ppo-Huggy / run_logs /timers.json
DaanMth's picture
Huggy
f4772ab verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4048010110855103,
"min": 1.4047960042953491,
"max": 1.4313181638717651,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70960.7109375,
"min": 68636.3125,
"max": 77006.5234375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 105.39957264957265,
"min": 98.14512922465208,
"max": 376.3233082706767,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49327.0,
"min": 48854.0,
"max": 50214.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999891.0,
"min": 49681.0,
"max": 1999891.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999891.0,
"min": 49681.0,
"max": 1999891.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.30536150932312,
"min": 0.08605475723743439,
"max": 2.3933913707733154,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1078.9091796875,
"min": 11.359228134155273,
"max": 1166.55419921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.4810442853177714,
"min": 1.8418909952496036,
"max": 3.8715183505344184,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1629.128725528717,
"min": 243.1296113729477,
"max": 1879.6607278585434,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.4810442853177714,
"min": 1.8418909952496036,
"max": 3.8715183505344184,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1629.128725528717,
"min": 243.1296113729477,
"max": 1879.6607278585434,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01494850351235881,
"min": 0.01300532792180699,
"max": 0.01897742722843153,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04484551053707643,
"min": 0.02601065584361398,
"max": 0.05353290092631748,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.049212923687365316,
"min": 0.0213198511240383,
"max": 0.07202567358811696,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14763877106209594,
"min": 0.0426397022480766,
"max": 0.19869766856233279,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.265348911583331e-06,
"min": 3.265348911583331e-06,
"max": 0.00029528145157284996,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.796046734749992e-06,
"min": 9.796046734749992e-06,
"max": 0.0008438706187097999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10108841666666667,
"min": 0.10108841666666667,
"max": 0.19842714999999994,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30326525,
"min": 0.2073987,
"max": 0.5812902,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.431199166666663e-05,
"min": 6.431199166666663e-05,
"max": 0.004921514785,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019293597499999988,
"min": 0.00019293597499999988,
"max": 0.01406638098,
"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": "1736279646",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1736282282"
},
"total": 2635.557241053,
"count": 1,
"self": 0.4259510339998087,
"children": {
"run_training.setup": {
"total": 0.05825092099996709,
"count": 1,
"self": 0.05825092099996709
},
"TrainerController.start_learning": {
"total": 2635.073039098,
"count": 1,
"self": 4.780414182003369,
"children": {
"TrainerController._reset_env": {
"total": 6.0527718959999675,
"count": 1,
"self": 6.0527718959999675
},
"TrainerController.advance": {
"total": 2624.1219400099963,
"count": 231104,
"self": 5.091998170158604,
"children": {
"env_step": {
"total": 2068.0427814289524,
"count": 231104,
"self": 1621.2171843140159,
"children": {
"SubprocessEnvManager._take_step": {
"total": 443.7733030689691,
"count": 231104,
"self": 16.786758075948455,
"children": {
"TorchPolicy.evaluate": {
"total": 426.98654499302063,
"count": 222972,
"self": 426.98654499302063
}
}
},
"workers": {
"total": 3.0522940459673578,
"count": 231104,
"self": 0.0,
"children": {
"worker_root": {
"total": 2627.427934566005,
"count": 231104,
"is_parallel": true,
"self": 1311.969078256057,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010008749999883548,
"count": 1,
"is_parallel": true,
"self": 0.0002720140000178617,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007288609999704931,
"count": 2,
"is_parallel": true,
"self": 0.0007288609999704931
}
}
},
"UnityEnvironment.step": {
"total": 0.031222845999991478,
"count": 1,
"is_parallel": true,
"self": 0.0003588060000652149,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002021819999526997,
"count": 1,
"is_parallel": true,
"self": 0.0002021819999526997
},
"communicator.exchange": {
"total": 0.029848716000003606,
"count": 1,
"is_parallel": true,
"self": 0.029848716000003606
},
"steps_from_proto": {
"total": 0.0008131419999699574,
"count": 1,
"is_parallel": true,
"self": 0.00024014499990698823,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005729970000629692,
"count": 2,
"is_parallel": true,
"self": 0.0005729970000629692
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1315.4588563099483,
"count": 231103,
"is_parallel": true,
"self": 39.49973621705294,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 91.91823632695753,
"count": 231103,
"is_parallel": true,
"self": 91.91823632695753
},
"communicator.exchange": {
"total": 1089.8625755659452,
"count": 231103,
"is_parallel": true,
"self": 1089.8625755659452
},
"steps_from_proto": {
"total": 94.17830819999244,
"count": 231103,
"is_parallel": true,
"self": 35.678523690994496,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.49978450899795,
"count": 462206,
"is_parallel": true,
"self": 58.49978450899795
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 550.9871604108853,
"count": 231104,
"self": 6.922269447858753,
"children": {
"process_trajectory": {
"total": 171.90860974902762,
"count": 231104,
"self": 170.48554320702647,
"children": {
"RLTrainer._checkpoint": {
"total": 1.423066542001152,
"count": 10,
"self": 1.423066542001152
}
}
},
"_update_policy": {
"total": 372.15628121399885,
"count": 97,
"self": 301.9711478999974,
"children": {
"TorchPPOOptimizer.update": {
"total": 70.18513331400146,
"count": 2910,
"self": 70.18513331400146
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.919999683916103e-07,
"count": 1,
"self": 9.919999683916103e-07
},
"TrainerController._save_models": {
"total": 0.11791201800042472,
"count": 1,
"self": 0.002191153000239865,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11572086500018486,
"count": 1,
"self": 0.11572086500018486
}
}
}
}
}
}
}