 173.800±12.131\n", ++ "Rollout 7615/9766, Reward: 288.391±24.239, Episode_length: 176.300±19.995\n", ++ "Rollout 7616/9766, Reward: 274.624±19.696, Episode_length: 158.000±17.216\n", ++ "Rollout 7617/9766, Reward: 284.720±7.389, Episode_length: 168.600±18.266\n", ++ "Rollout 7618/9766, Reward: 290.331±15.447, Episode_length: 186.200±64.595\n", ++ "Rollout 7619/9766, Reward: 278.473±16.526, Episode_length: 161.100±17.450\n", ++ "Rollout 7620/9766, Reward: 287.097±15.477, Episode_length: 160.100±18.801\n", ++ "Rollout 7621/9766, Reward: 295.814±15.659, Episode_length: 208.700±82.854\n", ++ "Rollout 7622/9766, Reward: 258.921±35.528, Episode_length: 233.600±156.290\n", ++ "Rollout 7623/9766, Reward: 268.489±28.160, Episode_length: 190.100±69.131\n", ++ "Rollout 7624/9766, Reward: 284.318±25.851, Episode_length: 172.000±20.548\n", ++ "Rollout 7625/9766, Reward: 283.297±20.947, Episode_length: 162.600±27.565\n", ++ "Rollout 7626/9766, Reward: 278.593±15.746, Episode_length: 181.200±55.661\n", ++ "Rollout 7627/9766, Reward: 273.738±23.748, Episode_length: 251.400±172.444\n", ++ "Rollout 7628/9766, Reward: 267.549±26.042, Episode_length: 190.500±62.652\n", ++ "Rollout 7629/9766, Reward: 288.842±8.487, Episode_length: 175.000±22.751\n", ++ "Rollout 7630/9766, Reward: 280.024±16.234, Episode_length: 169.100±19.170\n", ++ "Rollout 7631/9766, Reward: 292.473±19.658, Episode_length: 178.400±34.168\n", ++ "Rollout 7632/9766, Reward: 247.843±77.003, Episode_length: 291.200±280.175\n", ++ "Rollout 7633/9766, Reward: 284.138±12.012, Episode_length: 165.400±17.488\n", ++ "Rollout 7634/9766, Reward: 272.691±35.437, Episode_length: 249.400±250.493\n", ++ "Rollout 7635/9766, Reward: 288.596±17.076, Episode_length: 164.500±19.169\n", ++ "Rollout 7636/9766, Reward: 279.594±16.979, Episode_length: 215.900±158.751\n", ++ "Rollout 7637/9766, Reward: 286.873±11.408, Episode_length: 177.600±57.007\n", ++ "Rollout 7638/9766, Reward: 284.458±16.141, Episode_length: 167.100±16.398\n", ++ "Rollout 7639/9766, Reward: 284.643±16.383, Episode_length: 159.000±14.360\n", ++ "Rollout 7640/9766, Reward: 294.940±17.236, Episode_length: 172.300±20.426\n", ++ "Rollout 7641/9766, Reward: 282.466±14.225, Episode_length: 163.000±13.319\n", ++ "Rollout 7642/9766, Reward: 296.636±14.971, Episode_length: 171.900±22.514\n", ++ "Rollout 7643/9766, Reward: 288.357±18.089, Episode_length: 168.300±26.314\n", ++ "Rollout 7644/9766, Reward: 278.547±18.147, Episode_length: 159.200±18.782\n", ++ "Rollout 7645/9766, Reward: 284.422±19.734, Episode_length: 167.700±21.354\n", ++ "Rollout 7646/9766, Reward: 279.338±21.334, Episode_length: 190.200±64.796\n", ++ "Rollout 7647/9766, Reward: 282.985±31.239, Episode_length: 223.500±131.038\n", ++ "Rollout 7648/9766, Reward: 278.106±18.901, Episode_length: 167.700±17.211\n", ++ "Rollout 7649/9766, Reward: 289.892±16.593, Episode_length: 167.700±23.268\n", ++ "Rollout 7650/9766, Reward: 288.787±12.975, Episode_length: 168.300±21.213\n", ++ "Rollout 7651/9766, Reward: 285.637±13.465, Episode_length: 167.100±21.403\n", ++ "Rollout 7652/9766, Reward: 288.441±12.983, Episode_length: 165.200±17.854\n", ++ "Rollout 7653/9766, Reward: 280.625±16.398, Episode_length: 169.900±17.484\n", ++ "Rollout 7654/9766, Reward: 280.492±20.511, Episode_length: 160.100±19.992\n", ++ "Rollout 7655/9766, Reward: 300.515±14.690, Episode_length: 181.300±16.835\n", ++ "Rollout 7656/9766, Reward: 272.563±29.647, Episode_length: 202.700±125.673\n", ++ "Rollout 7657/9766, Reward: 283.543±17.175, Episode_length: 192.200±74.257\n", ++ "Rollout 7658/9766, Reward: 286.798±22.188, Episode_length: 167.600±18.624\n", ++ "Rollout 7659/9766, Reward: 283.323±24.057, Episode_length: 217.400±123.726\n", ++ "Rollout 7660/9766, Reward: 293.844±18.913, Episode_length: 183.900±27.804\n", ++ "Rollout 7661/9766, Reward: 290.639±11.747, Episode_length: 174.200±19.964\n", ++ "Rollout 7662/9766, Reward: 281.767±14.661, Episode_length: 176.400±24.229\n", ++ "Rollout 7663/9766, Reward: 286.834±17.581, Episode_length: 159.900±17.421\n", ++ "Rollout 7664/9766, Reward: 265.598±83.763, Episode_length: 161.900±24.595\n", ++ "Rollout 7665/9766, Reward: 288.079±19.994, Episode_length: 167.000±17.799\n", ++ "Rollout 7666/9766, Reward: 280.705±34.274, Episode_length: 255.300±248.652\n", ++ "Rollout 7667/9766, Reward: 285.056±17.540, Episode_length: 175.700±21.863\n", ++ "Rollout 7668/9766, Reward: 281.546±16.216, Episode_length: 161.300±12.092\n", ++ "Rollout 7669/9766, Reward: 263.899±34.379, Episode_length: 273.500±234.482\n", ++ "Rollout 7670/9766, Reward: 288.789±17.060, Episode_length: 158.800±15.638\n", ++ "Rollout 7671/9766, Reward: 296.768±16.837, Episode_length: 180.400±15.442\n", ++ "Rollout 7672/9766, Reward: 270.629±47.926, Episode_length: 410.600±366.670\n", ++ "Rollout 7673/9766, Reward: 270.584±30.298, Episode_length: 241.900±253.042\n", ++ "Rollout 7674/9766, Reward: 296.119±19.178, Episode_length: 235.100±223.173\n", ++ "Rollout 7675/9766, Reward: 290.942±12.673, Episode_length: 165.400±19.855\n", ++ "Rollout 7676/9766, Reward: 277.453±41.560, Episode_length: 252.100±249.956\n", ++ "Rollout 7677/9766, Reward: 289.788±16.721, Episode_length: 241.200±216.078\n", ++ "Rollout 7678/9766, Reward: 286.308±18.081, Episode_length: 169.200±20.537\n", ++ "Rollout 7679/9766, Reward: 254.917±72.628, Episode_length: 156.000±20.995\n", ++ "Rollout 7680/9766, Reward: 293.279±14.710, Episode_length: 173.200±35.448\n", ++ "Rollout 7681/9766, Reward: 288.718±18.802, Episode_length: 218.900±166.047\n", ++ "Rollout 7682/9766, Reward: 279.605±9.738, Episode_length: 153.200±15.555\n", ++ "Rollout 7683/9766, Reward: 286.343±22.244, Episode_length: 178.000±21.364\n", ++ "Rollout 7684/9766, Reward: 281.354±39.475, Episode_length: 253.100±249.537\n", ++ "Rollout 7685/9766, Reward: 288.451±13.650, Episode_length: 236.400±225.064\n", ++ "Rollout 7686/9766, Reward: 269.764±39.705, Episode_length: 320.900±291.593\n", ++ "Rollout 7687/9766, Reward: 288.660±16.448, Episode_length: 178.800±30.828\n", ++ "Rollout 7688/9766, Reward: 291.148±10.506, Episode_length: 162.600±17.188\n", ++ "Rollout 7689/9766, Reward: 285.338±14.235, Episode_length: 162.700±12.223\n", ++ "Rollout 7690/9766, Reward: 274.303±25.374, Episode_length: 231.600±186.757\n", ++ "Rollout 7691/9766, Reward: 287.987±16.150, Episode_length: 164.800±13.083\n", ++ "Rollout 7692/9766, Reward: 283.455±17.267, Episode_length: 164.300±19.683\n", ++ "Rollout 7693/9766, Reward: 262.805±72.704, Episode_length: 158.300±22.213\n", ++ "Rollout 7694/9766, Reward: 295.702±13.927, Episode_length: 182.600±37.438\n", ++ "Rollout 7695/9766, Reward: 281.031±20.304, Episode_length: 172.800±23.507\n", ++ "Rollout 7696/9766, Reward: 298.553±15.548, Episode_length: 237.300±156.444\n", ++ "Rollout 7697/9766, Reward: 290.303±15.761, Episode_length: 168.700±18.380\n", ++ "Rollout 7698/9766, Reward: 297.986±16.707, Episode_length: 170.000±14.893\n", ++ "Rollout 7699/9766, Reward: 297.907±12.997, Episode_length: 177.900±16.034\n", ++ "Rollout 7700/9766, Reward: 287.786±16.402, Episode_length: 163.100±14.467\n", ++ "Rollout 7701/9766, Reward: 296.022±16.917, Episode_length: 167.000±22.987\n", ++ "Rollout 7702/9766, Reward: 276.861±18.567, Episode_length: 155.700±14.332\n", ++ "Rollout 7703/9766, Reward: 283.304±19.186, Episode_length: 161.300±19.571\n", ++ "Rollout 7704/9766, Reward: 293.118±10.474, Episode_length: 173.200±16.105\n", ++ "Rollout 7705/9766, Reward: 283.819±20.961, Episode_length: 162.200±17.606\n", ++ "Rollout 7706/9766, Reward: 289.729±15.959, Episode_length: 163.400±20.771\n", ++ "Rollout 7707/9766, Reward: 290.129±13.483, Episode_length: 164.700±25.714\n", ++ "Rollout 7708/9766, Reward: 290.254±17.257, Episode_length: 167.400±18.348\n", ++ "Rollout 7709/9766, Reward: 298.410±11.603, Episode_length: 167.100±23.952\n", ++ "Rollout 7710/9766, Reward: 280.298±34.684, Episode_length: 324.700±332.257\n", ++ "Rollout 7711/9766, Reward: 294.987±17.181, Episode_length: 170.100±14.474\n", ++ "Rollout 7712/9766, Reward: 290.148±16.786, Episode_length: 250.400±243.180\n", ++ "Rollout 7713/9766, Reward: 289.392±14.601, Episode_length: 163.000±19.601\n", ++ "Rollout 7714/9766, Reward: 288.688±16.477, Episode_length: 166.900±14.515\n", ++ "Rollout 7715/9766, Reward: 292.740±13.678, Episode_length: 302.500±261.023\n", ++ "Rollout 7716/9766, Reward: 283.253±21.787, Episode_length: 169.800±16.503\n", ++ "Rollout 7717/9766, Reward: 291.495±14.514, Episode_length: 234.900±180.108\n", ++ "Rollout 7718/9766, Reward: 288.387±18.315, Episode_length: 177.200±17.775\n", ++ "Rollout 7719/9766, Reward: 287.454±15.270, Episode_length: 165.000±22.891\n", ++ "Rollout 7720/9766, Reward: 271.222±67.098, Episode_length: 167.600±28.136\n", ++ "Rollout 7721/9766, Reward: 291.720±15.883, Episode_length: 180.700±17.401\n", ++ "Rollout 7722/9766, Reward: 277.966±17.448, Episode_length: 168.300±15.120\n", ++ "Rollout 7723/9766, Reward: 257.231±62.127, Episode_length: 147.000±24.046\n", ++ "Rollout 7724/9766, Reward: 278.519±19.872, Episode_length: 201.100±108.755\n", ++ "Rollout 7725/9766, Reward: 290.768±11.828, Episode_length: 173.900±18.273\n", ++ "Rollout 7726/9766, Reward: 276.651±10.250, Episode_length: 162.700±14.785\n", ++ "Rollout 7727/9766, Reward: 289.412±10.208, Episode_length: 169.200±15.892\n", ++ "Rollout 7728/9766, Reward: 296.157±15.825, Episode_length: 180.400±15.737\n", ++ "Rollout 7729/9766, Reward: 294.670±9.577, Episode_length: 178.600±15.976\n", ++ "Rollout 7730/9766, Reward: 295.246±14.297, Episode_length: 174.900±17.846\n", ++ "Rollout 7731/9766, Reward: 219.073±188.373, Episode_length: 170.700±17.065\n", ++ "Rollout 7732/9766, Reward: 294.785±12.434, Episode_length: 175.100±24.934\n", ++ "Rollout 7733/9766, Reward: 286.820±18.073, Episode_length: 172.600±14.941\n", ++ "Rollout 7734/9766, Reward: 239.587±161.999, Episode_length: 181.700±13.770\n", ++ "Rollout 7735/9766, Reward: 282.828±12.518, Episode_length: 170.800±16.406\n", ++ "Rollout 7736/9766, Reward: 285.568±19.834, Episode_length: 171.200±22.671\n", ++ "Rollout 7737/9766, Reward: 294.970±15.776, Episode_length: 174.300±25.915\n", ++ "Rollout 7738/9766, Reward: 290.262±13.810, Episode_length: 173.300±12.149\n", ++ "Rollout 7739/9766, Reward: 222.462±195.439, Episode_length: 259.200±247.938\n", ++ "Rollout 7740/9766, Reward: 294.012±15.149, Episode_length: 171.700±19.840\n", ++ "Rollout 7741/9766, Reward: 293.104±17.031, Episode_length: 167.900±22.915\n", ++ "Rollout 7742/9766, Reward: 270.207±25.815, Episode_length: 239.100±142.094\n", ++ "Rollout 7743/9766, Reward: 283.683±10.412, Episode_length: 188.200±87.525\n", ++ "Rollout 7744/9766, Reward: 291.035±15.485, Episode_length: 169.000±16.941\n", ++ "Rollout 7745/9766, Reward: 294.292±15.376, Episode_length: 170.900±16.985\n", ++ "Rollout 7746/9766, Reward: 284.727±14.229, Episode_length: 172.700±17.071\n", ++ "Rollout 7747/9766, Reward: 288.761±13.390, Episode_length: 181.400±29.299\n", ++ "Rollout 7748/9766, Reward: 226.798±193.262, Episode_length: 178.900±21.718\n", ++ "Rollout 7749/9766, Reward: 279.401±29.726, Episode_length: 219.900±111.562\n", ++ "Rollout 7750/9766, Reward: 282.249±13.458, Episode_length: 168.700±17.187\n", ++ "Rollout 7751/9766, Reward: 283.177±19.080, Episode_length: 179.700±26.959\n", ++ "Rollout 7752/9766, Reward: 279.912±19.614, Episode_length: 174.800±15.197\n", ++ "Rollout 7753/9766, Reward: 289.281±18.932, Episode_length: 172.200±19.843\n", ++ "Rollout 7754/9766, Reward: 293.797±14.477, Episode_length: 170.000±24.112\n", ++ "Rollout 7755/9766, Reward: 274.629±43.149, Episode_length: 258.500±247.968\n", ++ "Rollout 7756/9766, Reward: 281.280±20.777, Episode_length: 164.600±20.915\n", ++ "Rollout 7757/9766, Reward: 300.269±16.122, Episode_length: 177.300±21.689\n", ++ "Rollout 7758/9766, Reward: 285.238±10.384, Episode_length: 164.100±18.641\n", ++ "Rollout 7759/9766, Reward: 292.730±21.172, Episode_length: 174.200±29.116\n", ++ "Rollout 7760/9766, Reward: 287.819±15.817, Episode_length: 167.000±19.794\n", ++ "Rollout 7761/9766, Reward: 280.550±31.977, Episode_length: 246.700±252.018\n", ++ "Rollout 7762/9766, Reward: 289.828±19.512, Episode_length: 172.300±16.007\n", ++ "Rollout 7763/9766, Reward: 287.142±14.287, Episode_length: 158.400±17.275\n", ++ "Rollout 7764/9766, Reward: 289.922±19.271, Episode_length: 167.600±17.856\n", ++ "Rollout 7765/9766, Reward: 286.558±21.879, Episode_length: 169.700±16.298\n", ++ "Rollout 7766/9766, Reward: 282.603±22.521, Episode_length: 204.500±112.702\n", ++ "Rollout 7767/9766, Reward: 285.405±15.198, Episode_length: 171.500±11.868\n", ++ "Rollout 7768/9766, Reward: 269.291±36.065, Episode_length: 244.700±252.541\n", ++ "Rollout 7769/9766, Reward: 280.143±25.404, Episode_length: 229.900±186.763\n", ++ "Rollout 7770/9766, Reward: 288.954±21.192, Episode_length: 178.900±20.954\n", ++ "Rollout 7771/9766, Reward: 286.380±21.520, Episode_length: 164.500±22.110\n", ++ "Rollout 7772/9766, Reward: 284.943±53.626, Episode_length: 261.700±246.353\n", ++ "Rollout 7773/9766, Reward: 287.128±17.191, Episode_length: 157.800±14.176\n", ++ "Rollout 7774/9766, Reward: 266.229±74.982, Episode_length: 166.600±25.769\n", ++ "Rollout 7775/9766, Reward: 284.391±10.490, Episode_length: 160.600±13.858\n", ++ "Rollout 7776/9766, Reward: 288.986±21.012, Episode_length: 169.100±17.288\n", ++ "Rollout 7777/9766, Reward: 282.475±18.420, Episode_length: 163.700±16.935\n", ++ "Rollout 7778/9766, Reward: 275.340±40.325, Episode_length: 255.700±249.012\n", ++ "Rollout 7779/9766, Reward: 282.440±14.241, Episode_length: 159.200±19.498\n", ++ "Rollout 7780/9766, Reward: 281.294±14.634, Episode_length: 169.600±20.872\n", ++ "Rollout 7781/9766, Reward: 289.068±19.748, Episode_length: 174.100±14.563\n", ++ "Rollout 7782/9766, Reward: 280.167±13.560, Episode_length: 155.100±11.528\n", ++ "Rollout 7783/9766, Reward: 249.787±57.759, Episode_length: 329.300±335.756\n", ++ "Rollout 7784/9766, Reward: 281.224±47.347, Episode_length: 257.100±248.214\n", ++ "Rollout 7785/9766, Reward: 283.223±12.366, Episode_length: 163.400±20.106\n", ++ "Rollout 7786/9766, Reward: 285.615±17.243, Episode_length: 165.800±15.092\n", ++ "Rollout 7787/9766, Reward: 283.629±17.451, Episode_length: 166.400±18.789\n", ++ "Rollout 7788/9766, Reward: 292.154±19.166, Episode_length: 168.600±17.477\n", ++ "Rollout 7789/9766, Reward: 285.753±13.218, Episode_length: 162.900±17.997\n", ++ "Rollout 7790/9766, Reward: 254.268±53.569, Episode_length: 416.200±382.358\n", ++ "Rollout 7791/9766, Reward: 285.166±17.729, Episode_length: 155.300±17.978\n", ++ "Rollout 7792/9766, Reward: 292.310±16.075, Episode_length: 188.200±49.996\n", ++ "Rollout 7793/9766, Reward: 284.378±18.925, Episode_length: 167.000±19.298\n", ++ "Rollout 7794/9766, Reward: 231.320±61.166, Episode_length: 496.100±411.584\n", ++ "Rollout 7795/9766, Reward: 265.649±43.244, Episode_length: 327.700±336.386\n", ++ "Rollout 7796/9766, Reward: 253.426±50.484, Episode_length: 413.700±384.447\n", ++ "Rollout 7797/9766, Reward: 258.612±47.807, Episode_length: 391.700±353.125\n", ++ "Rollout 7798/9766, Reward: 264.343±49.146, Episode_length: 328.500±336.121\n", ++ "Rollout 7799/9766, Reward: 264.151±48.099, Episode_length: 322.800±339.283\n", ++ "Rollout 7800/9766, Reward: 277.475±33.986, Episode_length: 374.500±276.168\n", ++ "Rollout 7801/9766, Reward: 192.300±54.193, Episode_length: 833.400±333.308\n", ++ "Rollout 7802/9766, Reward: 200.956±52.342, Episode_length: 878.000±248.103\n", ++ "Rollout 7803/9766, Reward: 229.085±83.061, Episode_length: 475.700±373.157\n", ++ "Rollout 7804/9766, Reward: 274.943±32.159, Episode_length: 357.700±326.921\n", ++ "Rollout 7805/9766, Reward: 282.988±34.671, Episode_length: 256.200±248.003\n", ++ "Rollout 7806/9766, Reward: 294.666±13.460, Episode_length: 165.000±20.263\n", ++ "Rollout 7807/9766, Reward: 289.570±23.361, Episode_length: 168.200±15.664\n", ++ "Rollout 7808/9766, Reward: 275.731±34.511, Episode_length: 239.300±253.798\n", ++ "Rollout 7809/9766, Reward: 284.295±38.445, Episode_length: 256.400±248.632\n", ++ "Rollout 7810/9766, Reward: 280.552±38.420, Episode_length: 251.800±249.779\n", ++ "Rollout 7811/9766, Reward: 289.683±13.695, Episode_length: 157.600±17.619\n", ++ "Rollout 7812/9766, Reward: 275.368±41.853, Episode_length: 243.000±252.944\n", ++ "Rollout 7813/9766, Reward: 291.780±18.098, Episode_length: 181.400±27.768\n", ++ "Rollout 7814/9766, Reward: 278.989±33.306, Episode_length: 246.100±251.753\n", ++ "Rollout 7815/9766, Reward: 284.685±17.889, Episode_length: 154.900±17.242\n", ++ "Rollout 7816/9766, Reward: 300.496±12.463, Episode_length: 163.700±18.000\n", ++ "Rollout 7817/9766, Reward: 280.135±17.756, Episode_length: 200.300±141.707\n", ++ "Rollout 7818/9766, Reward: 285.628±18.474, Episode_length: 158.700±11.341\n", ++ "Rollout 7819/9766, Reward: 266.587±37.293, Episode_length: 329.100±335.888\n", ++ "Rollout 7820/9766, Reward: 290.011±19.510, Episode_length: 178.400±25.644\n", ++ "Rollout 7821/9766, Reward: 289.329±12.898, Episode_length: 165.400±19.043\n", ++ "Rollout 7822/9766, Reward: 201.473±48.707, Episode_length: 869.100±270.879\n", ++ "Rollout 7823/9766, Reward: 156.412±19.751, Episode_length: 1000.000±0.000\n", ++ "Rollout 7824/9766, Reward: 153.256±22.424, Episode_length: 1000.000±0.000\n", ++ "Rollout 7825/9766, Reward: 168.648±50.824, Episode_length: 921.000±237.000\n", ++ "Rollout 7826/9766, Reward: 176.188±42.180, Episode_length: 934.900±195.300\n", ++ "Rollout 7827/9766, Reward: 161.591±15.235, Episode_length: 1000.000±0.000\n", ++ "Rollout 7828/9766, Reward: 142.901±19.322, Episode_length: 1000.000±0.000\n", ++ "Rollout 7829/9766, Reward: 145.739±25.724, Episode_length: 1000.000±0.000\n", ++ "Rollout 7830/9766, Reward: 152.177±17.124, Episode_length: 1000.000±0.000\n", ++ "Rollout 7831/9766, Reward: 164.209±19.984, Episode_length: 1000.000±0.000\n", ++ "Rollout 7832/9766, Reward: 172.554±73.611, Episode_length: 764.200±364.132\n", ++ "Rollout 7833/9766, Reward: 153.872±13.687, Episode_length: 1000.000±0.000\n", ++ "Rollout 7834/9766, Reward: 167.880±43.313, Episode_length: 985.300±44.100\n", ++ "Rollout 7835/9766, Reward: 158.678±13.746, Episode_length: 1000.000±0.000\n", ++ "Rollout 7836/9766, Reward: 158.654±23.902, Episode_length: 1000.000±0.000\n", ++ "Rollout 7837/9766, Reward: 147.591±18.197, Episode_length: 1000.000±0.000\n", ++ "Rollout 7838/9766, Reward: 136.047±34.804, Episode_length: 910.800±267.600\n", ++ "Rollout 7839/9766, Reward: 187.087±54.815, Episode_length: 835.900±324.992\n", ++ "Rollout 7840/9766, Reward: 177.615±51.409, Episode_length: 838.800±322.802\n", ++ "Rollout 7841/9766, Reward: 205.375±73.390, Episode_length: 691.300±378.565\n", ++ "Rollout 7842/9766, Reward: 178.502±52.693, Episode_length: 849.600±303.027\n", ++ "Rollout 7843/9766, Reward: 173.006±45.819, Episode_length: 919.500±241.500\n", ++ "Rollout 7844/9766, Reward: 186.011±45.448, Episode_length: 835.500±329.001\n", ++ "Rollout 7845/9766, Reward: 268.937±33.815, Episode_length: 384.500±293.504\n", ++ "Rollout 7846/9766, Reward: 281.229±16.065, Episode_length: 177.500±18.413\n", ++ "Rollout 7847/9766, Reward: 254.629±50.548, Episode_length: 412.600±367.818\n", ++ "Rollout 7848/9766, Reward: 243.212±58.476, Episode_length: 604.000±378.793\n", ++ "Rollout 7849/9766, Reward: 277.201±33.248, Episode_length: 392.400±346.889\n", ++ "Rollout 7850/9766, Reward: 276.643±18.057, Episode_length: 223.100±164.984\n", ++ "Rollout 7851/9766, Reward: 223.198±60.974, Episode_length: 586.200±413.964\n", ++ "Rollout 7852/9766, Reward: 289.852±14.710, Episode_length: 167.700±21.845\n", ++ "Rollout 7853/9766, Reward: 249.841±46.327, Episode_length: 544.900±396.226\n", ++ "Rollout 7854/9766, Reward: 274.813±29.782, Episode_length: 403.700±325.946\n", ++ "Rollout 7855/9766, Reward: 248.593±62.766, Episode_length: 590.200±387.837\n", ++ "Rollout 7856/9766, Reward: 254.562±44.044, Episode_length: 564.200±359.727\n", ++ "Rollout 7857/9766, Reward: 242.153±48.562, Episode_length: 599.100±373.026\n", ++ "Rollout 7858/9766, Reward: 277.853±10.156, Episode_length: 365.200±330.943\n", ++ "Rollout 7859/9766, Reward: 270.125±41.447, Episode_length: 286.000±269.352\n", ++ "Rollout 7860/9766, Reward: 220.260±46.421, Episode_length: 681.800±363.377\n", ++ "Rollout 7861/9766, Reward: 267.976±42.363, Episode_length: 315.200±316.077\n", ++ "Rollout 7862/9766, Reward: 279.455±13.724, Episode_length: 151.200±13.136\n", ++ "Rollout 7863/9766, Reward: 297.542±12.709, Episode_length: 170.100±17.513\n", ++ "Rollout 7864/9766, Reward: 281.956±17.648, Episode_length: 176.600±29.689\n", ++ "Rollout 7865/9766, Reward: 288.752±18.891, Episode_length: 168.300±17.527\n", ++ "Rollout 7866/9766, Reward: 283.821±13.593, Episode_length: 154.900±15.852\n", ++ "Rollout 7867/9766, Reward: 290.656±15.419, Episode_length: 193.900±78.387\n", ++ "Rollout 7868/9766, Reward: 294.311±19.206, Episode_length: 353.200±215.439\n", ++ "Rollout 7869/9766, Reward: 293.879±15.984, Episode_length: 317.900±106.143\n", ++ "Rollout 7870/9766, Reward: 283.755±15.126, Episode_length: 480.700±109.880\n", ++ "Rollout 7871/9766, Reward: 154.662±15.825, Episode_length: 1000.000±0.000\n", ++ "Rollout 7872/9766, Reward: 282.198±20.662, Episode_length: 511.200±141.776\n", ++ "Rollout 7873/9766, Reward: 179.853±47.241, Episode_length: 916.300±251.100\n", ++ "Rollout 7874/9766, Reward: 151.563±22.770, Episode_length: 1000.000±0.000\n", ++ "Rollout 7875/9766, Reward: 167.925±42.374, Episode_length: 935.400±193.800\n", ++ "Rollout 7876/9766, Reward: 150.115±17.166, Episode_length: 1000.000±0.000\n", ++ "Rollout 7877/9766, Reward: 169.502±20.993, Episode_length: 1000.000±0.000\n", ++ "Rollout 7878/9766, Reward: 167.357±22.796, Episode_length: 1000.000±0.000\n", ++ "Rollout 7879/9766, Reward: 160.344±22.613, Episode_length: 1000.000±0.000\n", ++ "Rollout 7880/9766, Reward: 155.228±24.351, Episode_length: 1000.000±0.000\n", ++ "Rollout 7881/9766, Reward: 147.245±17.648, Episode_length: 1000.000±0.000\n", ++ "Rollout 7882/9766, Reward: 148.348±22.727, Episode_length: 1000.000±0.000\n", ++ "Rollout 7883/9766, Reward: 158.074±19.254, Episode_length: 1000.000±0.000\n", ++ "Rollout 7884/9766, Reward: 157.646±24.051, Episode_length: 1000.000±0.000\n", ++ "Rollout 7885/9766, Reward: 167.861±48.710, Episode_length: 920.400±238.800\n", ++ "Rollout 7886/9766, Reward: 161.499±18.053, Episode_length: 1000.000±0.000\n", ++ "Rollout 7887/9766, Reward: 166.810±36.099, Episode_length: 973.600±79.200\n", ++ "Rollout 7888/9766, Reward: 170.993±44.598, Episode_length: 899.700±244.482\n", ++ "Rollout 7889/9766, Reward: 178.394±38.635, Episode_length: 927.300±147.429\n", ++ "Rollout 7890/9766, Reward: 155.226±18.685, Episode_length: 1000.000±0.000\n", ++ "Rollout 7891/9766, Reward: 267.505±20.236, Episode_length: 190.500±15.095\n", ++ "Rollout 7892/9766, Reward: 248.580±37.081, Episode_length: 370.900±291.332\n", ++ "Rollout 7893/9766, Reward: 265.707±26.181, Episode_length: 263.400±190.229\n", ++ "Rollout 7894/9766, Reward: 244.564±25.843, Episode_length: 317.300±164.957\n", ++ "Rollout 7895/9766, Reward: 276.485±21.748, Episode_length: 218.000±86.618\n", ++ "Rollout 7896/9766, Reward: 258.410±36.677, Episode_length: 263.400±246.024\n", ++ "Rollout 7897/9766, Reward: 242.620±50.670, Episode_length: 389.700±310.820\n", ++ "Rollout 7898/9766, Reward: 266.996±18.600, Episode_length: 263.400±162.416\n", ++ "Rollout 7899/9766, Reward: 233.729±55.575, Episode_length: 402.200±320.332\n", ++ "Rollout 7900/9766, Reward: 258.739±36.180, Episode_length: 251.900±149.433\n", ++ "Rollout 7901/9766, Reward: 217.450±56.381, Episode_length: 501.500±315.936\n", ++ "Rollout 7902/9766, Reward: 212.270±59.643, Episode_length: 528.300±256.125\n", ++ "Rollout 7903/9766, Reward: 233.018±47.622, Episode_length: 374.500±288.962\n", ++ "Rollout 7904/9766, Reward: 222.483±47.344, Episode_length: 343.300±257.892\n", ++ "Rollout 7905/9766, Reward: 259.031±23.850, Episode_length: 223.000±110.237\n", ++ "Rollout 7906/9766, Reward: 204.481±61.179, Episode_length: 575.700±362.777\n", ++ "Rollout 7907/9766, Reward: 253.357±34.222, Episode_length: 285.300±107.228\n", ++ "Rollout 7908/9766, Reward: 242.285±28.588, Episode_length: 279.500±137.924\n", ++ "Rollout 7909/9766, Reward: 244.549±47.677, Episode_length: 310.300±240.448\n", ++ "Rollout 7910/9766, Reward: 232.607±36.183, Episode_length: 362.300±253.101\n", ++ "Rollout 7911/9766, Reward: 201.017±40.457, Episode_length: 504.300±258.268\n", ++ "Rollout 7912/9766, Reward: 204.461±84.527, Episode_length: 351.100±333.331\n", ++ "Rollout 7913/9766, Reward: 234.552±34.754, Episode_length: 312.500±106.909\n", ++ "Rollout 7914/9766, Reward: 245.326±48.226, Episode_length: 376.000±251.653\n", ++ "Rollout 7915/9766, Reward: 222.365±32.184, Episode_length: 475.800±239.097\n", ++ "Rollout 7916/9766, Reward: 221.239±51.279, Episode_length: 395.100±238.802\n", ++ "Rollout 7917/9766, Reward: 212.832±40.504, Episode_length: 440.800±300.264\n", ++ "Rollout 7918/9766, Reward: 231.042±42.171, Episode_length: 330.000±241.993\n", ++ "Rollout 7919/9766, Reward: 197.626±49.787, Episode_length: 492.400±350.704\n", ++ "Rollout 7920/9766, Reward: 231.938±53.486, Episode_length: 372.800±319.820\n", ++ "Rollout 7921/9766, Reward: 201.345±53.401, Episode_length: 584.300±297.056\n", ++ "Rollout 7922/9766, Reward: 215.187±36.109, Episode_length: 414.400±142.888\n", ++ "Rollout 7923/9766, Reward: 241.462±64.326, Episode_length: 387.400±306.785\n", ++ "Rollout 7924/9766, Reward: 223.878±43.102, Episode_length: 430.200±277.661\n", ++ "Rollout 7925/9766, Reward: 168.855±87.609, Episode_length: 619.000±344.411\n", ++ "Rollout 7926/9766, Reward: 250.224±51.982, Episode_length: 435.400±283.744\n", ++ "Rollout 7927/9766, Reward: 219.186±63.633, Episode_length: 593.900±273.903\n", ++ "Rollout 7928/9766, Reward: 219.679±66.678, Episode_length: 571.600±349.877\n", ++ "Rollout 7929/9766, Reward: 201.767±59.103, Episode_length: 624.600±377.317\n", ++ "Rollout 7930/9766, Reward: 224.142±62.367, Episode_length: 455.600±364.233\n", ++ "Rollout 7931/9766, Reward: 183.956±65.914, Episode_length: 692.600±381.745\n", ++ "Rollout 7932/9766, Reward: 218.124±71.326, Episode_length: 521.300±391.832\n", ++ "Rollout 7933/9766, Reward: 233.089±69.434, Episode_length: 418.100±381.299\n", ++ "Rollout 7934/9766, Reward: 274.078±22.401, Episode_length: 201.300±58.359\n", ++ "Rollout 7935/9766, Reward: 216.622±63.411, Episode_length: 558.900±405.585\n", ++ "Rollout 7936/9766, Reward: 226.614±51.508, Episode_length: 547.400±389.811\n", ++ "Rollout 7937/9766, Reward: 236.653±64.032, Episode_length: 357.900±322.930\n", ++ "Rollout 7938/9766, Reward: 246.187±45.702, Episode_length: 272.800±245.487\n", ++ "Rollout 7939/9766, Reward: 267.731±46.698, Episode_length: 291.100±249.301\n", ++ "Rollout 7940/9766, Reward: 250.448±46.124, Episode_length: 355.900±325.325\n", ++ "Rollout 7941/9766, Reward: 257.326±48.537, Episode_length: 283.100±248.626\n", ++ "Rollout 7942/9766, Reward: 260.321±45.618, Episode_length: 287.200±250.518\n", ++ "Rollout 7943/9766, Reward: 260.130±38.568, Episode_length: 269.900±247.229\n", ++ "Rollout 7944/9766, Reward: 227.691±61.607, Episode_length: 552.000±388.558\n", ++ "Rollout 7945/9766, Reward: 200.069±84.477, Episode_length: 427.100±375.926\n", ++ "Rollout 7946/9766, Reward: 236.866±64.407, Episode_length: 342.400±329.487\n", ++ "Rollout 7947/9766, Reward: 260.701±68.496, Episode_length: 385.600±312.634\n", ++ "Rollout 7948/9766, Reward: 244.110±54.789, Episode_length: 337.300±295.249\n", ++ "Rollout 7949/9766, Reward: 250.146±58.617, Episode_length: 355.900±323.931\n", ++ "Rollout 7950/9766, Reward: 229.300±68.768, Episode_length: 471.500±371.931\n", ++ "Rollout 7951/9766, Reward: 205.549±74.127, Episode_length: 583.700±417.175\n", ++ "Rollout 7952/9766, Reward: 245.938±60.385, Episode_length: 350.100±325.182\n", ++ "Rollout 7953/9766, Reward: 246.582±58.220, Episode_length: 354.600±324.083\n", ++ "Rollout 7954/9766, Reward: 208.960±73.896, Episode_length: 445.200±374.240\n", ++ "Rollout 7955/9766, Reward: 227.939±58.547, Episode_length: 444.900±364.853\n", ++ "Rollout 7956/9766, Reward: 236.615±70.458, Episode_length: 360.200±322.142\n", ++ "Rollout 7957/9766, Reward: 246.655±63.646, Episode_length: 360.100±321.647\n", ++ "Rollout 7958/9766, Reward: 243.388±58.243, Episode_length: 260.200±247.143\n", ++ "Rollout 7959/9766, Reward: 231.208±71.822, Episode_length: 422.700±378.351\n", ++ "Rollout 7960/9766, Reward: 282.320±12.073, Episode_length: 175.700±53.479\n", ++ "Rollout 7961/9766, Reward: 278.610±14.152, Episode_length: 166.000±23.732\n", ++ "Rollout 7962/9766, Reward: 263.767±47.679, Episode_length: 287.300±243.194\n", ++ "Rollout 7963/9766, Reward: 284.999±20.581, Episode_length: 161.200±18.203\n", ++ "Rollout 7964/9766, Reward: 251.842±65.495, Episode_length: 348.100±326.430\n", ++ "Rollout 7965/9766, Reward: 284.601±19.811, Episode_length: 254.300±203.760\n", ++ "Rollout 7966/9766, Reward: 283.306±19.429, Episode_length: 181.400±20.766\n", ++ "Rollout 7967/9766, Reward: 258.067±48.679, Episode_length: 338.900±330.988\n", ++ "Rollout 7968/9766, Reward: 273.871±31.872, Episode_length: 248.000±250.943\n", ++ "Rollout 7969/9766, Reward: 272.009±19.322, Episode_length: 163.900±18.870\n", ++ "Rollout 7970/9766, Reward: 257.846±47.507, Episode_length: 381.300±356.541\n", ++ "Rollout 7971/9766, Reward: 290.059±14.613, Episode_length: 169.000±17.821\n", ++ "Rollout 7972/9766, Reward: 269.174±73.388, Episode_length: 168.200±32.018\n", ++ "Rollout 7973/9766, Reward: 290.823±15.800, Episode_length: 168.700±23.039\n", ++ "Rollout 7974/9766, Reward: 277.069±33.165, Episode_length: 255.900±248.478\n", ++ "Rollout 7975/9766, Reward: 276.528±21.504, Episode_length: 171.300±19.586\n", ++ "Rollout 7976/9766, Reward: 287.931±14.624, Episode_length: 174.500±26.246\n", ++ "Rollout 7977/9766, Reward: 269.146±42.029, Episode_length: 257.000±248.277\n", ++ "Rollout 7978/9766, Reward: 272.166±71.425, Episode_length: 176.200±24.951\n", ++ "Rollout 7979/9766, Reward: 303.359±4.124, Episode_length: 174.600±21.588\n", ++ "Rollout 7980/9766, Reward: 286.707±21.417, Episode_length: 163.000±13.682\n", ++ "Rollout 7981/9766, Reward: 296.338±18.223, Episode_length: 165.800±20.812\n", ++ "Rollout 7982/9766, Reward: 288.250±13.779, Episode_length: 167.400±14.115\n", ++ "Rollout 7983/9766, Reward: 271.164±33.074, Episode_length: 243.600±252.466\n", ++ "Rollout 7984/9766, Reward: 287.826±36.245, Episode_length: 252.000±250.044\n", ++ "Rollout 7985/9766, Reward: 290.426±13.126, Episode_length: 168.600±15.756\n", ++ "Rollout 7986/9766, Reward: 287.813±18.363, Episode_length: 165.200±22.076\n", ++ "Rollout 7987/9766, Reward: 290.762±10.231, Episode_length: 163.800±14.559\n", ++ "Rollout 7988/9766, Reward: 286.657±16.114, Episode_length: 157.100±15.346\n", ++ "Rollout 7989/9766, Reward: 287.234±38.306, Episode_length: 252.500±250.045\n", ++ "Rollout 7990/9766, Reward: 256.189±82.148, Episode_length: 246.600±252.764\n", ++ "Rollout 7991/9766, Reward: 286.359±16.514, Episode_length: 160.800±19.130\n", ++ "Rollout 7992/9766, Reward: 286.724±14.311, Episode_length: 162.700±13.806\n", ++ "Rollout 7993/9766, Reward: 280.747±19.312, Episode_length: 165.500±14.658\n", ++ "Rollout 7994/9766, Reward: 286.855±18.102, Episode_length: 165.600±12.753\n", ++ "Rollout 7995/9766, Reward: 288.887±12.829, Episode_length: 169.700±13.972\n", ++ "Rollout 7996/9766, Reward: 279.329±34.024, Episode_length: 252.900±249.421\n", ++ "Rollout 7997/9766, Reward: 290.448±9.784, Episode_length: 166.900±13.202\n", ++ "Rollout 7998/9766, Reward: 294.491±20.258, Episode_length: 166.600±25.057\n", ++ "Rollout 7999/9766, Reward: 282.140±11.996, Episode_length: 161.400±13.477\n", ++ "Rollout 8000/9766, Reward: 264.255±74.884, Episode_length: 152.400±24.200\n", ++ "Rollout 8001/9766, Reward: 289.987±21.188, Episode_length: 175.300±19.011\n", ++ "Rollout 8002/9766, Reward: 273.181±28.572, Episode_length: 251.100±250.502\n", ++ "Rollout 8003/9766, Reward: 288.947±18.826, Episode_length: 231.300±218.922\n", ++ "Rollout 8004/9766, Reward: 272.460±43.148, Episode_length: 247.900±251.836\n", ++ "Rollout 8005/9766, Reward: 261.332±42.042, Episode_length: 245.300±252.067\n", ++ "Rollout 8006/9766, Reward: 279.761±41.760, Episode_length: 252.200±250.280\n", ++ "Rollout 8007/9766, Reward: 293.691±10.288, Episode_length: 167.700±15.659\n", ++ "Rollout 8008/9766, Reward: 284.118±13.153, Episode_length: 165.100±14.639\n", ++ "Rollout 8009/9766, Reward: 264.934±63.155, Episode_length: 333.100±333.814\n", ++ "Rollout 8010/9766, Reward: 231.880±71.263, Episode_length: 418.000±381.067\n", ++ "Rollout 8011/9766, Reward: 282.894±11.855, Episode_length: 162.700±14.806\n", ++ "Rollout 8012/9766, Reward: 270.483±34.276, Episode_length: 243.400±252.442\n", ++ "Rollout 8013/9766, Reward: 276.816±48.388, Episode_length: 262.200±247.519\n", ++ "Rollout 8014/9766, Reward: 236.886±73.192, Episode_length: 499.300±408.951\n", ++ "Rollout 8015/9766, Reward: 286.335±18.868, Episode_length: 167.200±20.307\n", ++ "Rollout 8016/9766, Reward: 259.007±51.123, Episode_length: 324.900±337.892\n", ++ "Rollout 8017/9766, Reward: 270.739±55.149, Episode_length: 334.400±333.213\n", ++ "Rollout 8018/9766, Reward: 238.892±84.311, Episode_length: 235.900±256.154\n", ++ "Rollout 8019/9766, Reward: 256.509±49.733, Episode_length: 322.700±338.930\n", ++ "Rollout 8020/9766, Reward: 216.826±87.958, Episode_length: 408.000±388.541\n", ++ "Rollout 8021/9766, Reward: 273.422±38.462, Episode_length: 308.200±307.709\n", ++ "Rollout 8022/9766, Reward: 230.883±60.613, Episode_length: 408.300±387.619\n", ++ "Rollout 8023/9766, Reward: 260.239±48.690, Episode_length: 329.100±335.757\n", ++ "Rollout 8024/9766, Reward: 282.350±18.136, Episode_length: 157.900±12.235\n", ++ "Rollout 8025/9766, Reward: 272.679±33.197, Episode_length: 312.300±308.617\n", ++ "Rollout 8026/9766, Reward: 238.231±60.283, Episode_length: 535.200±391.694\n", ++ "Rollout 8027/9766, Reward: 270.828±16.803, Episode_length: 238.700±250.365\n", ++ "Rollout 8028/9766, Reward: 273.433±44.922, Episode_length: 334.300±318.494\n", ++ "Rollout 8029/9766, Reward: 240.526±67.014, Episode_length: 417.400±381.832\n", ++ "Rollout 8030/9766, Reward: 274.323±15.171, Episode_length: 163.400±20.475\n", ++ "Rollout 8031/9766, Reward: 273.743±57.743, Episode_length: 252.500±249.629\n", ++ "Rollout 8032/9766, Reward: 216.098±90.133, Episode_length: 324.300±338.560\n", ++ "Rollout 8033/9766, Reward: 275.729±26.350, Episode_length: 249.100±250.722\n", ++ "Rollout 8034/9766, Reward: 267.171±47.153, Episode_length: 380.500±337.797\n", ++ "Rollout 8035/9766, Reward: 264.310±49.822, Episode_length: 262.400±246.887\n", ++ "Rollout 8036/9766, Reward: 257.934±56.631, Episode_length: 427.000±376.966\n", ++ "Rollout 8037/9766, Reward: 268.657±35.980, Episode_length: 298.700±289.699\n", ++ "Rollout 8038/9766, Reward: 261.835±59.552, Episode_length: 331.300±334.616\n", ++ "Rollout 8039/9766, Reward: 249.278±46.982, Episode_length: 410.400±386.184\n", ++ "Rollout 8040/9766, Reward: 257.785±43.501, Episode_length: 244.100±252.550\n", ++ "Rollout 8041/9766, Reward: 267.758±39.558, Episode_length: 249.900±250.786\n", ++ "Rollout 8042/9766, Reward: 269.813±15.772, Episode_length: 167.700±16.340\n", ++ "Rollout 8043/9766, Reward: 278.873±41.099, Episode_length: 256.100±248.151\n", ++ "Rollout 8044/9766, Reward: 263.651±38.407, Episode_length: 239.900±253.583\n", ++ "Rollout 8045/9766, Reward: 251.003±51.755, Episode_length: 326.000±337.154\n", ++ "Rollout 8046/9766, Reward: 261.306±37.426, Episode_length: 249.300±250.850\n", ++ "Rollout 8047/9766, Reward: 255.452±70.114, Episode_length: 495.800±400.281\n", ++ "Rollout 8048/9766, Reward: 271.519±52.047, Episode_length: 246.100±252.088\n", ++ "Rollout 8049/9766, Reward: 266.241±33.331, Episode_length: 308.800±279.331\n", ++ "Rollout 8050/9766, Reward: 272.497±42.535, Episode_length: 258.800±253.615\n", ++ "Rollout 8051/9766, Reward: 264.475±46.839, Episode_length: 365.700±325.300\n", ++ "Rollout 8052/9766, Reward: 263.747±52.924, Episode_length: 343.200±330.607\n", ++ "Rollout 8053/9766, Reward: 277.810±20.843, Episode_length: 153.200±12.065\n", ++ "Rollout 8054/9766, Reward: 276.670±18.295, Episode_length: 183.800±39.927\n", ++ "Rollout 8055/9766, Reward: 288.016±9.676, Episode_length: 168.800±29.946\n", ++ "Rollout 8056/9766, Reward: 256.116±44.188, Episode_length: 338.300±331.419\n", ++ "Rollout 8057/9766, Reward: 284.801±20.878, Episode_length: 184.200±57.882\n", ++ "Rollout 8058/9766, Reward: 237.434±84.188, Episode_length: 322.700±339.957\n", ++ "Rollout 8059/9766, Reward: 258.272±50.160, Episode_length: 328.400±336.084\n", ++ "Rollout 8060/9766, Reward: 241.811±58.313, Episode_length: 510.300±400.561\n", ++ "Rollout 8061/9766, Reward: 279.045±32.903, Episode_length: 249.800±250.467\n", ++ "Rollout 8062/9766, Reward: 247.227±49.478, Episode_length: 408.400±387.516\n", ++ "Rollout 8063/9766, Reward: 257.996±38.651, Episode_length: 328.600±336.049\n", ++ "Rollout 8064/9766, Reward: 261.026±47.766, Episode_length: 392.300±324.126\n", ++ "Rollout 8065/9766, Reward: 241.905±53.034, Episode_length: 481.800±390.972\n", ++ "Rollout 8066/9766, Reward: 220.402±60.058, Episode_length: 682.500±385.752\n", ++ "Rollout 8067/9766, Reward: 287.887±20.443, Episode_length: 208.400±75.304\n", ++ "Rollout 8068/9766, Reward: 226.869±59.793, Episode_length: 629.600±383.410\n", ++ "Rollout 8069/9766, Reward: 233.026±51.524, Episode_length: 553.100±381.692\n", ++ "Rollout 8070/9766, Reward: 198.758±58.457, Episode_length: 745.000±389.568\n", ++ "Rollout 8071/9766, Reward: 259.755±50.130, Episode_length: 349.600±327.106\n", ++ "Rollout 8072/9766, Reward: 259.635±52.988, Episode_length: 333.200±334.936\n", ++ "Rollout 8073/9766, Reward: 280.093±14.519, Episode_length: 160.800±21.683\n", ++ "Rollout 8074/9766, Reward: 276.609±36.377, Episode_length: 244.700±252.163\n", ++ "Rollout 8075/9766, Reward: 265.643±44.181, Episode_length: 311.100±312.582\n", ++ "Rollout 8076/9766, Reward: 267.110±36.175, Episode_length: 247.500±251.653\n", ++ "Rollout 8077/9766, Reward: 267.473±36.929, Episode_length: 298.900±273.937\n", ++ "Rollout 8078/9766, Reward: 244.521±55.005, Episode_length: 417.200±381.888\n", ++ "Rollout 8079/9766, Reward: 272.218±15.556, Episode_length: 249.000±249.501\n", ++ "Rollout 8080/9766, Reward: 279.125±16.492, Episode_length: 170.200±28.481\n", ++ "Rollout 8081/9766, Reward: 248.533±55.975, Episode_length: 416.800±382.456\n", ++ "Rollout 8082/9766, Reward: 282.101±19.557, Episode_length: 168.500±14.975\n", ++ "Rollout 8083/9766, Reward: 269.649±21.481, Episode_length: 282.300±237.097\n", ++ "Rollout 8084/9766, Reward: 256.363±59.223, Episode_length: 361.700±321.327\n", ++ "Rollout 8085/9766, Reward: 267.587±43.953, Episode_length: 268.200±246.647\n", ++ "Rollout 8086/9766, Reward: 261.430±55.070, Episode_length: 341.700±330.868\n", ++ "Rollout 8087/9766, Reward: 271.812±22.221, Episode_length: 261.900±214.330\n", ++ "Rollout 8088/9766, Reward: 256.403±43.773, Episode_length: 326.500±337.360\n", ++ "Rollout 8089/9766, Reward: 223.784±55.771, Episode_length: 581.900±418.292\n", ++ "Rollout 8090/9766, Reward: 177.650±54.835, Episode_length: 907.100±229.307\n", ++ "Rollout 8091/9766, Reward: 180.042±48.312, Episode_length: 838.300±323.747\n", ++ "Rollout 8092/9766, Reward: 186.235±67.403, Episode_length: 774.900±347.284\n", ++ "Rollout 8093/9766, Reward: 175.559±51.701, Episode_length: 828.300±343.402\n", ++ "Rollout 8094/9766, Reward: 200.401±76.972, Episode_length: 707.000±363.677\n", ++ "Rollout 8095/9766, Reward: 164.498±31.194, Episode_length: 974.000±78.000\n", ++ "Rollout 8096/9766, Reward: 191.134±152.842, Episode_length: 527.300±387.116\n", ++ "Rollout 8097/9766, Reward: 227.023±62.947, Episode_length: 515.800±396.145\n", ++ "Rollout 8098/9766, Reward: 154.205±70.179, Episode_length: 831.200±338.665\n", ++ "Rollout 8099/9766, Reward: 165.306±35.428, Episode_length: 922.900±231.300\n", ++ "Rollout 8100/9766, Reward: 204.089±61.266, Episode_length: 601.100±400.326\n", ++ "Rollout 8101/9766, Reward: 192.717±52.027, Episode_length: 792.000±323.603\n", ++ "Rollout 8102/9766, Reward: 173.316±64.521, Episode_length: 834.300±331.455\n", ++ "Rollout 8103/9766, Reward: 258.765±50.603, Episode_length: 461.000±375.276\n", ++ "Rollout 8104/9766, Reward: 253.117±49.641, Episode_length: 427.300±343.404\n", ++ "Rollout 8105/9766, Reward: 236.936±51.326, Episode_length: 426.300±376.266\n", ++ "Rollout 8106/9766, Reward: 209.788±64.263, Episode_length: 674.200±399.242\n", ++ "Rollout 8107/9766, Reward: 263.726±56.158, Episode_length: 333.800±334.056\n", ++ "Rollout 8108/9766, Reward: 284.284±18.944, Episode_length: 157.400±18.090\n", ++ "Rollout 8109/9766, Reward: 286.148±15.704, Episode_length: 177.900±20.964\n", ++ "Rollout 8110/9766, Reward: 265.598±34.569, Episode_length: 361.500±322.321\n", ++ "Rollout 8111/9766, Reward: 282.791±16.539, Episode_length: 180.600±56.525\n", ++ "Rollout 8112/9766, Reward: 233.829±59.845, Episode_length: 581.400±415.688\n", ++ "Rollout 8113/9766, Reward: 183.577±51.748, Episode_length: 829.000±342.000\n", ++ "Rollout 8114/9766, Reward: 194.502±50.070, Episode_length: 875.900±264.052\n", ++ "Rollout 8115/9766, Reward: 168.694±33.709, Episode_length: 985.500±43.500\n", ++ "Rollout 8116/9766, Reward: 190.790±55.200, Episode_length: 872.300±255.616\n", ++ "Rollout 8117/9766, Reward: 195.124±66.630, Episode_length: 785.800±328.974\n", ++ "Rollout 8118/9766, Reward: 193.909±63.333, Episode_length: 889.300±246.392\n", ++ "Rollout 8119/9766, Reward: 154.277±13.717, Episode_length: 1000.000±0.000\n", ++ "Rollout 8120/9766, Reward: 201.461±40.626, Episode_length: 744.700±390.022\n", ++ "Rollout 8121/9766, Reward: 177.272±67.795, Episode_length: 860.000±271.434\n", ++ "Rollout 8122/9766, Reward: 236.305±46.857, Episode_length: 712.700±362.424\n", ++ "Rollout 8123/9766, Reward: 204.180±46.781, Episode_length: 838.400±323.300\n", ++ "Rollout 8124/9766, Reward: 219.164±46.592, Episode_length: 808.500±318.364\n", ++ "Rollout 8125/9766, Reward: 229.341±57.779, Episode_length: 632.400±398.451\n", ++ "Rollout 8126/9766, Reward: 260.280±36.622, Episode_length: 321.000±339.765\n", ++ "Rollout 8127/9766, Reward: 265.480±45.538, Episode_length: 341.700±332.235\n", ++ "Rollout 8128/9766, Reward: 234.628±52.141, Episode_length: 632.700±392.163\n", ++ "Rollout 8129/9766, Reward: 262.954±38.509, Episode_length: 326.200±337.162\n", ++ "Rollout 8130/9766, Reward: 277.706±52.166, Episode_length: 405.600±307.096\n", ++ "Rollout 8131/9766, Reward: 278.579±40.043, Episode_length: 256.100±248.975\n", ++ "Rollout 8132/9766, Reward: 256.064±48.439, Episode_length: 576.300±289.882\n", ++ "Rollout 8133/9766, Reward: 268.217±40.300, Episode_length: 544.600±180.097\n", ++ "Rollout 8134/9766, Reward: 255.310±43.550, Episode_length: 640.700±135.362\n", ++ "Rollout 8135/9766, Reward: 249.060±57.578, Episode_length: 555.700±249.843\n", ++ "Rollout 8136/9766, Reward: 223.626±56.793, Episode_length: 650.500±298.485\n", ++ "Rollout 8137/9766, Reward: 237.182±67.337, Episode_length: 610.300±297.261\n", ++ "Rollout 8138/9766, Reward: 274.785±39.814, Episode_length: 268.700±252.860\n", ++ "Rollout 8139/9766, Reward: 286.337±20.485, Episode_length: 163.600±14.814\n", ++ "Rollout 8140/9766, Reward: 288.742±24.030, Episode_length: 162.900±20.280\n", ++ "Rollout 8141/9766, Reward: 270.962±41.991, Episode_length: 245.100±251.949\n", ++ "Rollout 8142/9766, Reward: 287.084±16.446, Episode_length: 165.800±11.600\n", ++ "Rollout 8143/9766, Reward: 278.097±13.340, Episode_length: 151.800±20.721\n", ++ "Rollout 8144/9766, Reward: 277.284±19.160, Episode_length: 152.700±15.944\n", ++ "Rollout 8145/9766, Reward: 278.220±12.549, Episode_length: 246.600±244.362\n", ++ "Rollout 8146/9766, Reward: 279.744±22.301, Episode_length: 155.900±10.737\n", ++ "Rollout 8147/9766, Reward: 276.687±48.026, Episode_length: 322.300±289.801\n", ++ "Rollout 8148/9766, Reward: 275.658±31.501, Episode_length: 280.000±253.009\n", ++ "Rollout 8149/9766, Reward: 286.783±12.141, Episode_length: 410.900±30.550\n", ++ "Rollout 8150/9766, Reward: 292.496±14.654, Episode_length: 316.600±85.955\n", ++ "Rollout 8151/9766, Reward: 285.017±20.256, Episode_length: 520.400±63.866\n", ++ "Rollout 8152/9766, Reward: 170.697±45.112, Episode_length: 929.500±211.500\n", ++ "Rollout 8153/9766, Reward: 170.830±43.543, Episode_length: 926.900±219.300\n", ++ "Rollout 8154/9766, Reward: 171.779±41.455, Episode_length: 949.800±150.600\n", ++ "Rollout 8155/9766, Reward: 170.382±14.048, Episode_length: 1000.000±0.000\n", ++ "Rollout 8156/9766, Reward: 165.978±18.020, Episode_length: 1000.000±0.000\n", ++ "Rollout 8157/9766, Reward: 157.924±17.896, Episode_length: 1000.000±0.000\n", ++ "Rollout 8158/9766, Reward: 161.972±19.865, Episode_length: 1000.000±0.000\n", ++ "Rollout 8159/9766, Reward: 155.967±14.836, Episode_length: 1000.000±0.000\n", ++ "Rollout 8160/9766, Reward: 164.319±11.110, Episode_length: 1000.000±0.000\n", ++ "Rollout 8161/9766, Reward: 174.873±44.414, Episode_length: 971.500±85.500\n", ++ "Rollout 8162/9766, Reward: 152.340±18.549, Episode_length: 1000.000±0.000\n", ++ "Rollout 8163/9766, Reward: 276.811±14.568, Episode_length: 407.400±309.066\n", ++ "Rollout 8164/9766, Reward: 262.961±36.054, Episode_length: 518.500±375.431\n", ++ "Rollout 8165/9766, Reward: 290.559±16.779, Episode_length: 322.100±245.671\n", ++ "Rollout 8166/9766, Reward: 280.665±35.252, Episode_length: 539.100±337.848\n", ++ "Rollout 8167/9766, Reward: 259.453±45.544, Episode_length: 458.100±364.655\n", ++ "Rollout 8168/9766, Reward: 241.156±52.823, Episode_length: 791.200±315.266\n", ++ "Rollout 8169/9766, Reward: 236.516±70.851, Episode_length: 805.700±322.787\n", ++ "Rollout 8170/9766, Reward: 230.701±51.340, Episode_length: 960.300±69.564\n", ++ "Rollout 8171/9766, Reward: 244.743±62.200, Episode_length: 804.100±304.298\n", ++ "Rollout 8172/9766, Reward: 247.791±46.503, Episode_length: 743.100±339.858\n", ++ "Rollout 8173/9766, Reward: 218.915±56.967, Episode_length: 982.700±30.322\n", ++ "Rollout 8174/9766, Reward: 279.231±9.694, Episode_length: 859.300±196.065\n", ++ "Rollout 8175/9766, Reward: 223.242±48.341, Episode_length: 891.800±252.291\n", ++ "Rollout 8176/9766, Reward: 245.936±42.952, Episode_length: 879.600±144.884\n", ++ "Rollout 8177/9766, Reward: 267.654±46.157, Episode_length: 702.000±320.751\n", ++ "Rollout 8178/9766, Reward: 252.260±42.114, Episode_length: 712.100±346.556\n", ++ "Rollout 8179/9766, Reward: 259.833±50.726, Episode_length: 689.300±310.395\n", ++ "Rollout 8180/9766, Reward: 249.859±55.330, Episode_length: 722.400±370.145\n", ++ "Rollout 8181/9766, Reward: 247.444±48.249, Episode_length: 846.200±234.954\n", ++ "Rollout 8182/9766, Reward: 247.240±55.370, Episode_length: 790.300±317.524\n", ++ "Rollout 8183/9766, Reward: 272.431±49.198, Episode_length: 417.100±374.193\n", ++ "Rollout 8184/9766, Reward: 237.108±49.600, Episode_length: 743.500±318.260\n", ++ "Rollout 8185/9766, Reward: 289.843±18.598, Episode_length: 211.500±92.987\n", ++ "Rollout 8186/9766, Reward: 274.724±29.101, Episode_length: 356.000±299.474\n", ++ "Rollout 8187/9766, Reward: 291.575±13.160, Episode_length: 200.000±102.200\n", ++ "Rollout 8188/9766, Reward: 285.500±14.857, Episode_length: 423.500±96.654\n", ++ "Rollout 8189/9766, Reward: 277.588±16.550, Episode_length: 435.300±98.810\n", ++ "Rollout 8190/9766, Reward: 156.312±14.056, Episode_length: 1000.000±0.000\n", ++ "Rollout 8191/9766, Reward: 161.743±16.023, Episode_length: 1000.000±0.000\n", ++ "Rollout 8192/9766, Reward: 156.033±12.630, Episode_length: 1000.000±0.000\n", ++ "Rollout 8193/9766, Reward: 166.172±49.785, Episode_length: 918.700±243.900\n", ++ "Rollout 8194/9766, Reward: 156.114±17.573, Episode_length: 1000.000±0.000\n", ++ "Rollout 8195/9766, Reward: 143.973±24.089, Episode_length: 1000.000±0.000\n", ++ "Rollout 8196/9766, Reward: 151.368±21.716, Episode_length: 1000.000±0.000\n", ++ "Rollout 8197/9766, Reward: 146.017±13.208, Episode_length: 1000.000±0.000\n", ++ "Rollout 8198/9766, Reward: 161.044±15.622, Episode_length: 1000.000±0.000\n", ++ "Rollout 8199/9766, Reward: 126.493±88.507, Episode_length: 919.100±242.700\n", ++ "Rollout 8200/9766, Reward: 152.754±22.840, Episode_length: 1000.000±0.000\n", ++ "Rollout 8201/9766, Reward: 274.859±35.066, Episode_length: 430.400±292.356\n", ++ "Rollout 8202/9766, Reward: 251.537±51.655, Episode_length: 607.300±358.364\n", ++ "Rollout 8203/9766, Reward: 280.432±18.579, Episode_length: 426.500±283.038\n", ++ "Rollout 8204/9766, Reward: 286.458±20.110, Episode_length: 168.500±21.892\n", ++ "Rollout 8205/9766, Reward: 268.066±28.536, Episode_length: 368.500±333.301\n", ++ "Rollout 8206/9766, Reward: 277.610±38.951, Episode_length: 396.400±360.235\n", ++ "Rollout 8207/9766, Reward: 272.056±39.523, Episode_length: 340.500±330.039\n", ++ "Rollout 8208/9766, Reward: 290.342±34.500, Episode_length: 303.400±285.124\n", ++ "Rollout 8209/9766, Reward: 282.084±18.156, Episode_length: 161.200±12.998\n", ++ "Rollout 8210/9766, Reward: 279.096±18.506, Episode_length: 157.800±19.676\n", ++ "Rollout 8211/9766, Reward: 298.393±15.755, Episode_length: 172.300±19.058\n", ++ "Rollout 8212/9766, Reward: 288.411±24.110, Episode_length: 161.700±14.980\n", ++ "Rollout 8213/9766, Reward: 289.183±14.923, Episode_length: 161.900±17.885\n", ++ "Rollout 8214/9766, Reward: 285.315±16.186, Episode_length: 164.300±16.211\n", ++ "Rollout 8215/9766, Reward: 299.802±19.571, Episode_length: 169.500±17.546\n", ++ "Rollout 8216/9766, Reward: 293.480±10.405, Episode_length: 161.800±19.431\n", ++ "Rollout 8217/9766, Reward: 278.071±37.053, Episode_length: 241.400±253.280\n", ++ "Rollout 8218/9766, Reward: 269.390±34.099, Episode_length: 244.500±252.303\n", ++ "Rollout 8219/9766, Reward: 282.754±18.213, Episode_length: 165.600±15.396\n", ++ "Rollout 8220/9766, Reward: 287.382±15.902, Episode_length: 161.800±18.302\n", ++ "Rollout 8221/9766, Reward: 284.914±17.664, Episode_length: 153.900±17.677\n", ++ "Rollout 8222/9766, Reward: 287.437±14.701, Episode_length: 161.500±22.393\n", ++ "Rollout 8223/9766, Reward: 259.345±74.324, Episode_length: 160.600±21.285\n", ++ "Rollout 8224/9766, Reward: 283.839±13.126, Episode_length: 161.600±15.857\n", ++ "Rollout 8225/9766, Reward: 279.963±38.847, Episode_length: 251.300±249.837\n", ++ "Rollout 8226/9766, Reward: 294.462±16.334, Episode_length: 170.200±24.207\n", ++ "Rollout 8227/9766, Reward: 295.150±15.119, Episode_length: 162.900±17.254\n", ++ "Rollout 8228/9766, Reward: 288.423±17.501, Episode_length: 158.300±14.269\n", ++ "Rollout 8229/9766, Reward: 282.308±23.082, Episode_length: 167.700±10.706\n", ++ "Rollout 8230/9766, Reward: 286.250±20.284, Episode_length: 167.400±15.857\n", ++ "Rollout 8231/9766, Reward: 288.964±15.246, Episode_length: 169.700±11.270\n", ++ "Rollout 8232/9766, Reward: 295.566±17.701, Episode_length: 161.700±16.517\n", ++ "Rollout 8233/9766, Reward: 285.952±17.923, Episode_length: 154.200±19.078\n", ++ "Rollout 8234/9766, Reward: 287.028±32.174, Episode_length: 262.100±246.531\n", ++ "Rollout 8235/9766, Reward: 260.107±74.826, Episode_length: 154.600±25.590\n", ++ "Rollout 8236/9766, Reward: 294.947±10.815, Episode_length: 159.700±13.602\n", ++ "Rollout 8237/9766, Reward: 286.307±31.418, Episode_length: 248.600±251.210\n", ++ "Rollout 8238/9766, Reward: 278.784±38.470, Episode_length: 246.700±251.811\n", ++ "Rollout 8239/9766, Reward: 287.629±18.647, Episode_length: 159.900±15.719\n", ++ "Rollout 8240/9766, Reward: 281.380±21.230, Episode_length: 149.500±14.445\n", ++ "Rollout 8241/9766, Reward: 289.576±43.999, Episode_length: 250.600±250.134\n", ++ "Rollout 8242/9766, Reward: 284.357±44.958, Episode_length: 339.400±330.768\n", ++ "Rollout 8243/9766, Reward: 280.004±38.689, Episode_length: 249.800±250.901\n", ++ "Rollout 8244/9766, Reward: 293.048±18.260, Episode_length: 221.500±172.760\n", ++ "Rollout 8245/9766, Reward: 271.746±41.015, Episode_length: 381.300±346.160\n", ++ "Rollout 8246/9766, Reward: 256.373±45.159, Episode_length: 589.900±383.332\n", ++ "Rollout 8247/9766, Reward: 253.587±48.948, Episode_length: 702.000±356.888\n", ++ "Rollout 8248/9766, Reward: 187.134±32.082, Episode_length: 994.400±16.800\n", ++ "Rollout 8249/9766, Reward: 179.832±40.929, Episode_length: 920.200±239.400\n", ++ "Rollout 8250/9766, Reward: 206.389±59.587, Episode_length: 971.900±46.775\n" ++ ] ++ }, ++ { ++ "ename": "KeyboardInterrupt", ++ "evalue": "", ++ "output_type": "error", ++ "traceback": [ ++ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", ++ "\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)", ++ "Cell \u001b[0;32mIn[7], line 182\u001b[0m\n\u001b[1;32m 179\u001b[0m writer\u001b[38;5;241m.\u001b[39madd_scalar(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtrain/clip_frac\u001b[39m\u001b[38;5;124m\"\u001b[39m, clip_frac\u001b[38;5;241m.\u001b[39mitem(), global_step)\n\u001b[1;32m 181\u001b[0m \u001b[38;5;66;03m# Eval\u001b[39;00m\n\u001b[0;32m--> 182\u001b[0m reward_mean, reward_std, ep_len_mean, ep_len_std \u001b[38;5;241m=\u001b[39m \u001b[43meval_agent\u001b[49m\u001b[43m(\u001b[49m\u001b[43menv_id\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43magent\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mn_runs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m10\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 183\u001b[0m writer\u001b[38;5;241m.\u001b[39madd_scalar(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrollout/mean_reward\u001b[39m\u001b[38;5;124m\"\u001b[39m, reward_mean, rollout_idx)\n\u001b[1;32m 184\u001b[0m writer\u001b[38;5;241m.\u001b[39madd_scalar(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mrollout/std_reward\u001b[39m\u001b[38;5;124m\"\u001b[39m, reward_std, rollout_idx)\n", ++ "File \u001b[0;32m~/anaconda3/envs/deep_rl_course/lib/python3.10/site-packages/torch/utils/_contextlib.py:116\u001b[0m, in \u001b[0;36mcontext_decorator..decorate_context\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 113\u001b[0m \u001b[38;5;129m@functools\u001b[39m\u001b[38;5;241m.\u001b[39mwraps(func)\n\u001b[1;32m 114\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdecorate_context\u001b[39m(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m 115\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m ctx_factory():\n\u001b[0;32m--> 116\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", ++ "Cell \u001b[0;32mIn[2], line 20\u001b[0m, in \u001b[0;36meval_agent\u001b[0;34m(env_id, agent, n_runs)\u001b[0m\n\u001b[1;32m 18\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28;01mTrue\u001b[39;00m:\n\u001b[1;32m 19\u001b[0m observs_torch \u001b[38;5;241m=\u001b[39m torch\u001b[38;5;241m.\u001b[39mfrom_numpy(observation)\u001b[38;5;241m.\u001b[39munsqueeze(\u001b[38;5;241m0\u001b[39m)\u001b[38;5;241m.\u001b[39mcuda()\n\u001b[0;32m---> 20\u001b[0m action \u001b[38;5;241m=\u001b[39m \u001b[43magent\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_action_logits\u001b[49m\u001b[43m(\u001b[49m\u001b[43mobservs_torch\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241m.\u001b[39margmax(\u001b[38;5;241m1\u001b[39m)[\u001b[38;5;241m0\u001b[39m]\u001b[38;5;241m.\u001b[39mitem()\n\u001b[1;32m 21\u001b[0m observation, reward, terminated, truncated, info \u001b[38;5;241m=\u001b[39m env\u001b[38;5;241m.\u001b[39mstep(action)\n\u001b[1;32m 22\u001b[0m rewards[i] \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m reward\n", ++ "Cell \u001b[0;32mIn[3], line 34\u001b[0m, in \u001b[0;36mAgent.get_action_logits\u001b[0;34m(self, observation)\u001b[0m\n\u001b[1;32m 33\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mget_action_logits\u001b[39m(\u001b[38;5;28mself\u001b[39m, observation):\n\u001b[0;32m---> 34\u001b[0m action_logits \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mactor\u001b[49m\u001b[43m(\u001b[49m\u001b[43mobservation\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 35\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m action_logits\n", ++ "File \u001b[0;32m~/anaconda3/envs/deep_rl_course/lib/python3.10/site-packages/torch/nn/modules/module.py:1736\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1734\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m 1735\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1736\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", ++ "File \u001b[0;32m~/anaconda3/envs/deep_rl_course/lib/python3.10/site-packages/torch/nn/modules/module.py:1747\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1742\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m 1743\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m 1744\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m 1745\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m 1746\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1747\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1749\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 1750\u001b[0m called_always_called_hooks \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mset\u001b[39m()\n", ++ "File \u001b[0;32m~/anaconda3/envs/deep_rl_course/lib/python3.10/site-packages/torch/nn/modules/container.py:250\u001b[0m, in \u001b[0;36mSequential.forward\u001b[0;34m(self, input)\u001b[0m\n\u001b[1;32m 248\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;28minput\u001b[39m):\n\u001b[1;32m 249\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m module \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m:\n\u001b[0;32m--> 250\u001b[0m \u001b[38;5;28minput\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[43mmodule\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 251\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28minput\u001b[39m\n", ++ "File \u001b[0;32m~/anaconda3/envs/deep_rl_course/lib/python3.10/site-packages/torch/nn/modules/module.py:1736\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1734\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m 1735\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1736\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", ++ "File \u001b[0;32m~/anaconda3/envs/deep_rl_course/lib/python3.10/site-packages/torch/nn/modules/module.py:1747\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1742\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m 1743\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m 1744\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m 1745\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m 1746\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1747\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1749\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 1750\u001b[0m called_always_called_hooks \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mset\u001b[39m()\n", ++ "Cell \u001b[0;32mIn[3], line 11\u001b[0m, in \u001b[0;36mTransformerMLP.forward\u001b[0;34m(self, x)\u001b[0m\n\u001b[1;32m 10\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\u001b[38;5;28mself\u001b[39m, x):\n\u001b[0;32m---> 11\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdown_proj(\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mact_fn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgate_proj\u001b[49m\u001b[43m(\u001b[49m\u001b[43mx\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;241m*\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mup_proj(x))\n", ++ "File \u001b[0;32m~/anaconda3/envs/deep_rl_course/lib/python3.10/site-packages/torch/nn/modules/module.py:1736\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1734\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs) \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[1;32m 1735\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 1736\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", ++ "File \u001b[0;32m~/anaconda3/envs/deep_rl_course/lib/python3.10/site-packages/torch/nn/modules/module.py:1747\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1742\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[1;32m 1743\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[1;32m 1744\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[1;32m 1745\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[1;32m 1746\u001b[0m \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[0;32m-> 1747\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1749\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 1750\u001b[0m called_always_called_hooks \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mset\u001b[39m()\n", ++ "File \u001b[0;32m~/anaconda3/envs/deep_rl_course/lib/python3.10/site-packages/torch/nn/modules/activation.py:432\u001b[0m, in \u001b[0;36mSiLU.forward\u001b[0;34m(self, input)\u001b[0m\n\u001b[1;32m 431\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mforward\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;28minput\u001b[39m: Tensor) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tensor:\n\u001b[0;32m--> 432\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mF\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msilu\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43minplace\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minplace\u001b[49m\u001b[43m)\u001b[49m\n", ++ "File \u001b[0;32m~/anaconda3/envs/deep_rl_course/lib/python3.10/site-packages/torch/nn/functional.py:2380\u001b[0m, in \u001b[0;36msilu\u001b[0;34m(input, inplace)\u001b[0m\n\u001b[1;32m 2378\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m inplace:\n\u001b[1;32m 2379\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m torch\u001b[38;5;241m.\u001b[39m_C\u001b[38;5;241m.\u001b[39m_nn\u001b[38;5;241m.\u001b[39msilu_(\u001b[38;5;28minput\u001b[39m)\n\u001b[0;32m-> 2380\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mtorch\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_C\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_nn\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msilu\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m)\u001b[49m\n", ++ "\u001b[0;31mKeyboardInterrupt\u001b[0m: " + ] + } + ], + "source": [ +- "env_id = \"LunarLander-v3\"\n", ++ "env_id = \"LunarLander-v2\"\n", + "batch_size = 512\n", + "n_steps = 1024\n", + "n_epochs = 4\n", + "n_envs = 10\n", + "total_time_steps = 100000000\n", + "seed = 42\n", +- "lr = 1e-4\n", ++ "lr = 3e-4\n", + "gamma = 0.999\n", + "gae_lambda = 0.95\n", + "clip_epsilon = 0.2\n", +@@ -175,11 +8420,9 @@ + "n_rollouts = math.ceil(total_time_steps / (n_steps * n_envs))\n", + "\n", + "set_seed(seed)\n", +- "env = gym.make_vec(\n", +- " id=env_id,\n", +- " vectorization_mode=\"async\",\n", +- " num_envs=n_envs\n", +- ")\n", ++ "env = gym.vector.AsyncVectorEnv([\n", ++ " lambda: gym.make(\"LunarLander-v2\") for _ in range(n_envs)\n", ++ "])\n", + "agent = Agent(\n", + " observation_dim=env.single_observation_space.shape[0],\n", + " action_dim=env.single_action_space.n\n", +@@ -345,39 +8588,51 @@ + " # best-model\n", + " if reward_mean > best_reward:\n", + " best_reward = reward_mean\n", +- " torch.save(agent, \"./best-model.pth\")" ++ " torch.save(agent, f\"./{env_id}-best-model.pth\")" + ] + }, + { + "cell_type": "code", +- "execution_count": 19, ++ "execution_count": 5, + "metadata": {}, + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ +- "/tmp/ipykernel_5623/3857132175.py:2: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n", ++ "/tmp/ipykernel_957/3380663230.py:2: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n", + " agent = torch.load(f)\n" + ] + } + ], + "source": [ +- "with open(\"./best-model.pth\", \"rb\") as f:\n", ++ "with open(\"./LunarLander-v2-best-model-reward283.pth\", \"rb\") as f:\n", + " agent = torch.load(f)" + ] + }, + { + "cell_type": "code", +- "execution_count": 12, ++ "execution_count": 7, + "metadata": {}, +- "outputs": [], ++ "outputs": [ ++ { ++ "ename": "", ++ "evalue": "", ++ "output_type": "error", ++ "traceback": [ ++ "\u001b[1;31mThe Kernel crashed while executing code in the current cell or a previous cell. \n", ++ "\u001b[1;31mPlease review the code in the cell(s) to identify a possible cause of the failure. \n", ++ "\u001b[1;31mClick here for more info. \n", ++ "\u001b[1;31mView Jupyter log for further details." ++ ] ++ } ++ ], + "source": [ + "# agent = Agent(\n", + "# observation_dim=vec_env.observation_space.shape[1],\n", + "# action_dim=vec_env.action_space[0].n\n", + "# ).cuda()\n", +- "env = gym.make(\"LunarLander-v3\", render_mode=\"human\")\n", ++ "env = gym.make(\"LunarLander-v2\", render_mode=\"human\")\n", + "observation, info = env.reset(seed=42)\n", + "with torch.inference_mode():\n", + " for i in range(200):\n", +@@ -401,30 +8656,411 @@ + }, + { + "cell_type": "code", +- "execution_count": 6, ++ "execution_count": 9, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ +- "-1584.911±896.309\n" ++ "283.783±25.679\n" + ] + } + ], + "source": [ +- "reward_mean, reward_std = eval_agent(agent, n_runs=100)\n", ++ "reward_mean, reward_std, ep_len_mean, ep_len_std = eval_agent(\"LunarLander-v2\", agent, n_runs=100)\n", + "print(f\"{reward_mean:.3f}±{reward_std:.3f}\")" + ] + }, ++ { ++ "cell_type": "markdown", ++ "metadata": {}, ++ "source": [ ++ "### push to hub" ++ ] ++ }, + { + "cell_type": "code", +- "execution_count": null, ++ "execution_count": 6, ++ "metadata": {}, ++ "outputs": [], ++ "source": [ ++ "\n", ++ "import tempfile\n", ++ "import datetime\n", ++ "import json\n", ++ "import shutil\n", ++ "import imageio\n", ++ "from pathlib import Path\n", ++ "\n", ++ "from huggingface_hub import HfApi, upload_folder\n", ++ "from huggingface_hub.repocard import metadata_eval_result, metadata_save\n", ++ "from wasabi import Printer" ++ ] ++ }, ++ { ++ "cell_type": "code", ++ "execution_count": 7, ++ "metadata": {}, ++ "outputs": [], ++ "source": [ ++ "device = \"cuda\"\n", ++ "def _evaluate_agent(env, n_eval_episodes, policy):\n", ++ " \"\"\"\n", ++ " Evaluate the agent for ``n_eval_episodes`` episodes and returns average reward and std of reward.\n", ++ " :param env: The evaluation environment\n", ++ " :param n_eval_episodes: Number of episode to evaluate the agent\n", ++ " :param policy: The agent\n", ++ " \"\"\"\n", ++ " episode_rewards = []\n", ++ " for episode in range(n_eval_episodes):\n", ++ " state, _ = env.reset()\n", ++ " step = 0\n", ++ " done = False\n", ++ " total_rewards_ep = 0\n", ++ "\n", ++ " while done is False:\n", ++ " state = torch.Tensor(state).to(device)\n", ++ " action_logits = policy.get_action_logits(state)\n", ++ " action = torch.argmax(action_logits)\n", ++ " new_state, reward, terminations, truncations, info = env.step(action.cpu().numpy())\n", ++ " total_rewards_ep += reward\n", ++ " if terminations or truncations:\n", ++ " break\n", ++ " state = new_state\n", ++ " episode_rewards.append(total_rewards_ep)\n", ++ " mean_reward = np.mean(episode_rewards)\n", ++ " std_reward = np.std(episode_rewards)\n", ++ "\n", ++ " return mean_reward, std_reward\n", ++ "\n", ++ "\n", ++ "def record_video(env, policy, out_directory, fps=30):\n", ++ " images = []\n", ++ " done = False\n", ++ " state, _ = env.reset()\n", ++ " img = env.render()\n", ++ " images.append(img)\n", ++ " while not done:\n", ++ " state = torch.Tensor(state).to(device)\n", ++ " action_logits = policy.get_action_logits(state)\n", ++ " action = torch.argmax(action_logits)\n", ++ " state, reward, terminations, truncations, info = env.step(action.cpu().numpy())\n", ++ " done = terminations or truncations\n", ++ " img = env.render()\n", ++ " images.append(img)\n", ++ " imageio.mimsave(\n", ++ " out_directory,\n", ++ " [np.array(img) for i, img in enumerate(images)],\n", ++ " fps=fps\n", ++ " )\n", ++ "\n", ++ "\n", ++ "def _generate_model_card(model_name, env_id, mean_reward, std_reward, hyperparameters):\n", ++ " \"\"\"\n", ++ " Generate the model card for the Hub\n", ++ " :param model_name: name of the model\n", ++ " :env_id: name of the environment\n", ++ " :mean_reward: mean reward of the agent\n", ++ " :std_reward: standard deviation of the mean reward of the agent\n", ++ " :hyperparameters: training arguments\n", ++ " \"\"\"\n", ++ " # Step 1: Select the tags\n", ++ " metadata = generate_metadata(model_name, env_id, mean_reward, std_reward)\n", ++ "\n", ++ " # Transform the hyperparams namespace to string\n", ++ " converted_dict = vars(hyperparameters)\n", ++ " converted_str = str(converted_dict)\n", ++ " converted_str = converted_str.split(\", \")\n", ++ " converted_str = \"\\n\".join(converted_str)\n", ++ "\n", ++ " # Step 2: Generate the model card\n", ++ " model_card = f\"\"\"\n", ++ " # PPO Agent Playing {env_id}\n", ++ "\n", ++ " This is a trained model of a PPO agent playing {env_id}.\n", ++ "\n", ++ " # Hyperparameters\n", ++ " \"\"\"\n", ++ " return model_card, metadata\n", ++ "\n", ++ "\n", ++ "def generate_metadata(model_name, env_id, mean_reward, std_reward):\n", ++ " \"\"\"\n", ++ " Define the tags for the model card\n", ++ " :param model_name: name of the model\n", ++ " :param env_id: name of the environment\n", ++ " :mean_reward: mean reward of the agent\n", ++ " :std_reward: standard deviation of the mean reward of the agent\n", ++ " \"\"\"\n", ++ " metadata = {}\n", ++ " metadata[\"tags\"] = [\n", ++ " env_id,\n", ++ " \"ppo\",\n", ++ " \"deep-reinforcement-learning\",\n", ++ " \"reinforcement-learning\",\n", ++ " \"custom-implementation\",\n", ++ " \"deep-rl-course\",\n", ++ " ]\n", ++ "\n", ++ " # Add metrics\n", ++ " eval = metadata_eval_result(\n", ++ " model_pretty_name=model_name,\n", ++ " task_pretty_name=\"reinforcement-learning\",\n", ++ " task_id=\"reinforcement-learning\",\n", ++ " metrics_pretty_name=\"mean_reward\",\n", ++ " metrics_id=\"mean_reward\",\n", ++ " metrics_value=f\"{mean_reward:.2f} +/- {std_reward:.2f}\",\n", ++ " dataset_pretty_name=env_id,\n", ++ " dataset_id=env_id,\n", ++ " )\n", ++ "\n", ++ " # Merges both dictionaries\n", ++ " metadata = {**metadata, **eval}\n", ++ "\n", ++ " return metadata\n", ++ "\n", ++ "\n", ++ "def _save_model_card(local_path, generated_model_card, metadata):\n", ++ " \"\"\"Saves a model card for the repository.\n", ++ " :param local_path: repository directory\n", ++ " :param generated_model_card: model card generated by _generate_model_card()\n", ++ " :param metadata: metadata\n", ++ " \"\"\"\n", ++ " readme_path = local_path / \"README.md\"\n", ++ " readme = \"\"\n", ++ " if readme_path.exists():\n", ++ " with readme_path.open(\"r\", encoding=\"utf8\") as f:\n", ++ " readme = f.read()\n", ++ " else:\n", ++ " readme = generated_model_card\n", ++ "\n", ++ " with readme_path.open(\"w\", encoding=\"utf-8\") as f:\n", ++ " f.write(readme)\n", ++ "\n", ++ " # Save our metrics to Readme metadata\n", ++ " metadata_save(readme_path, metadata)\n", ++ "\n", ++ "\n", ++ "def _add_logdir(local_path: Path, logdir: Path):\n", ++ " \"\"\"Adds a logdir to the repository.\n", ++ " :param local_path: repository directory\n", ++ " :param logdir: logdir directory\n", ++ " \"\"\"\n", ++ " if logdir.exists() and logdir.is_dir():\n", ++ " # Add the logdir to the repository under new dir called logs\n", ++ " repo_logdir = local_path / \"logs\"\n", ++ "\n", ++ " # Delete current logs if they exist\n", ++ " if repo_logdir.exists():\n", ++ " shutil.rmtree(repo_logdir)\n", ++ "\n", ++ " # Copy logdir into repo logdir\n", ++ " shutil.copytree(logdir, repo_logdir)" ++ ] ++ }, ++ { ++ "cell_type": "code", ++ "execution_count": 8, ++ "metadata": {}, ++ "outputs": [], ++ "source": [ ++ "repo_url = HfApi().create_repo(\n", ++ " repo_id=\"Snorlax/LunarLander-v2-PPO-reproduce\",\n", ++ " token=None,\n", ++ " private=False,\n", ++ " exist_ok=True,\n", ++ ")" ++ ] ++ }, ++ { ++ "cell_type": "code", ++ "execution_count": 9, ++ "metadata": {}, ++ "outputs": [], ++ "source": [ ++ "eval_env = gym.make(\"LunarLander-v2\", render_mode=\"rgb_array\")" ++ ] ++ }, ++ { ++ "cell_type": "code", ++ "execution_count": 34, ++ "metadata": {}, ++ "outputs": [ ++ { ++ "name": "stdout", ++ "output_type": "stream", ++ "text": [ ++ "290.7548217937816±15.207132138146612\n" ++ ] ++ } ++ ], ++ "source": [ ++ "mean_reward, std_reward = _evaluate_agent(eval_env, 10, agent)\n", ++ "print(f\"{mean_reward}±{std_reward}\")" ++ ] ++ }, ++ { ++ "cell_type": "code", ++ "execution_count": 35, ++ "metadata": {}, ++ "outputs": [], ++ "source": [ ++ "eval_datetime = datetime.datetime.now()\n", ++ "eval_form_datetime = eval_datetime.isoformat()\n", ++ "\n", ++ "evaluate_data = {\n", ++ " \"env_id\": \"LunarLander-v2\",\n", ++ " \"mean_reward\": mean_reward,\n", ++ " \"std_reward\": std_reward,\n", ++ " \"n_evaluation_episodes\": 10,\n", ++ " \"eval_datetime\": eval_form_datetime,\n", ++ "}" ++ ] ++ }, ++ { ++ "cell_type": "code", ++ "execution_count": 38, ++ "metadata": {}, ++ "outputs": [ ++ { ++ "name": "stderr", ++ "output_type": "stream", ++ "text": [ ++ "IMAGEIO FFMPEG_WRITER WARNING: input image is not divisible by macro_block_size=16, resizing from (600, 400) to (608, 400) to ensure video compatibility with most codecs and players. To prevent resizing, make your input image divisible by the macro_block_size or set the macro_block_size to 1 (risking incompatibility).\n", ++ "[swscaler @ 0x36280d40] Warning: data is not aligned! This can lead to a speed loss\n" ++ ] ++ } ++ ], ++ "source": [ ++ "import os\n", ++ "\n", ++ "tmpdirname = './hub_tmp'\n", ++ "os.makedirs(tmpdirname, exist_ok=True)\n", ++ "tmpdirname = Path(tmpdirname)\n", ++ "with open(tmpdirname / \"results.json\", \"w\") as outfile:\n", ++ " json.dump(evaluate_data, outfile)\n", ++ "video_path = tmpdirname / \"replay.mp4\"\n", ++ "record_video(eval_env, agent, video_path, fps=30)" ++ ] ++ }, ++ { ++ "cell_type": "code", ++ "execution_count": 39, ++ "metadata": {}, ++ "outputs": [], ++ "source": [ ++ "parser = argparse.ArgumentParser()\n", ++ "args = parser.parse_args([])" ++ ] ++ }, ++ { ++ "cell_type": "code", ++ "execution_count": 40, ++ "metadata": {}, ++ "outputs": [], ++ "source": [ ++ "hyperparameters = {\n", ++ " \"env_id\": \"LunarLander-v2\",\n", ++ " \"batch_size\": 512,\n", ++ " \"n_steps\": 1024,\n", ++ " \"n_epochs\": 4,\n", ++ " \"n_envs\": 10,\n", ++ " \"total_time_steps\": 100000000,\n", ++ " \"seed\": 42,\n", ++ " \"lr\": 3e-4,\n", ++ " \"gamma\": 0.999,\n", ++ " \"gae_lambda\": 0.95,\n", ++ " \"clip_epsilon\": 0.2,\n", ++ " \"c1\": 0.5,\n", ++ " \"c2\": 0.01,\n", ++ " \"max_grad_norm\": 0.5,\n", ++ " \"normalize_advantage\": True,\n", ++ " \"cosine_annealing\": True,\n", ++ " \"check_first_ratio\": True,\n", ++ " \"mask_done\": True\n", ++ "}\n", ++ "for k, v in hyperparameters.items():\n", ++ " args.__setattr__(k, v)" ++ ] ++ }, ++ { ++ "cell_type": "code", ++ "execution_count": 22, ++ "metadata": {}, ++ "outputs": [ ++ { ++ "data": { ++ "text/plain": [ ++ "0.2" ++ ] ++ }, ++ "execution_count": 22, ++ "metadata": {}, ++ "output_type": "execute_result" ++ } ++ ], ++ "source": [ ++ "args.clip_epsilon" ++ ] ++ }, ++ { ++ "cell_type": "code", ++ "execution_count": 33, + "metadata": {}, + "outputs": [], + "source": [ +- "from stable_baselines3 import PPO" ++ "torch.save(agent.state_dict(), tmpdirname / \"model.pth\")" + ] ++ }, ++ { ++ "cell_type": "code", ++ "execution_count": 41, ++ "metadata": {}, ++ "outputs": [], ++ "source": [ ++ "generated_model_card, metadata = _generate_model_card(\n", ++ " \"PPO\", \"LunarLander-v2\", mean_reward, std_reward, args\n", ++ ")\n", ++ "_save_model_card(tmpdirname, generated_model_card, metadata)" ++ ] ++ }, ++ { ++ "cell_type": "code", ++ "execution_count": 42, ++ "metadata": {}, ++ "outputs": [ ++ { ++ "data": { ++ "application/vnd.jupyter.widget-view+json": { ++ "model_id": "913f2bf273e34458bfe5598767070e36", ++ "version_major": 2, ++ "version_minor": 0 ++ }, ++ "text/plain": [ ++ "model.pth: 0%| | 0.00/38.1M [00:00