ppo-Huggy / run_logs /timers.json
pabloyesteb's picture
Huggy
d8674c2
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3991328477859497,
"min": 1.3991323709487915,
"max": 1.4268561601638794,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70348.3984375,
"min": 67285.3828125,
"max": 76441.578125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 114.71495327102804,
"min": 83.52364864864865,
"max": 380.06060606060606,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49098.0,
"min": 48976.0,
"max": 50168.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999884.0,
"min": 49550.0,
"max": 1999884.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999884.0,
"min": 49550.0,
"max": 1999884.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2952442169189453,
"min": 0.07706116884946823,
"max": 2.4293456077575684,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 982.364501953125,
"min": 10.095012664794922,
"max": 1421.479248046875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.4301374067212933,
"min": 1.7667426805914814,
"max": 3.931053409625978,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1468.0988100767136,
"min": 231.44329115748405,
"max": 2202.2782931923866,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.4301374067212933,
"min": 1.7667426805914814,
"max": 3.931053409625978,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1468.0988100767136,
"min": 231.44329115748405,
"max": 2202.2782931923866,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.02014641665191448,
"min": 0.01470068506472065,
"max": 0.0211811096368668,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.06043924995574344,
"min": 0.029736071918159725,
"max": 0.06043924995574344,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04748354574872388,
"min": 0.02257385930667321,
"max": 0.06585777542657321,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14245063724617163,
"min": 0.04514771861334642,
"max": 0.19757332627971966,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.2502489166166622e-06,
"min": 3.2502489166166622e-06,
"max": 0.00029528347657217487,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.750746749849986e-06,
"min": 9.750746749849986e-06,
"max": 0.0008440291686569499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10108338333333335,
"min": 0.10108338333333335,
"max": 0.198427825,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30325015000000005,
"min": 0.20734175000000007,
"max": 0.5813430500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.40608283333333e-05,
"min": 6.40608283333333e-05,
"max": 0.0049215484675,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001921824849999999,
"min": 0.0001921824849999999,
"max": 0.014069018195000001,
"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": "1681722708",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1681725028"
},
"total": 2319.422292646,
"count": 1,
"self": 0.38901010300014605,
"children": {
"run_training.setup": {
"total": 0.1101858249999168,
"count": 1,
"self": 0.1101858249999168
},
"TrainerController.start_learning": {
"total": 2318.923096718,
"count": 1,
"self": 4.181431069087921,
"children": {
"TrainerController._reset_env": {
"total": 3.890764792999903,
"count": 1,
"self": 3.890764792999903
},
"TrainerController.advance": {
"total": 2310.731910282912,
"count": 231824,
"self": 4.458707777865584,
"children": {
"env_step": {
"total": 1816.1950178610318,
"count": 231824,
"self": 1539.0022144679801,
"children": {
"SubprocessEnvManager._take_step": {
"total": 274.435057082052,
"count": 231824,
"self": 15.963373299118075,
"children": {
"TorchPolicy.evaluate": {
"total": 258.47168378293395,
"count": 223106,
"self": 258.47168378293395
}
}
},
"workers": {
"total": 2.7577463109995506,
"count": 231824,
"self": 0.0,
"children": {
"worker_root": {
"total": 2310.8480687798706,
"count": 231824,
"is_parallel": true,
"self": 1050.524767005839,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009296370000129173,
"count": 1,
"is_parallel": true,
"self": 0.0002690540001140107,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006605829998989066,
"count": 2,
"is_parallel": true,
"self": 0.0006605829998989066
}
}
},
"UnityEnvironment.step": {
"total": 0.03170803400007571,
"count": 1,
"is_parallel": true,
"self": 0.00032894700018459844,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023781599998073943,
"count": 1,
"is_parallel": true,
"self": 0.00023781599998073943
},
"communicator.exchange": {
"total": 0.03046472999994876,
"count": 1,
"is_parallel": true,
"self": 0.03046472999994876
},
"steps_from_proto": {
"total": 0.0006765409999616168,
"count": 1,
"is_parallel": true,
"self": 0.00019963099998676626,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004769099999748505,
"count": 2,
"is_parallel": true,
"self": 0.0004769099999748505
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1260.3233017740315,
"count": 231823,
"is_parallel": true,
"self": 38.05327489003071,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.87319680310202,
"count": 231823,
"is_parallel": true,
"self": 78.87319680310202
},
"communicator.exchange": {
"total": 1055.1952717119402,
"count": 231823,
"is_parallel": true,
"self": 1055.1952717119402
},
"steps_from_proto": {
"total": 88.20155836895856,
"count": 231823,
"is_parallel": true,
"self": 33.311040705925734,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.890517663032824,
"count": 463646,
"is_parallel": true,
"self": 54.890517663032824
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 490.0781846440144,
"count": 231824,
"self": 6.669673544076318,
"children": {
"process_trajectory": {
"total": 126.30225664893715,
"count": 231824,
"self": 125.0303831919374,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2718734569997423,
"count": 10,
"self": 1.2718734569997423
}
}
},
"_update_policy": {
"total": 357.10625445100095,
"count": 97,
"self": 299.7297702030054,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.37648424799556,
"count": 2910,
"self": 57.37648424799556
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4170000213198364e-06,
"count": 1,
"self": 1.4170000213198364e-06
},
"TrainerController._save_models": {
"total": 0.1189891560002252,
"count": 1,
"self": 0.001972741999907157,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11701641400031804,
"count": 1,
"self": 0.11701641400031804
}
}
}
}
}
}
}