ppo-Huggy / run_logs /timers.json
codeSpaghetti's picture
Huggy
c6c5642
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.403088092803955,
"min": 1.403088092803955,
"max": 1.4268999099731445,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71536.4453125,
"min": 68011.265625,
"max": 77397.96875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 107.9673202614379,
"min": 93.96780303030303,
"max": 375.70676691729324,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49557.0,
"min": 49360.0,
"max": 50029.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999951.0,
"min": 49823.0,
"max": 1999951.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999951.0,
"min": 49823.0,
"max": 1999951.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3198928833007812,
"min": 0.11001735180616379,
"max": 2.374255418777466,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1062.510986328125,
"min": 14.522290229797363,
"max": 1204.840087890625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.534326360085125,
"min": 1.805727070479682,
"max": 3.8467248461219703,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1618.7214729189873,
"min": 238.35597330331802,
"max": 1946.8194417953491,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.534326360085125,
"min": 1.805727070479682,
"max": 3.8467248461219703,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1618.7214729189873,
"min": 238.35597330331802,
"max": 1946.8194417953491,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01701119269321983,
"min": 0.013074926413779999,
"max": 0.020912936653864258,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03402238538643966,
"min": 0.02643806679116096,
"max": 0.05667388872000932,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04903422687202692,
"min": 0.02060081297531724,
"max": 0.054198278072807526,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09806845374405385,
"min": 0.04120162595063448,
"max": 0.16259483421842258,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.5710484763500135e-06,
"min": 4.5710484763500135e-06,
"max": 0.00029537062654312493,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.142096952700027e-06,
"min": 9.142096952700027e-06,
"max": 0.00084383416872195,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10152365000000002,
"min": 0.10152365000000002,
"max": 0.19845687500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20304730000000004,
"min": 0.20304730000000004,
"max": 0.5812780500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.603013500000018e-05,
"min": 8.603013500000018e-05,
"max": 0.0049229980625,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017206027000000036,
"min": 0.00017206027000000036,
"max": 0.014065774694999998,
"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": "1673024755",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1673027153"
},
"total": 2398.8237227160002,
"count": 1,
"self": 0.38557156000024406,
"children": {
"run_training.setup": {
"total": 0.11971252099999674,
"count": 1,
"self": 0.11971252099999674
},
"TrainerController.start_learning": {
"total": 2398.318438635,
"count": 1,
"self": 4.256369254959736,
"children": {
"TrainerController._reset_env": {
"total": 8.294159406000006,
"count": 1,
"self": 8.294159406000006
},
"TrainerController.advance": {
"total": 2385.6469101240405,
"count": 231543,
"self": 4.715596532049403,
"children": {
"env_step": {
"total": 1897.7294262349856,
"count": 231543,
"self": 1598.805625533893,
"children": {
"SubprocessEnvManager._take_step": {
"total": 296.02004006504256,
"count": 231543,
"self": 15.6594290150976,
"children": {
"TorchPolicy.evaluate": {
"total": 280.36061104994496,
"count": 223042,
"self": 69.53401373596023,
"children": {
"TorchPolicy.sample_actions": {
"total": 210.82659731398473,
"count": 223042,
"self": 210.82659731398473
}
}
}
}
},
"workers": {
"total": 2.903760636050208,
"count": 231543,
"self": 0.0,
"children": {
"worker_root": {
"total": 2389.3652659820264,
"count": 231543,
"is_parallel": true,
"self": 1079.772192670001,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002262702999985322,
"count": 1,
"is_parallel": true,
"self": 0.0003694689999917955,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018932339999935266,
"count": 2,
"is_parallel": true,
"self": 0.0018932339999935266
}
}
},
"UnityEnvironment.step": {
"total": 0.03041543299997329,
"count": 1,
"is_parallel": true,
"self": 0.00031724099994789867,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021941800002878153,
"count": 1,
"is_parallel": true,
"self": 0.00021941800002878153
},
"communicator.exchange": {
"total": 0.0290804059999914,
"count": 1,
"is_parallel": true,
"self": 0.0290804059999914
},
"steps_from_proto": {
"total": 0.0007983680000052118,
"count": 1,
"is_parallel": true,
"self": 0.0002738839999665288,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000524484000038683,
"count": 2,
"is_parallel": true,
"self": 0.000524484000038683
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1309.5930733120254,
"count": 231542,
"is_parallel": true,
"self": 36.75955811603717,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.38095396198264,
"count": 231542,
"is_parallel": true,
"self": 84.38095396198264
},
"communicator.exchange": {
"total": 1087.3136651919876,
"count": 231542,
"is_parallel": true,
"self": 1087.3136651919876
},
"steps_from_proto": {
"total": 101.13889604201785,
"count": 231542,
"is_parallel": true,
"self": 44.10913340300988,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.02976263900797,
"count": 463084,
"is_parallel": true,
"self": 57.02976263900797
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 483.20188735700566,
"count": 231543,
"self": 6.520698804024619,
"children": {
"process_trajectory": {
"total": 156.57376244798064,
"count": 231543,
"self": 155.34430391198055,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2294585360000951,
"count": 10,
"self": 1.2294585360000951
}
}
},
"_update_policy": {
"total": 320.1074261050004,
"count": 96,
"self": 266.2345108029962,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.872915302004174,
"count": 2880,
"self": 53.872915302004174
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.590000106778461e-07,
"count": 1,
"self": 8.590000106778461e-07
},
"TrainerController._save_models": {
"total": 0.12099899099985123,
"count": 1,
"self": 0.0020899189998999645,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11890907199995127,
"count": 1,
"self": 0.11890907199995127
}
}
}
}
}
}
}