ppo-Huggy / run_logs /timers.json
katk31's picture
Huggy
7200b98 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4069370031356812,
"min": 1.4069370031356812,
"max": 1.4316898584365845,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71113.6328125,
"min": 67790.5234375,
"max": 76774.4921875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 97.41176470588235,
"min": 95.7984496124031,
"max": 388.5891472868217,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49680.0,
"min": 49020.0,
"max": 50134.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999550.0,
"min": 49809.0,
"max": 1999550.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999550.0,
"min": 49809.0,
"max": 1999550.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.351179838180542,
"min": 0.11561359465122223,
"max": 2.389543056488037,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1201.452880859375,
"min": 14.798540115356445,
"max": 1211.725830078125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.771224362276305,
"min": 1.917414522729814,
"max": 3.857002747610277,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1927.0956491231918,
"min": 245.4290589094162,
"max": 1927.0956491231918,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.771224362276305,
"min": 1.917414522729814,
"max": 3.857002747610277,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1927.0956491231918,
"min": 245.4290589094162,
"max": 1927.0956491231918,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018326825785768757,
"min": 0.012377234479178392,
"max": 0.020801515355318163,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.054980477357306275,
"min": 0.024754468958356785,
"max": 0.05825757123529911,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.052708727162745266,
"min": 0.021979240607470273,
"max": 0.05948208390424649,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1581261814882358,
"min": 0.043958481214940545,
"max": 0.17651846148073674,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.178398940566678e-06,
"min": 3.178398940566678e-06,
"max": 0.00029532315155895,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.535196821700034e-06,
"min": 9.535196821700034e-06,
"max": 0.0008440881186373001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10105943333333334,
"min": 0.10105943333333334,
"max": 0.19844105,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3031783,
"min": 0.20729004999999995,
"max": 0.5813626999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.286572333333354e-05,
"min": 6.286572333333354e-05,
"max": 0.0049222083950000006,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001885971700000006,
"min": 0.0001885971700000006,
"max": 0.01406999873,
"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": "1715841367",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1715843734"
},
"total": 2366.938410359,
"count": 1,
"self": 0.4422098149998419,
"children": {
"run_training.setup": {
"total": 0.05309619800004839,
"count": 1,
"self": 0.05309619800004839
},
"TrainerController.start_learning": {
"total": 2366.443104346,
"count": 1,
"self": 4.175994253061617,
"children": {
"TrainerController._reset_env": {
"total": 2.9317692490000127,
"count": 1,
"self": 2.9317692490000127
},
"TrainerController.advance": {
"total": 2359.2192887329384,
"count": 231387,
"self": 4.65203020102399,
"children": {
"env_step": {
"total": 1870.141057839899,
"count": 231387,
"self": 1545.8527381937797,
"children": {
"SubprocessEnvManager._take_step": {
"total": 321.46381695005005,
"count": 231387,
"self": 17.88205776213681,
"children": {
"TorchPolicy.evaluate": {
"total": 303.58175918791324,
"count": 222970,
"self": 303.58175918791324
}
}
},
"workers": {
"total": 2.824502696069203,
"count": 231387,
"self": 0.0,
"children": {
"worker_root": {
"total": 2359.395924893959,
"count": 231387,
"is_parallel": true,
"self": 1114.8594662719815,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008967030000803788,
"count": 1,
"is_parallel": true,
"self": 0.00022244499996304512,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006742580001173337,
"count": 2,
"is_parallel": true,
"self": 0.0006742580001173337
}
}
},
"UnityEnvironment.step": {
"total": 0.03234658500002752,
"count": 1,
"is_parallel": true,
"self": 0.00040104499987592135,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018914700001460005,
"count": 1,
"is_parallel": true,
"self": 0.00018914700001460005
},
"communicator.exchange": {
"total": 0.03089818200010086,
"count": 1,
"is_parallel": true,
"self": 0.03089818200010086
},
"steps_from_proto": {
"total": 0.0008582110000361354,
"count": 1,
"is_parallel": true,
"self": 0.00024931899997682194,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006088920000593134,
"count": 2,
"is_parallel": true,
"self": 0.0006088920000593134
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1244.5364586219775,
"count": 231386,
"is_parallel": true,
"self": 38.40198755486881,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.61590397602788,
"count": 231386,
"is_parallel": true,
"self": 81.61590397602788
},
"communicator.exchange": {
"total": 1036.1776876860404,
"count": 231386,
"is_parallel": true,
"self": 1036.1776876860404
},
"steps_from_proto": {
"total": 88.3408794050406,
"count": 231386,
"is_parallel": true,
"self": 31.204914343095993,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.1359650619446,
"count": 462772,
"is_parallel": true,
"self": 57.1359650619446
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 484.4262006920152,
"count": 231387,
"self": 6.371128757066344,
"children": {
"process_trajectory": {
"total": 148.35114249694993,
"count": 231387,
"self": 147.1138965639508,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2372459329991443,
"count": 10,
"self": 1.2372459329991443
}
}
},
"_update_policy": {
"total": 329.7039294379989,
"count": 97,
"self": 265.75136612899496,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.95256330900395,
"count": 2910,
"self": 63.95256330900395
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.130000423989259e-07,
"count": 1,
"self": 8.130000423989259e-07
},
"TrainerController._save_models": {
"total": 0.11605129800000213,
"count": 1,
"self": 0.0022465490001195576,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11380474899988258,
"count": 1,
"self": 0.11380474899988258
}
}
}
}
}
}
}