ppo-Huggy / run_logs /timers.json
Amir901's picture
Huggy Pushed
85c63fe verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4056415557861328,
"min": 1.4056415557861328,
"max": 1.4285417795181274,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69818.21875,
"min": 69232.8125,
"max": 77553.8203125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 79.96920583468396,
"min": 75.35015290519878,
"max": 377.7878787878788,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49341.0,
"min": 49026.0,
"max": 50084.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999944.0,
"min": 49673.0,
"max": 1999944.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999944.0,
"min": 49673.0,
"max": 1999944.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.459555149078369,
"min": 0.0961952731013298,
"max": 2.4815495014190674,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1517.5455322265625,
"min": 12.601580619812012,
"max": 1563.441650390625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.835379718768152,
"min": 1.7386249813414711,
"max": 3.984614529163857,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2366.42928647995,
"min": 227.75987255573273,
"max": 2487.8929418325424,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.835379718768152,
"min": 1.7386249813414711,
"max": 3.984614529163857,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2366.42928647995,
"min": 227.75987255573273,
"max": 2487.8929418325424,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017050388542379048,
"min": 0.013506033097352581,
"max": 0.019944971289563303,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05115116562713714,
"min": 0.027012066194705163,
"max": 0.055204038964196414,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05677956069509188,
"min": 0.021835044926653308,
"max": 0.061456344462931155,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17033868208527564,
"min": 0.043670089853306615,
"max": 0.17979501423736413,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5648988117333247e-06,
"min": 3.5648988117333247e-06,
"max": 0.0002953680015439999,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0694696435199974e-05,
"min": 1.0694696435199974e-05,
"max": 0.0008440095186634999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10118826666666668,
"min": 0.10118826666666668,
"max": 0.19845599999999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3035648,
"min": 0.20754584999999998,
"max": 0.5813365,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.92945066666665e-05,
"min": 6.92945066666665e-05,
"max": 0.0049229544,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002078835199999995,
"min": 0.0002078835199999995,
"max": 0.014068691349999999,
"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": "1733845827",
"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": "1733848380"
},
"total": 2553.148563834,
"count": 1,
"self": 0.47555704499973217,
"children": {
"run_training.setup": {
"total": 0.06015390500010653,
"count": 1,
"self": 0.06015390500010653
},
"TrainerController.start_learning": {
"total": 2552.612852884,
"count": 1,
"self": 4.554725237958792,
"children": {
"TrainerController._reset_env": {
"total": 6.2912166199998865,
"count": 1,
"self": 6.2912166199998865
},
"TrainerController.advance": {
"total": 2541.645177980042,
"count": 232924,
"self": 4.821728712118329,
"children": {
"env_step": {
"total": 1989.8933316419516,
"count": 232924,
"self": 1567.6139288361,
"children": {
"SubprocessEnvManager._take_step": {
"total": 419.4412265149349,
"count": 232924,
"self": 15.944597521868218,
"children": {
"TorchPolicy.evaluate": {
"total": 403.4966289930667,
"count": 222888,
"self": 403.4966289930667
}
}
},
"workers": {
"total": 2.8381762909166355,
"count": 232924,
"self": 0.0,
"children": {
"worker_root": {
"total": 2545.3728782339517,
"count": 232924,
"is_parallel": true,
"self": 1267.9473243249458,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008472310000797734,
"count": 1,
"is_parallel": true,
"self": 0.00021157799983484438,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000635653000244929,
"count": 2,
"is_parallel": true,
"self": 0.000635653000244929
}
}
},
"UnityEnvironment.step": {
"total": 0.030829359999870576,
"count": 1,
"is_parallel": true,
"self": 0.0004979629998160817,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021677999984603957,
"count": 1,
"is_parallel": true,
"self": 0.00021677999984603957
},
"communicator.exchange": {
"total": 0.029246254000099725,
"count": 1,
"is_parallel": true,
"self": 0.029246254000099725
},
"steps_from_proto": {
"total": 0.0008683630001087295,
"count": 1,
"is_parallel": true,
"self": 0.00022644500018031977,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006419179999284097,
"count": 2,
"is_parallel": true,
"self": 0.0006419179999284097
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1277.4255539090059,
"count": 232923,
"is_parallel": true,
"self": 38.92095742879087,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.88452327606751,
"count": 232923,
"is_parallel": true,
"self": 83.88452327606751
},
"communicator.exchange": {
"total": 1062.8397445770402,
"count": 232923,
"is_parallel": true,
"self": 1062.8397445770402
},
"steps_from_proto": {
"total": 91.78032862710734,
"count": 232923,
"is_parallel": true,
"self": 32.604591629042034,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.175736998065304,
"count": 465846,
"is_parallel": true,
"self": 59.175736998065304
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 546.9301176259719,
"count": 232924,
"self": 6.4878698418644944,
"children": {
"process_trajectory": {
"total": 178.06501825811097,
"count": 232924,
"self": 176.5585147671111,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5065034909998758,
"count": 10,
"self": 1.5065034909998758
}
}
},
"_update_policy": {
"total": 362.3772295259964,
"count": 97,
"self": 293.03636241601794,
"children": {
"TorchPPOOptimizer.update": {
"total": 69.34086710997849,
"count": 2910,
"self": 69.34086710997849
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0619996828609146e-06,
"count": 1,
"self": 1.0619996828609146e-06
},
"TrainerController._save_models": {
"total": 0.12173198399977991,
"count": 1,
"self": 0.0022560049992534914,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11947597900052642,
"count": 1,
"self": 0.11947597900052642
}
}
}
}
}
}
}