ppo-Huggy / run_logs /timers.json
staryesh's picture
Huggy
9f29b0c
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3970621824264526,
"min": 1.3970621824264526,
"max": 1.4257683753967285,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68823.4765625,
"min": 68775.5546875,
"max": 78322.953125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 77.61102362204724,
"min": 68.21991701244814,
"max": 413.5409836065574,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49283.0,
"min": 49165.0,
"max": 50452.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999962.0,
"min": 49913.0,
"max": 1999962.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999962.0,
"min": 49913.0,
"max": 1999962.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.6096279621124268,
"min": -0.030256260186433792,
"max": 2.6096279621124268,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1657.11376953125,
"min": -3.6610074043273926,
"max": 1828.39697265625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 4.077525552896064,
"min": 1.722768699827273,
"max": 4.096002539970737,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2589.2287260890007,
"min": 208.45501267910004,
"max": 2860.2500005960464,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 4.077525552896064,
"min": 1.722768699827273,
"max": 4.096002539970737,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2589.2287260890007,
"min": 208.45501267910004,
"max": 2860.2500005960464,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016456059222238962,
"min": 0.011584963109089585,
"max": 0.02033855801435291,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04936817766671689,
"min": 0.02316992621817917,
"max": 0.06101567404305873,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05729138979481326,
"min": 0.024348536940912404,
"max": 0.06629567734069293,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17187416938443978,
"min": 0.04869707388182481,
"max": 0.1988870320220788,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7381987539666667e-06,
"min": 3.7381987539666667e-06,
"max": 0.00029531535156154993,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.12145962619e-05,
"min": 1.12145962619e-05,
"max": 0.0008438587687137498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10124603333333336,
"min": 0.10124603333333336,
"max": 0.19843845000000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30373810000000007,
"min": 0.20768765,
"max": 0.58128625,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.217706333333331e-05,
"min": 7.217706333333331e-05,
"max": 0.004922078655,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021653118999999995,
"min": 0.00021653118999999995,
"max": 0.014066183875000002,
"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": "1696502481",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=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": "1696504962"
},
"total": 2481.801180987,
"count": 1,
"self": 0.8429761209995377,
"children": {
"run_training.setup": {
"total": 0.04269568300003357,
"count": 1,
"self": 0.04269568300003357
},
"TrainerController.start_learning": {
"total": 2480.9155091830003,
"count": 1,
"self": 4.53087317106565,
"children": {
"TrainerController._reset_env": {
"total": 4.178243357000042,
"count": 1,
"self": 4.178243357000042
},
"TrainerController.advance": {
"total": 2472.015587390934,
"count": 233426,
"self": 4.62513942376836,
"children": {
"env_step": {
"total": 1899.924702445009,
"count": 233426,
"self": 1604.606394186063,
"children": {
"SubprocessEnvManager._take_step": {
"total": 292.3381439809349,
"count": 233426,
"self": 16.533973967922066,
"children": {
"TorchPolicy.evaluate": {
"total": 275.8041700130128,
"count": 222902,
"self": 275.8041700130128
}
}
},
"workers": {
"total": 2.9801642780109887,
"count": 233426,
"self": 0.0,
"children": {
"worker_root": {
"total": 2473.1981963769285,
"count": 233426,
"is_parallel": true,
"self": 1161.9918458668335,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008889289999842731,
"count": 1,
"is_parallel": true,
"self": 0.00022808799997164897,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006608410000126241,
"count": 2,
"is_parallel": true,
"self": 0.0006608410000126241
}
}
},
"UnityEnvironment.step": {
"total": 0.028625984999962384,
"count": 1,
"is_parallel": true,
"self": 0.0003225690001045223,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002379179999252301,
"count": 1,
"is_parallel": true,
"self": 0.0002379179999252301
},
"communicator.exchange": {
"total": 0.027316952999967725,
"count": 1,
"is_parallel": true,
"self": 0.027316952999967725
},
"steps_from_proto": {
"total": 0.0007485449999649063,
"count": 1,
"is_parallel": true,
"self": 0.00021981999987019663,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005287250000947097,
"count": 2,
"is_parallel": true,
"self": 0.0005287250000947097
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1311.206350510095,
"count": 233425,
"is_parallel": true,
"self": 40.37867014899075,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.16007252706072,
"count": 233425,
"is_parallel": true,
"self": 81.16007252706072
},
"communicator.exchange": {
"total": 1089.864327933038,
"count": 233425,
"is_parallel": true,
"self": 1089.864327933038
},
"steps_from_proto": {
"total": 99.80327990100557,
"count": 233425,
"is_parallel": true,
"self": 35.58263721712649,
"children": {
"_process_rank_one_or_two_observation": {
"total": 64.22064268387908,
"count": 466850,
"is_parallel": true,
"self": 64.22064268387908
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 567.4657455221563,
"count": 233426,
"self": 6.79901990725466,
"children": {
"process_trajectory": {
"total": 146.9849625809003,
"count": 233426,
"self": 145.71754464790024,
"children": {
"RLTrainer._checkpoint": {
"total": 1.267417933000047,
"count": 10,
"self": 1.267417933000047
}
}
},
"_update_policy": {
"total": 413.6817630340014,
"count": 97,
"self": 352.85080760399615,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.83095543000525,
"count": 2910,
"self": 60.83095543000525
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5340001482400112e-06,
"count": 1,
"self": 1.5340001482400112e-06
},
"TrainerController._save_models": {
"total": 0.19080373000042528,
"count": 1,
"self": 0.0029116390005583526,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18789209099986692,
"count": 1,
"self": 0.18789209099986692
}
}
}
}
}
}
}