ppo-Huggy / run_logs /timers.json
GeerBox's picture
Huggy
67fda4b verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.401485562324524,
"min": 1.4014779329299927,
"max": 1.428643822669983,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69754.7421875,
"min": 67780.828125,
"max": 76563.9609375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 140.43304843304844,
"min": 105.81156316916488,
"max": 411.4918032786885,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49292.0,
"min": 49071.0,
"max": 50202.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999383.0,
"min": 49619.0,
"max": 1999383.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999383.0,
"min": 49619.0,
"max": 1999383.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.238553524017334,
"min": 0.10578255355358124,
"max": 2.3626880645751953,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 783.4937744140625,
"min": 12.799689292907715,
"max": 1078.7156982421875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.4244308606215887,
"min": 1.883615322103185,
"max": 3.8047536114412073,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1198.550801217556,
"min": 227.9174539744854,
"max": 1719.7486323714256,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.4244308606215887,
"min": 1.883615322103185,
"max": 3.8047536114412073,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1198.550801217556,
"min": 227.9174539744854,
"max": 1719.7486323714256,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015699411459596982,
"min": 0.0125291595342181,
"max": 0.019568320529166766,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.031398822919193964,
"min": 0.0250583190684362,
"max": 0.051821574747251964,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.03584092203527689,
"min": 0.02159523821125428,
"max": 0.055166412703692914,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.07168184407055378,
"min": 0.04468101914972067,
"max": 0.1593074763814608,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.82734872425001e-06,
"min": 3.82734872425001e-06,
"max": 0.0002952933015688999,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 7.65469744850002e-06,
"min": 7.65469744850002e-06,
"max": 0.0008440125186625,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10127574999999997,
"min": 0.10127574999999997,
"max": 0.19843110000000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20255149999999994,
"min": 0.20255149999999994,
"max": 0.5813375000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.365992500000017e-05,
"min": 7.365992500000017e-05,
"max": 0.004921711890000002,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00014731985000000035,
"min": 0.00014731985000000035,
"max": 0.01406874125,
"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": "1749179541",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1749182093"
},
"total": 2551.566390346,
"count": 1,
"self": 0.4870976279999013,
"children": {
"run_training.setup": {
"total": 0.022373099999981605,
"count": 1,
"self": 0.022373099999981605
},
"TrainerController.start_learning": {
"total": 2551.056919618,
"count": 1,
"self": 4.882502101065711,
"children": {
"TrainerController._reset_env": {
"total": 3.599130563000017,
"count": 1,
"self": 3.599130563000017
},
"TrainerController.advance": {
"total": 2542.464702591934,
"count": 230410,
"self": 5.065407986917307,
"children": {
"env_step": {
"total": 2065.9238084849558,
"count": 230410,
"self": 1619.008725846913,
"children": {
"SubprocessEnvManager._take_step": {
"total": 443.92516538899235,
"count": 230410,
"self": 16.879960202934058,
"children": {
"TorchPolicy.evaluate": {
"total": 427.0452051860583,
"count": 222934,
"self": 427.0452051860583
}
}
},
"workers": {
"total": 2.9899172490504498,
"count": 230410,
"self": 0.0,
"children": {
"worker_root": {
"total": 2543.2745420020083,
"count": 230410,
"is_parallel": true,
"self": 1229.7044907489699,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009536289999232395,
"count": 1,
"is_parallel": true,
"self": 0.0002638099998648613,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006898190000583782,
"count": 2,
"is_parallel": true,
"self": 0.0006898190000583782
}
}
},
"UnityEnvironment.step": {
"total": 0.03226796000001286,
"count": 1,
"is_parallel": true,
"self": 0.0003090400000473892,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021421700000701094,
"count": 1,
"is_parallel": true,
"self": 0.00021421700000701094
},
"communicator.exchange": {
"total": 0.03105276999997386,
"count": 1,
"is_parallel": true,
"self": 0.03105276999997386
},
"steps_from_proto": {
"total": 0.0006919329999846013,
"count": 1,
"is_parallel": true,
"self": 0.00019758500002353685,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004943479999610645,
"count": 2,
"is_parallel": true,
"self": 0.0004943479999610645
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1313.5700512530384,
"count": 230409,
"is_parallel": true,
"self": 38.62082362010506,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.313998787885,
"count": 230409,
"is_parallel": true,
"self": 83.313998787885
},
"communicator.exchange": {
"total": 1099.8704180940504,
"count": 230409,
"is_parallel": true,
"self": 1099.8704180940504
},
"steps_from_proto": {
"total": 91.76481075099821,
"count": 230409,
"is_parallel": true,
"self": 33.479237435786786,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.28557331521142,
"count": 460818,
"is_parallel": true,
"self": 58.28557331521142
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 471.4754861200611,
"count": 230410,
"self": 7.292422949062825,
"children": {
"process_trajectory": {
"total": 160.3477421709996,
"count": 230410,
"self": 159.14312796199908,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2046142090005105,
"count": 10,
"self": 1.2046142090005105
}
}
},
"_update_policy": {
"total": 303.83532099999866,
"count": 96,
"self": 238.59176287500077,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.24355812499789,
"count": 2880,
"self": 65.24355812499789
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.770002750679851e-07,
"count": 1,
"self": 8.770002750679851e-07
},
"TrainerController._save_models": {
"total": 0.11058348500000648,
"count": 1,
"self": 0.0018002980000346724,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1087831869999718,
"count": 1,
"self": 0.1087831869999718
}
}
}
}
}
}
}