ppo-Huggy / run_logs /timers.json
Sukmin's picture
Huggy
4406898
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4128552675247192,
"min": 1.4128552675247192,
"max": 1.432778000831604,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70344.6484375,
"min": 67175.7578125,
"max": 76174.4375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 127.58717948717948,
"min": 98.246,
"max": 409.1885245901639,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49759.0,
"min": 49012.0,
"max": 50417.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999410.0,
"min": 49572.0,
"max": 1999410.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999410.0,
"min": 49572.0,
"max": 1999410.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.260305166244507,
"min": 0.20159947872161865,
"max": 2.385887861251831,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 881.5189819335938,
"min": 24.393537521362305,
"max": 1134.262451171875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.4485331922005384,
"min": 1.9272021760871587,
"max": 3.812613448532679,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1344.92794495821,
"min": 233.1914633065462,
"max": 1800.312742292881,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.4485331922005384,
"min": 1.9272021760871587,
"max": 3.812613448532679,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1344.92794495821,
"min": 233.1914633065462,
"max": 1800.312742292881,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017244577428209597,
"min": 0.013074379187310116,
"max": 0.01976627193701764,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.034489154856419194,
"min": 0.026148758374620232,
"max": 0.05777192876654832,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0432997294391195,
"min": 0.01973511775334676,
"max": 0.0703946544478337,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.086599458878239,
"min": 0.03947023550669352,
"max": 0.1977288141846657,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.247198584299991e-06,
"min": 4.247198584299991e-06,
"max": 0.00029532045155984996,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.494397168599982e-06,
"min": 8.494397168599982e-06,
"max": 0.0008439097686967499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1014157,
"min": 0.1014157,
"max": 0.19844015000000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.2028314,
"min": 0.2028314,
"max": 0.5813032499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.06434299999999e-05,
"min": 8.06434299999999e-05,
"max": 0.0049221634850000005,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001612868599999998,
"min": 0.0001612868599999998,
"max": 0.014067032174999999,
"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": "1687331589",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"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": "1687334654"
},
"total": 3064.6738475310003,
"count": 1,
"self": 0.9035874539999895,
"children": {
"run_training.setup": {
"total": 0.04979944400002978,
"count": 1,
"self": 0.04979944400002978
},
"TrainerController.start_learning": {
"total": 3063.720460633,
"count": 1,
"self": 6.4439539489872,
"children": {
"TrainerController._reset_env": {
"total": 5.082275788999993,
"count": 1,
"self": 5.082275788999993
},
"TrainerController.advance": {
"total": 3051.956611463013,
"count": 230355,
"self": 6.8920444330665305,
"children": {
"env_step": {
"total": 2431.7947039109627,
"count": 230355,
"self": 2032.2009268000522,
"children": {
"SubprocessEnvManager._take_step": {
"total": 395.4191048429412,
"count": 230355,
"self": 23.69971727589575,
"children": {
"TorchPolicy.evaluate": {
"total": 371.71938756704543,
"count": 223016,
"self": 371.71938756704543
}
}
},
"workers": {
"total": 4.1746722679692425,
"count": 230355,
"self": 0.0,
"children": {
"worker_root": {
"total": 3052.8783351459297,
"count": 230355,
"is_parallel": true,
"self": 1405.4788608489723,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000971128999992743,
"count": 1,
"is_parallel": true,
"self": 0.0002713220000032379,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006998069999895051,
"count": 2,
"is_parallel": true,
"self": 0.0006998069999895051
}
}
},
"UnityEnvironment.step": {
"total": 0.06642309500000465,
"count": 1,
"is_parallel": true,
"self": 0.00038172699993310744,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00025051800002984237,
"count": 1,
"is_parallel": true,
"self": 0.00025051800002984237
},
"communicator.exchange": {
"total": 0.06480888900000537,
"count": 1,
"is_parallel": true,
"self": 0.06480888900000537
},
"steps_from_proto": {
"total": 0.0009819610000363355,
"count": 1,
"is_parallel": true,
"self": 0.0002913820000571832,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006905789999791523,
"count": 2,
"is_parallel": true,
"self": 0.0006905789999791523
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1647.3994742969574,
"count": 230354,
"is_parallel": true,
"self": 48.37083706896988,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 99.20613774898601,
"count": 230354,
"is_parallel": true,
"self": 99.20613774898601
},
"communicator.exchange": {
"total": 1378.4393644269962,
"count": 230354,
"is_parallel": true,
"self": 1378.4393644269962
},
"steps_from_proto": {
"total": 121.38313505200512,
"count": 230354,
"is_parallel": true,
"self": 44.0493814650676,
"children": {
"_process_rank_one_or_two_observation": {
"total": 77.33375358693752,
"count": 460708,
"is_parallel": true,
"self": 77.33375358693752
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 613.2698631189835,
"count": 230355,
"self": 10.001917158990182,
"children": {
"process_trajectory": {
"total": 156.96053653499314,
"count": 230355,
"self": 155.29654135699263,
"children": {
"RLTrainer._checkpoint": {
"total": 1.663995178000505,
"count": 10,
"self": 1.663995178000505
}
}
},
"_update_policy": {
"total": 446.3074094250001,
"count": 96,
"self": 379.93247641799866,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.37493300700146,
"count": 2880,
"self": 66.37493300700146
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.7359998309984803e-06,
"count": 1,
"self": 1.7359998309984803e-06
},
"TrainerController._save_models": {
"total": 0.23761769600014304,
"count": 1,
"self": 0.003488868000204093,
"children": {
"RLTrainer._checkpoint": {
"total": 0.23412882799993895,
"count": 1,
"self": 0.23412882799993895
}
}
}
}
}
}
}