ppo-Huggy / run_logs /timers.json
Varun3003's picture
Huggy
38ecae3 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4078185558319092,
"min": 1.4078185558319092,
"max": 1.4079304933547974,
"count": 3
},
"Huggy.Policy.Entropy.sum": {
"value": 70303.640625,
"min": 34229.60546875,
"max": 70806.9453125,
"count": 3
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 69.24297752808988,
"min": 63.31436314363144,
"max": 69.43723554301833,
"count": 3
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49301.0,
"min": 23363.0,
"max": 49301.0,
"count": 3
},
"Huggy.Step.mean": {
"value": 1999895.0,
"min": 1899906.0,
"max": 1999895.0,
"count": 3
},
"Huggy.Step.sum": {
"value": 1999895.0,
"min": 1899906.0,
"max": 1999895.0,
"count": 3
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5791008472442627,
"min": 2.4865686893463135,
"max": 2.5969748497009277,
"count": 3
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1836.31982421875,
"min": 915.0572509765625,
"max": 1841.255126953125,
"count": 3
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 4.112842669480302,
"min": 3.7975530732908975,
"max": 4.148647422430714,
"count": 3
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2928.3439806699753,
"min": 1397.4995309710503,
"max": 2941.391022503376,
"count": 3
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 4.112842669480302,
"min": 3.7975530732908975,
"max": 4.148647422430714,
"count": 3
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2928.3439806699753,
"min": 1397.4995309710503,
"max": 2941.391022503376,
"count": 3
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01438166230909701,
"min": 0.01438166230909701,
"max": 0.016280190468144915,
"count": 3
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04314498692729103,
"min": 0.016280190468144915,
"max": 0.04314498692729103,
"count": 3
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06650554392900732,
"min": 0.06050551186005275,
"max": 0.07349235241611798,
"count": 3
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.19951663178702195,
"min": 0.07349235241611798,
"max": 0.19951663178702195,
"count": 3
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.1660989446666586e-06,
"min": 3.1660989446666586e-06,
"max": 1.5478144840649985e-05,
"count": 3
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.498296833999976e-06,
"min": 9.498296833999976e-06,
"max": 2.1715542761549993e-05,
"count": 3
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10105533333333334,
"min": 0.10105533333333334,
"max": 0.10515935000000003,
"count": 3
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30316600000000005,
"min": 0.10515935000000003,
"max": 0.30316600000000005,
"count": 3
},
"Huggy.Policy.Beta.mean": {
"value": 6.26611333333332e-05,
"min": 6.26611333333332e-05,
"max": 0.0002674515649999999,
"count": 3
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001879833999999996,
"min": 0.0001879833999999996,
"max": 0.0003811986549999998,
"count": 3
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 3
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 3
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1735715681",
"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 --resume",
"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": "1735715845"
},
"total": 163.20464884000012,
"count": 1,
"self": 0.42561060699972586,
"children": {
"run_training.setup": {
"total": 0.07794596700023249,
"count": 1,
"self": 0.07794596700023249
},
"TrainerController.start_learning": {
"total": 162.70109226600016,
"count": 1,
"self": 0.28975740298847086,
"children": {
"TrainerController._reset_env": {
"total": 2.969570159000341,
"count": 1,
"self": 2.969570159000341
},
"TrainerController.advance": {
"total": 159.32523929001127,
"count": 14729,
"self": 0.3018612370333358,
"children": {
"env_step": {
"total": 124.5877541089676,
"count": 14729,
"self": 98.86658754790687,
"children": {
"SubprocessEnvManager._take_step": {
"total": 25.544050222028545,
"count": 14729,
"self": 0.9978616390003481,
"children": {
"TorchPolicy.evaluate": {
"total": 24.546188583028197,
"count": 13888,
"self": 24.546188583028197
}
}
},
"workers": {
"total": 0.1771163390321817,
"count": 14729,
"self": 0.0,
"children": {
"worker_root": {
"total": 161.99661894402288,
"count": 14729,
"is_parallel": true,
"self": 81.91649820003886,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0012232979997861548,
"count": 1,
"is_parallel": true,
"self": 0.00043257199968138593,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007907260001047689,
"count": 2,
"is_parallel": true,
"self": 0.0007907260001047689
}
}
},
"UnityEnvironment.step": {
"total": 0.047294634000081714,
"count": 1,
"is_parallel": true,
"self": 0.000400545000047714,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021651299994118745,
"count": 1,
"is_parallel": true,
"self": 0.00021651299994118745
},
"communicator.exchange": {
"total": 0.04590668299988465,
"count": 1,
"is_parallel": true,
"self": 0.04590668299988465
},
"steps_from_proto": {
"total": 0.0007708930002081615,
"count": 1,
"is_parallel": true,
"self": 0.0002213010006926197,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005495919995155418,
"count": 2,
"is_parallel": true,
"self": 0.0005495919995155418
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 80.08012074398403,
"count": 14728,
"is_parallel": true,
"self": 2.428441069991095,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.151757104981243,
"count": 14728,
"is_parallel": true,
"self": 5.151757104981243
},
"communicator.exchange": {
"total": 66.74710102898644,
"count": 14728,
"is_parallel": true,
"self": 66.74710102898644
},
"steps_from_proto": {
"total": 5.752821540025252,
"count": 14728,
"is_parallel": true,
"self": 2.1375824729689157,
"children": {
"_process_rank_one_or_two_observation": {
"total": 3.6152390670563364,
"count": 29456,
"is_parallel": true,
"self": 3.6152390670563364
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 34.43562394401033,
"count": 14729,
"self": 0.41448756902082096,
"children": {
"process_trajectory": {
"total": 12.708713380988684,
"count": 14729,
"self": 12.541479591988718,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16723378899996533,
"count": 1,
"self": 0.16723378899996533
}
}
},
"_update_policy": {
"total": 21.312422994000826,
"count": 6,
"self": 16.639868448003654,
"children": {
"TorchPPOOptimizer.update": {
"total": 4.672554545997173,
"count": 180,
"self": 4.672554545997173
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0230000953015406e-06,
"count": 1,
"self": 1.0230000953015406e-06
},
"TrainerController._save_models": {
"total": 0.11652439099998446,
"count": 1,
"self": 0.002964906999750383,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11355948400023408,
"count": 1,
"self": 0.11355948400023408
}
}
}
}
}
}
}