ppo-Huggy / run_logs /timers.json
lvtiendev's picture
Huggy
78c4a32 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.406119465827942,
"min": 1.406119465827942,
"max": 1.4299938678741455,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71773.9609375,
"min": 67685.2890625,
"max": 77332.953125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 102.32172131147541,
"min": 79.11698717948718,
"max": 424.7881355932203,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49933.0,
"min": 48954.0,
"max": 50125.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999766.0,
"min": 49729.0,
"max": 1999766.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999766.0,
"min": 49729.0,
"max": 1999766.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4633259773254395,
"min": 0.03303833305835724,
"max": 2.4792544841766357,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1202.10302734375,
"min": 3.8654849529266357,
"max": 1508.1082763671875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.808101892593454,
"min": 1.7307228109775445,
"max": 3.9207818426919028,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1858.3537235856056,
"min": 202.4945688843727,
"max": 2376.7691264152527,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.808101892593454,
"min": 1.7307228109775445,
"max": 3.9207818426919028,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1858.3537235856056,
"min": 202.4945688843727,
"max": 2376.7691264152527,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018803313619597854,
"min": 0.014045640252212858,
"max": 0.0218669590530529,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05640994085879356,
"min": 0.028091280504425716,
"max": 0.057072980058243655,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05053247461716334,
"min": 0.021232315121839443,
"max": 0.05911328090975682,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15159742385149003,
"min": 0.042464630243678886,
"max": 0.17608762308955195,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4244988585333274e-06,
"min": 3.4244988585333274e-06,
"max": 0.00029528737657087505,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0273496575599982e-05,
"min": 1.0273496575599982e-05,
"max": 0.0008439729186756999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10114146666666667,
"min": 0.10114146666666667,
"max": 0.19842912499999993,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3034244,
"min": 0.20746964999999995,
"max": 0.5813242999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.695918666666659e-05,
"min": 6.695918666666659e-05,
"max": 0.0049216133374999985,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020087755999999976,
"min": 0.00020087755999999976,
"max": 0.01406808257,
"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": "1722351511",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1722354283"
},
"total": 2772.235833231,
"count": 1,
"self": 0.4872708200005036,
"children": {
"run_training.setup": {
"total": 0.06607792299996618,
"count": 1,
"self": 0.06607792299996618
},
"TrainerController.start_learning": {
"total": 2771.682484488,
"count": 1,
"self": 5.393054099897199,
"children": {
"TrainerController._reset_env": {
"total": 3.285085492999997,
"count": 1,
"self": 3.285085492999997
},
"TrainerController.advance": {
"total": 2762.8858550801024,
"count": 232628,
"self": 5.539223341287197,
"children": {
"env_step": {
"total": 2215.2335957789055,
"count": 232628,
"self": 1830.021178929053,
"children": {
"SubprocessEnvManager._take_step": {
"total": 381.52736872397134,
"count": 232628,
"self": 20.979119931966466,
"children": {
"TorchPolicy.evaluate": {
"total": 360.54824879200487,
"count": 223020,
"self": 360.54824879200487
}
}
},
"workers": {
"total": 3.685048125881167,
"count": 232628,
"self": 0.0,
"children": {
"worker_root": {
"total": 2763.3099201020596,
"count": 232628,
"is_parallel": true,
"self": 1288.197585812047,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010954809999930148,
"count": 1,
"is_parallel": true,
"self": 0.00029907300006470905,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007964079999283058,
"count": 2,
"is_parallel": true,
"self": 0.0007964079999283058
}
}
},
"UnityEnvironment.step": {
"total": 0.03135183400002006,
"count": 1,
"is_parallel": true,
"self": 0.00045572499993795645,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022265100005824934,
"count": 1,
"is_parallel": true,
"self": 0.00022265100005824934
},
"communicator.exchange": {
"total": 0.029843766999988475,
"count": 1,
"is_parallel": true,
"self": 0.029843766999988475
},
"steps_from_proto": {
"total": 0.0008296910000353819,
"count": 1,
"is_parallel": true,
"self": 0.00026665300003969605,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005630379999956858,
"count": 2,
"is_parallel": true,
"self": 0.0005630379999956858
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1475.1123342900125,
"count": 232627,
"is_parallel": true,
"self": 45.13443049590683,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 92.09313005212596,
"count": 232627,
"is_parallel": true,
"self": 92.09313005212596
},
"communicator.exchange": {
"total": 1232.8561627070667,
"count": 232627,
"is_parallel": true,
"self": 1232.8561627070667
},
"steps_from_proto": {
"total": 105.02861103491307,
"count": 232627,
"is_parallel": true,
"self": 37.42186578568351,
"children": {
"_process_rank_one_or_two_observation": {
"total": 67.60674524922956,
"count": 465254,
"is_parallel": true,
"self": 67.60674524922956
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 542.1130359599097,
"count": 232628,
"self": 8.355937044912139,
"children": {
"process_trajectory": {
"total": 175.9601402080002,
"count": 232628,
"self": 174.55209761399942,
"children": {
"RLTrainer._checkpoint": {
"total": 1.40804259400079,
"count": 10,
"self": 1.40804259400079
}
}
},
"_update_policy": {
"total": 357.7969587069973,
"count": 97,
"self": 289.8156886769856,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.98127003001173,
"count": 2910,
"self": 67.98127003001173
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.93999947240809e-07,
"count": 1,
"self": 9.93999947240809e-07
},
"TrainerController._save_models": {
"total": 0.11848882100002811,
"count": 1,
"self": 0.0022227280001061445,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11626609299992197,
"count": 1,
"self": 0.11626609299992197
}
}
}
}
}
}
}