ppo-Huggy / run_logs /timers.json
zacdennis's picture
Huggy
4cb2407
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4081639051437378,
"min": 1.4081639051437378,
"max": 1.428421974182129,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70823.6015625,
"min": 68773.171875,
"max": 76789.0234375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 108.7956043956044,
"min": 83.7402376910017,
"max": 376.02255639097746,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49502.0,
"min": 48774.0,
"max": 50132.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999942.0,
"min": 49508.0,
"max": 1999942.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999942.0,
"min": 49508.0,
"max": 1999942.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.358515501022339,
"min": 0.15908180177211761,
"max": 2.483584403991699,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1073.12451171875,
"min": 20.998798370361328,
"max": 1397.088623046875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.570840296509502,
"min": 1.7679102565302993,
"max": 3.959548600637705,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1624.7323349118233,
"min": 233.3641538619995,
"max": 2220.7244632840157,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.570840296509502,
"min": 1.7679102565302993,
"max": 3.959548600637705,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1624.7323349118233,
"min": 233.3641538619995,
"max": 2220.7244632840157,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015450387835476753,
"min": 0.012678772700908466,
"max": 0.020510482813187993,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04635116350643026,
"min": 0.02760150395859758,
"max": 0.05932116262071456,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04947800098194016,
"min": 0.022275534179061654,
"max": 0.07775552740527523,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1484340029458205,
"min": 0.04455106835812331,
"max": 0.23326658221582572,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3977488674499964e-06,
"min": 3.3977488674499964e-06,
"max": 0.0002952513015829,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.019324660234999e-05,
"min": 1.019324660234999e-05,
"max": 0.0008439088686970498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10113254999999999,
"min": 0.10113254999999999,
"max": 0.1984171,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30339764999999996,
"min": 0.20741410000000007,
"max": 0.58130295,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.651424499999995e-05,
"min": 6.651424499999995e-05,
"max": 0.00492101329,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019954273499999986,
"min": 0.00019954273499999986,
"max": 0.014067017205000002,
"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": "1690225470",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"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": "1690228099"
},
"total": 2629.109456272,
"count": 1,
"self": 0.445308716999989,
"children": {
"run_training.setup": {
"total": 0.03718996700001753,
"count": 1,
"self": 0.03718996700001753
},
"TrainerController.start_learning": {
"total": 2628.626957588,
"count": 1,
"self": 5.444514010973762,
"children": {
"TrainerController._reset_env": {
"total": 6.987586899000007,
"count": 1,
"self": 6.987586899000007
},
"TrainerController.advance": {
"total": 2616.0394222150267,
"count": 231995,
"self": 5.139243604214698,
"children": {
"env_step": {
"total": 2039.3594706849342,
"count": 231995,
"self": 1724.6236636358358,
"children": {
"SubprocessEnvManager._take_step": {
"total": 311.269637006032,
"count": 231995,
"self": 18.126595411011294,
"children": {
"TorchPolicy.evaluate": {
"total": 293.1430415950207,
"count": 223054,
"self": 293.1430415950207
}
}
},
"workers": {
"total": 3.466170043066427,
"count": 231995,
"self": 0.0,
"children": {
"worker_root": {
"total": 2619.4926739569873,
"count": 231995,
"is_parallel": true,
"self": 1213.0706680339417,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008870160000924443,
"count": 1,
"is_parallel": true,
"self": 0.00022835500010387477,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006586609999885695,
"count": 2,
"is_parallel": true,
"self": 0.0006586609999885695
}
}
},
"UnityEnvironment.step": {
"total": 0.053199788000029,
"count": 1,
"is_parallel": true,
"self": 0.0003211000000646891,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002656589999787684,
"count": 1,
"is_parallel": true,
"self": 0.0002656589999787684
},
"communicator.exchange": {
"total": 0.051721607999979824,
"count": 1,
"is_parallel": true,
"self": 0.051721607999979824
},
"steps_from_proto": {
"total": 0.000891421000005721,
"count": 1,
"is_parallel": true,
"self": 0.00022212500005025504,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000669295999955466,
"count": 2,
"is_parallel": true,
"self": 0.000669295999955466
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1406.4220059230456,
"count": 231994,
"is_parallel": true,
"self": 42.539933784828236,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.01546545012661,
"count": 231994,
"is_parallel": true,
"self": 83.01546545012661
},
"communicator.exchange": {
"total": 1177.8546651601387,
"count": 231994,
"is_parallel": true,
"self": 1177.8546651601387
},
"steps_from_proto": {
"total": 103.0119415279521,
"count": 231994,
"is_parallel": true,
"self": 36.226623624007516,
"children": {
"_process_rank_one_or_two_observation": {
"total": 66.78531790394459,
"count": 463988,
"is_parallel": true,
"self": 66.78531790394459
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 571.5407079258778,
"count": 231995,
"self": 7.887448564924625,
"children": {
"process_trajectory": {
"total": 144.05742561695297,
"count": 231995,
"self": 142.56291911995345,
"children": {
"RLTrainer._checkpoint": {
"total": 1.49450649699952,
"count": 10,
"self": 1.49450649699952
}
}
},
"_update_policy": {
"total": 419.5958337440002,
"count": 97,
"self": 366.36427478099336,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.23155896300682,
"count": 2910,
"self": 53.23155896300682
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.7580000530870166e-06,
"count": 1,
"self": 1.7580000530870166e-06
},
"TrainerController._save_models": {
"total": 0.1554327049998392,
"count": 1,
"self": 0.0026387399998384353,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15279396500000075,
"count": 1,
"self": 0.15279396500000075
}
}
}
}
}
}
}