{ "name": "root", "gauges": { "Pyramids.Policy.Entropy.mean": { "value": 0.418950617313385, "min": 0.418950617313385, "max": 1.390873670578003, "count": 33 }, "Pyramids.Policy.Entropy.sum": { "value": 12528.298828125, "min": 12528.298828125, "max": 42193.54296875, "count": 33 }, "Pyramids.Step.mean": { "value": 989932.0, "min": 29952.0, "max": 989932.0, "count": 33 }, "Pyramids.Step.sum": { "value": 989932.0, "min": 29952.0, "max": 989932.0, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.mean": { "value": 0.3882584869861603, "min": -0.10076591372489929, "max": 0.40734216570854187, "count": 33 }, "Pyramids.Policy.ExtrinsicValueEstimate.sum": { "value": 101.72372436523438, "min": -24.28458595275879, "max": 109.57504272460938, "count": 33 }, "Pyramids.Policy.RndValueEstimate.mean": { "value": -0.30826428532600403, "min": -0.30826428532600403, "max": 0.653338611125946, "count": 33 }, "Pyramids.Policy.RndValueEstimate.sum": { "value": -80.76524353027344, "min": -80.76524353027344, "max": 154.84124755859375, "count": 33 }, "Pyramids.Losses.PolicyLoss.mean": { "value": 0.07009639321005949, "min": 0.0656664643219166, "max": 0.07307927815450561, "count": 33 }, "Pyramids.Losses.PolicyLoss.sum": { "value": 0.9813495049408328, "min": 0.4985873787647151, "max": 1.0961891723175843, "count": 33 }, "Pyramids.Losses.ValueLoss.mean": { "value": 0.022467649782248324, "min": 0.0006347373232505554, "max": 0.022467649782248324, "count": 33 }, "Pyramids.Losses.ValueLoss.sum": { "value": 0.31454709695147653, "min": 0.008491236318475407, "max": 0.31454709695147653, "count": 33 }, "Pyramids.Policy.LearningRate.mean": { "value": 7.461590369978572e-06, "min": 7.461590369978572e-06, "max": 0.00029515063018788575, "count": 33 }, "Pyramids.Policy.LearningRate.sum": { "value": 0.00010446226517970001, "min": 0.00010446226517970001, "max": 0.0037578346473885003, "count": 33 }, "Pyramids.Policy.Epsilon.mean": { "value": 0.10248716428571428, "min": 0.10248716428571428, "max": 0.19838354285714285, "count": 33 }, "Pyramids.Policy.Epsilon.sum": { "value": 1.4348203, "min": 1.3886848, "max": 2.652611500000001, "count": 33 }, "Pyramids.Policy.Beta.mean": { "value": 0.0002584677121428572, "min": 0.0002584677121428572, "max": 0.00983851593142857, "count": 33 }, "Pyramids.Policy.Beta.sum": { "value": 0.0036185479700000006, "min": 0.0036185479700000006, "max": 0.12527588885000002, "count": 33 }, "Pyramids.Losses.RNDLoss.mean": { "value": 0.014607344754040241, "min": 0.014607344754040241, "max": 0.588964581489563, "count": 33 }, "Pyramids.Losses.RNDLoss.sum": { "value": 0.20450282096862793, "min": 0.20450282096862793, "max": 4.1227521896362305, "count": 33 }, "Pyramids.Environment.EpisodeLength.mean": { "value": 446.35, "min": 446.35, "max": 999.0, "count": 33 }, "Pyramids.Environment.EpisodeLength.sum": { "value": 26781.0, "min": 15984.0, "max": 33718.0, "count": 33 }, "Pyramids.Environment.CumulativeReward.mean": { "value": 1.42248193431096, "min": -1.0000000521540642, "max": 1.42248193431096, "count": 33 }, "Pyramids.Environment.CumulativeReward.sum": { "value": 86.77139799296856, "min": -30.271401688456535, "max": 92.93099818378687, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.mean": { "value": 1.42248193431096, "min": -1.0000000521540642, "max": 1.42248193431096, "count": 33 }, "Pyramids.Policy.ExtrinsicReward.sum": { "value": 86.77139799296856, "min": -30.271401688456535, "max": 92.93099818378687, "count": 33 }, "Pyramids.Policy.RndReward.mean": { "value": 0.06754464865662158, "min": 0.06754464865662158, "max": 12.064284019172192, "count": 33 }, "Pyramids.Policy.RndReward.sum": { "value": 4.120223568053916, "min": 4.120223568053916, "max": 193.02854430675507, "count": 33 }, "Pyramids.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 }, "Pyramids.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 33 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679168646", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1679170651" }, "total": 2004.6091470819997, "count": 1, "self": 0.8922794459995202, "children": { "run_training.setup": { "total": 0.09986737500003073, "count": 1, "self": 0.09986737500003073 }, "TrainerController.start_learning": { "total": 2003.6170002610002, "count": 1, "self": 1.3090187099496688, "children": { "TrainerController._reset_env": { "total": 5.8806003820000115, "count": 1, "self": 5.8806003820000115 }, "TrainerController.advance": { "total": 1996.28658593105, "count": 63502, "self": 1.3351066010513932, "children": { "env_step": { "total": 1396.0005973860816, "count": 63502, "self": 1293.691476208116, "children": { "SubprocessEnvManager._take_step": { "total": 101.54615369400926, "count": 63502, "self": 4.498328026921172, "children": { "TorchPolicy.evaluate": { "total": 97.04782566708809, "count": 62569, "self": 97.04782566708809 } } }, "workers": { "total": 0.762967483956345, "count": 63502, "self": 0.0, "children": { "worker_root": { "total": 1999.3892030991897, "count": 63502, "is_parallel": true, "self": 814.1076798631648, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0017966339996746683, "count": 1, "is_parallel": true, "self": 0.0006285719991865335, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011680620004881348, "count": 8, "is_parallel": true, "self": 0.0011680620004881348 } } }, "UnityEnvironment.step": { "total": 0.047912801999700605, "count": 1, "is_parallel": true, "self": 0.0005092860001241206, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004527459996097605, "count": 1, "is_parallel": true, "self": 0.0004527459996097605 }, "communicator.exchange": { "total": 0.04523759499988955, "count": 1, "is_parallel": true, "self": 0.04523759499988955 }, "steps_from_proto": { "total": 0.0017131750000771717, "count": 1, "is_parallel": true, "self": 0.0003945930002373643, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013185819998398074, "count": 8, "is_parallel": true, "self": 0.0013185819998398074 } } } } } } }, "UnityEnvironment.step": { "total": 1185.281523236025, "count": 63501, "is_parallel": true, "self": 29.97486963303527, "children": { "UnityEnvironment._generate_step_input": { "total": 21.828409154079054, "count": 63501, "is_parallel": true, "self": 21.828409154079054 }, "communicator.exchange": { "total": 1045.4213900919544, "count": 63501, "is_parallel": true, "self": 1045.4213900919544 }, "steps_from_proto": { "total": 88.05685435695614, "count": 63501, "is_parallel": true, "self": 18.56369703674909, "children": { "_process_rank_one_or_two_observation": { "total": 69.49315732020705, "count": 508008, "is_parallel": true, "self": 69.49315732020705 } } } } } } } } } } }, "trainer_advance": { "total": 598.950881943917, "count": 63502, "self": 2.3878587068356865, "children": { "process_trajectory": { "total": 111.85542982407742, "count": 63502, "self": 111.55336911107725, "children": { "RLTrainer._checkpoint": { "total": 0.30206071300017356, "count": 2, "self": 0.30206071300017356 } } }, "_update_policy": { "total": 484.7075934130039, "count": 455, "self": 308.9757453699485, "children": { "TorchPPOOptimizer.update": { "total": 175.73184804305538, "count": 22782, "self": 175.73184804305538 } } } } } } }, "trainer_threads": { "total": 1.4170000213198364e-06, "count": 1, "self": 1.4170000213198364e-06 }, "TrainerController._save_models": { "total": 0.14079382100044313, "count": 1, "self": 0.0019650430003821384, "children": { "RLTrainer._checkpoint": { "total": 0.138828778000061, "count": 1, "self": 0.138828778000061 } } } } } } }