ppo-Huggy / run_logs /timers.json
Davide Paolini
Huggy
0172364
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4017877578735352,
"min": 1.4017877578735352,
"max": 1.4249809980392456,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69410.921875,
"min": 68704.8984375,
"max": 78034.640625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 83.17845117845118,
"min": 73.23476968796435,
"max": 405.8048780487805,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49408.0,
"min": 48675.0,
"max": 50185.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999973.0,
"min": 49978.0,
"max": 1999973.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999973.0,
"min": 49978.0,
"max": 1999973.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4855990409851074,
"min": 0.09128981083631516,
"max": 2.496088981628418,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1476.44580078125,
"min": 11.137356758117676,
"max": 1650.375244140625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8804855554392845,
"min": 1.8656711382944076,
"max": 4.072091242897299,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2305.008419930935,
"min": 227.61187887191772,
"max": 2632.965951502323,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8804855554392845,
"min": 1.8656711382944076,
"max": 4.072091242897299,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2305.008419930935,
"min": 227.61187887191772,
"max": 2632.965951502323,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01770052363313476,
"min": 0.01354292105291582,
"max": 0.022301424737452183,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.053101570899404274,
"min": 0.02708584210583164,
"max": 0.05847789314866532,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.054202016236053564,
"min": 0.021724173643936716,
"max": 0.0646362434244818,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1626060487081607,
"min": 0.04344834728787343,
"max": 0.19390873027344543,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7116987628000043e-06,
"min": 3.7116987628000043e-06,
"max": 0.00029532000156,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1135096288400013e-05,
"min": 1.1135096288400013e-05,
"max": 0.0008438908687030498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10123720000000001,
"min": 0.10123720000000001,
"max": 0.19844000000000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037116,
"min": 0.2075993,
"max": 0.58129695,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.173628000000008e-05,
"min": 7.173628000000008e-05,
"max": 0.0049221560000000004,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021520884000000024,
"min": 0.00021520884000000024,
"max": 0.014066717805,
"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": "1682244380",
"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": "1682246960"
},
"total": 2580.621359502,
"count": 1,
"self": 0.43746208099992145,
"children": {
"run_training.setup": {
"total": 0.1306163090000041,
"count": 1,
"self": 0.1306163090000041
},
"TrainerController.start_learning": {
"total": 2580.053281112,
"count": 1,
"self": 4.995455033953931,
"children": {
"TrainerController._reset_env": {
"total": 5.743061146000002,
"count": 1,
"self": 5.743061146000002
},
"TrainerController.advance": {
"total": 2569.1310266560463,
"count": 233292,
"self": 5.106868744027906,
"children": {
"env_step": {
"total": 2018.6845448940662,
"count": 233292,
"self": 1716.2600491970702,
"children": {
"SubprocessEnvManager._take_step": {
"total": 299.27644247902697,
"count": 233292,
"self": 18.049910497080646,
"children": {
"TorchPolicy.evaluate": {
"total": 281.2265319819463,
"count": 223020,
"self": 281.2265319819463
}
}
},
"workers": {
"total": 3.148053217969135,
"count": 233292,
"self": 0.0,
"children": {
"worker_root": {
"total": 2570.978333850114,
"count": 233292,
"is_parallel": true,
"self": 1165.6083000952258,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011426100000164752,
"count": 1,
"is_parallel": true,
"self": 0.00043637300001364565,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007062370000028295,
"count": 2,
"is_parallel": true,
"self": 0.0007062370000028295
}
}
},
"UnityEnvironment.step": {
"total": 0.05701593000000571,
"count": 1,
"is_parallel": true,
"self": 0.0003320890000111376,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00024991099999738253,
"count": 1,
"is_parallel": true,
"self": 0.00024991099999738253
},
"communicator.exchange": {
"total": 0.05556353099999001,
"count": 1,
"is_parallel": true,
"self": 0.05556353099999001
},
"steps_from_proto": {
"total": 0.0008703990000071826,
"count": 1,
"is_parallel": true,
"self": 0.0002811589999964781,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005892400000107045,
"count": 2,
"is_parallel": true,
"self": 0.0005892400000107045
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1405.370033754888,
"count": 233291,
"is_parallel": true,
"self": 40.95393923191841,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 89.73483266299172,
"count": 233291,
"is_parallel": true,
"self": 89.73483266299172
},
"communicator.exchange": {
"total": 1177.4908656939278,
"count": 233291,
"is_parallel": true,
"self": 1177.4908656939278
},
"steps_from_proto": {
"total": 97.1903961660501,
"count": 233291,
"is_parallel": true,
"self": 39.283324136987915,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.90707202906219,
"count": 466582,
"is_parallel": true,
"self": 57.90707202906219
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 545.3396130179524,
"count": 233292,
"self": 7.164191422907152,
"children": {
"process_trajectory": {
"total": 147.80518107404572,
"count": 233292,
"self": 146.26386577904634,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5413152949993787,
"count": 10,
"self": 1.5413152949993787
}
}
},
"_update_policy": {
"total": 390.37024052099946,
"count": 97,
"self": 330.7502229950006,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.62001752599883,
"count": 2910,
"self": 59.62001752599883
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5250002434186172e-06,
"count": 1,
"self": 1.5250002434186172e-06
},
"TrainerController._save_models": {
"total": 0.18373675099974207,
"count": 1,
"self": 0.0021018009997533227,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18163494999998875,
"count": 1,
"self": 0.18163494999998875
}
}
}
}
}
}
}