ppo-Huggy / run_logs /timers.json
HellsCreature's picture
Huggy
0b76448 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.405005931854248,
"min": 1.405005931854248,
"max": 1.4263216257095337,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71016.0234375,
"min": 66023.828125,
"max": 78459.921875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 79.14423076923077,
"min": 79.06487341772151,
"max": 434.6,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49386.0,
"min": 48723.0,
"max": 50266.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999922.0,
"min": 49681.0,
"max": 1999922.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999922.0,
"min": 49681.0,
"max": 1999922.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4805476665496826,
"min": 0.05684151127934456,
"max": 2.5248899459838867,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1547.86181640625,
"min": 6.4799323081970215,
"max": 1547.86181640625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7999223657907586,
"min": 1.9112243423597854,
"max": 4.042667640243322,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2371.1515562534332,
"min": 217.87957502901554,
"max": 2388.8964752554893,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7999223657907586,
"min": 1.9112243423597854,
"max": 4.042667640243322,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2371.1515562534332,
"min": 217.87957502901554,
"max": 2388.8964752554893,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01543372108313229,
"min": 0.01349670224590227,
"max": 0.020799967853236012,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04630116324939687,
"min": 0.02699340449180454,
"max": 0.058431782506522714,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05906954109668731,
"min": 0.02102249873181184,
"max": 0.06229535359889269,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17720862329006193,
"min": 0.04204499746362368,
"max": 0.17833154785136382,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4934988355333354e-06,
"min": 3.4934988355333354e-06,
"max": 0.0002953377015541,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0480496506600006e-05,
"min": 1.0480496506600006e-05,
"max": 0.0008441677686107498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10116446666666667,
"min": 0.10116446666666667,
"max": 0.19844590000000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3034934,
"min": 0.20746395000000006,
"max": 0.58138925,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.810688666666673e-05,
"min": 6.810688666666673e-05,
"max": 0.004922450409999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020432066000000018,
"min": 0.00020432066000000018,
"max": 0.014071323575,
"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": "1775319491",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1775324058"
},
"total": 4566.802021547001,
"count": 1,
"self": 1.7076093120012956,
"children": {
"run_training.setup": {
"total": 0.03326064300017606,
"count": 1,
"self": 0.03326064300017606
},
"TrainerController.start_learning": {
"total": 4565.061151591999,
"count": 1,
"self": 7.778489825886936,
"children": {
"TrainerController._reset_env": {
"total": 3.412156143000175,
"count": 1,
"self": 3.412156143000175
},
"TrainerController.advance": {
"total": 4553.720171484114,
"count": 232641,
"self": 7.944058931618201,
"children": {
"env_step": {
"total": 3088.9355124970607,
"count": 232641,
"self": 2627.737857952503,
"children": {
"SubprocessEnvManager._take_step": {
"total": 456.0585929994977,
"count": 232641,
"self": 27.9070279371208,
"children": {
"TorchPolicy.evaluate": {
"total": 428.1515650623769,
"count": 222981,
"self": 428.1515650623769
}
}
},
"workers": {
"total": 5.139061545060031,
"count": 232641,
"self": 0.0,
"children": {
"worker_root": {
"total": 4542.519983906968,
"count": 232641,
"is_parallel": true,
"self": 2447.337797824559,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008736800009501167,
"count": 1,
"is_parallel": true,
"self": 0.0002450720003253082,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006286080006248085,
"count": 2,
"is_parallel": true,
"self": 0.0006286080006248085
}
}
},
"UnityEnvironment.step": {
"total": 0.03435929499937629,
"count": 1,
"is_parallel": true,
"self": 0.00038820099871372804,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002232750011899043,
"count": 1,
"is_parallel": true,
"self": 0.0002232750011899043
},
"communicator.exchange": {
"total": 0.03294942600041395,
"count": 1,
"is_parallel": true,
"self": 0.03294942600041395
},
"steps_from_proto": {
"total": 0.0007983929990587058,
"count": 1,
"is_parallel": true,
"self": 0.0002162809978472069,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005821120012114989,
"count": 2,
"is_parallel": true,
"self": 0.0005821120012114989
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2095.1821860824093,
"count": 232640,
"is_parallel": true,
"self": 62.34558957979425,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 112.19080371913333,
"count": 232640,
"is_parallel": true,
"self": 112.19080371913333
},
"communicator.exchange": {
"total": 1785.3339640135637,
"count": 232640,
"is_parallel": true,
"self": 1785.3339640135637
},
"steps_from_proto": {
"total": 135.31182876991807,
"count": 232640,
"is_parallel": true,
"self": 44.180447293936595,
"children": {
"_process_rank_one_or_two_observation": {
"total": 91.13138147598147,
"count": 465280,
"is_parallel": true,
"self": 91.13138147598147
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1456.840600055435,
"count": 232641,
"self": 12.111325549789399,
"children": {
"process_trajectory": {
"total": 234.63921871964703,
"count": 232641,
"self": 233.2922486126481,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3469701069989242,
"count": 10,
"self": 1.3469701069989242
}
}
},
"_update_policy": {
"total": 1210.0900557859986,
"count": 97,
"self": 312.0415895900205,
"children": {
"TorchPPOOptimizer.update": {
"total": 898.0484661959781,
"count": 2910,
"self": 898.0484661959781
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.562999386806041e-06,
"count": 1,
"self": 1.562999386806041e-06
},
"TrainerController._save_models": {
"total": 0.15033257599861827,
"count": 1,
"self": 0.0029366489998210454,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14739592699879722,
"count": 1,
"self": 0.14739592699879722
}
}
}
}
}
}
}