ppo-Huggy / run_logs /timers.json
xianbin's picture
Huggy
7291c0c
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4038119316101074,
"min": 1.4038119316101074,
"max": 1.4306318759918213,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70646.8359375,
"min": 68683.2109375,
"max": 78758.2265625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 87.94326241134752,
"min": 87.39399293286219,
"max": 430.5982905982906,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49600.0,
"min": 48875.0,
"max": 50380.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999458.0,
"min": 49869.0,
"max": 1999458.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999458.0,
"min": 49869.0,
"max": 1999458.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3880460262298584,
"min": 0.10138252377510071,
"max": 2.4145476818084717,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1346.85791015625,
"min": 11.76037311553955,
"max": 1366.634033203125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7944910945833152,
"min": 1.6607365094382187,
"max": 3.951237033387932,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2140.09297734499,
"min": 192.64543509483337,
"max": 2170.0616979002953,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7944910945833152,
"min": 1.6607365094382187,
"max": 3.951237033387932,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2140.09297734499,
"min": 192.64543509483337,
"max": 2170.0616979002953,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.012359136577773218,
"min": 0.008589643383553872,
"max": 0.01435807121937008,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.012359136577773218,
"min": 0.008589643383553872,
"max": 0.02527336452815992,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05642702939609687,
"min": 0.021797888601819675,
"max": 0.05942037142813206,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.05642702939609687,
"min": 0.021797888601819675,
"max": 0.1114906186858813,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 6.987348602550001e-06,
"min": 6.987348602550001e-06,
"max": 0.00048965225206955,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 6.987348602550001e-06,
"min": 6.987348602550001e-06,
"max": 0.0008866405226718999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10139744999999997,
"min": 0.10139744999999997,
"max": 0.19793045000000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.10139744999999997,
"min": 0.10139744999999997,
"max": 0.37732810000000017,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.973275499999998e-05,
"min": 7.973275499999998e-05,
"max": 0.004896729455,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 7.973275499999998e-05,
"min": 7.973275499999998e-05,
"max": 0.00886867219,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1690354663",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1690357117"
},
"total": 2453.479738306,
"count": 1,
"self": 0.4368960369997694,
"children": {
"run_training.setup": {
"total": 0.03440986700002213,
"count": 1,
"self": 0.03440986700002213
},
"TrainerController.start_learning": {
"total": 2453.008432402,
"count": 1,
"self": 4.292862148990935,
"children": {
"TrainerController._reset_env": {
"total": 5.499935883000035,
"count": 1,
"self": 5.499935883000035
},
"TrainerController.advance": {
"total": 2443.089041614009,
"count": 231486,
"self": 4.6378030930463865,
"children": {
"env_step": {
"total": 1891.8888334360151,
"count": 231486,
"self": 1596.3705676899422,
"children": {
"SubprocessEnvManager._take_step": {
"total": 292.60382602706477,
"count": 231486,
"self": 17.316788613080803,
"children": {
"TorchPolicy.evaluate": {
"total": 275.28703741398397,
"count": 222905,
"self": 275.28703741398397
}
}
},
"workers": {
"total": 2.914439719008101,
"count": 231486,
"self": 0.0,
"children": {
"worker_root": {
"total": 2445.1661769100065,
"count": 231486,
"is_parallel": true,
"self": 1138.9354903130475,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009681780001074003,
"count": 1,
"is_parallel": true,
"self": 0.0002901160002011238,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006780619999062765,
"count": 2,
"is_parallel": true,
"self": 0.0006780619999062765
}
}
},
"UnityEnvironment.step": {
"total": 0.032083467999996174,
"count": 1,
"is_parallel": true,
"self": 0.00036910199992234993,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002390289999993911,
"count": 1,
"is_parallel": true,
"self": 0.0002390289999993911
},
"communicator.exchange": {
"total": 0.030747123000082865,
"count": 1,
"is_parallel": true,
"self": 0.030747123000082865
},
"steps_from_proto": {
"total": 0.0007282139999915671,
"count": 1,
"is_parallel": true,
"self": 0.0002085360000592118,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005196779999323553,
"count": 2,
"is_parallel": true,
"self": 0.0005196779999323553
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1306.230686596959,
"count": 231485,
"is_parallel": true,
"self": 41.18964661703012,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.85444609496346,
"count": 231485,
"is_parallel": true,
"self": 82.85444609496346
},
"communicator.exchange": {
"total": 1083.7707645878759,
"count": 231485,
"is_parallel": true,
"self": 1083.7707645878759
},
"steps_from_proto": {
"total": 98.41582929708954,
"count": 231485,
"is_parallel": true,
"self": 35.87606140011212,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.53976789697742,
"count": 462970,
"is_parallel": true,
"self": 62.53976789697742
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 546.5624050849474,
"count": 231486,
"self": 6.486662521969947,
"children": {
"process_trajectory": {
"total": 137.41836290197818,
"count": 231486,
"self": 136.1473524429789,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2710104589992852,
"count": 10,
"self": 1.2710104589992852
}
}
},
"_update_policy": {
"total": 402.65737966099925,
"count": 48,
"self": 347.6464533699959,
"children": {
"TorchPPOOptimizer.update": {
"total": 55.01092629100333,
"count": 1440,
"self": 55.01092629100333
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.579995665058959e-07,
"count": 1,
"self": 8.579995665058959e-07
},
"TrainerController._save_models": {
"total": 0.1265918980002425,
"count": 1,
"self": 0.0024928060001911945,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12409909200005131,
"count": 1,
"self": 0.12409909200005131
}
}
}
}
}
}
}