ppo-Huggy / run_logs /timers.json
jaredoong's picture
Huggy
2641997
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4053897857666016,
"min": 1.4053897857666016,
"max": 1.4295499324798584,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71746.5546875,
"min": 69011.34375,
"max": 76935.875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 100.34279918864097,
"min": 85.78298611111111,
"max": 387.93798449612405,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49469.0,
"min": 48909.0,
"max": 50072.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999955.0,
"min": 49644.0,
"max": 1999955.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999955.0,
"min": 49644.0,
"max": 1999955.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4181509017944336,
"min": 0.19685962796211243,
"max": 2.483394145965576,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1192.1484375,
"min": 25.19803237915039,
"max": 1410.56787109375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.707850577623317,
"min": 2.034335750620812,
"max": 3.9281788307806136,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1827.9703347682953,
"min": 260.39497607946396,
"max": 2231.2055758833885,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.707850577623317,
"min": 2.034335750620812,
"max": 3.9281788307806136,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1827.9703347682953,
"min": 260.39497607946396,
"max": 2231.2055758833885,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01983552039277533,
"min": 0.012304112830800781,
"max": 0.020674083361680258,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.059506561178325985,
"min": 0.024608225661601563,
"max": 0.062022250085040774,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05196976669960552,
"min": 0.02069048093010982,
"max": 0.06300986874848605,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15590930009881657,
"min": 0.042610075697302824,
"max": 0.1797385955850283,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.2361489213166554e-06,
"min": 3.2361489213166554e-06,
"max": 0.00029536950154350006,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.708446763949967e-06,
"min": 9.708446763949967e-06,
"max": 0.0008439154686948498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10107868333333336,
"min": 0.10107868333333336,
"max": 0.19845650000000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3032360500000001,
"min": 0.2073022,
"max": 0.5813051500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.382629833333318e-05,
"min": 6.382629833333318e-05,
"max": 0.00492297935,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019147889499999954,
"min": 0.00019147889499999954,
"max": 0.014067126985000001,
"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": "1692624393",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=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": "1692626836"
},
"total": 2442.152259289,
"count": 1,
"self": 0.437458425999921,
"children": {
"run_training.setup": {
"total": 0.04213848399996323,
"count": 1,
"self": 0.04213848399996323
},
"TrainerController.start_learning": {
"total": 2441.672662379,
"count": 1,
"self": 4.413517611031239,
"children": {
"TrainerController._reset_env": {
"total": 4.673592134000046,
"count": 1,
"self": 4.673592134000046
},
"TrainerController.advance": {
"total": 2432.4633493849688,
"count": 232192,
"self": 4.703217825924639,
"children": {
"env_step": {
"total": 1874.6346300820885,
"count": 232192,
"self": 1582.1624807300254,
"children": {
"SubprocessEnvManager._take_step": {
"total": 289.5354225629959,
"count": 232192,
"self": 16.394750871090935,
"children": {
"TorchPolicy.evaluate": {
"total": 273.14067169190497,
"count": 223054,
"self": 273.14067169190497
}
}
},
"workers": {
"total": 2.9367267890672224,
"count": 232192,
"self": 0.0,
"children": {
"worker_root": {
"total": 2434.0491194339174,
"count": 232192,
"is_parallel": true,
"self": 1143.3805058509467,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008615019999638207,
"count": 1,
"is_parallel": true,
"self": 0.00022972399995069281,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006317780000131279,
"count": 2,
"is_parallel": true,
"self": 0.0006317780000131279
}
}
},
"UnityEnvironment.step": {
"total": 0.07305786500000977,
"count": 1,
"is_parallel": true,
"self": 0.000349351000011211,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020840899998120221,
"count": 1,
"is_parallel": true,
"self": 0.00020840899998120221
},
"communicator.exchange": {
"total": 0.0716852599999811,
"count": 1,
"is_parallel": true,
"self": 0.0716852599999811
},
"steps_from_proto": {
"total": 0.0008148450000362573,
"count": 1,
"is_parallel": true,
"self": 0.0002092040000434281,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006056409999928292,
"count": 2,
"is_parallel": true,
"self": 0.0006056409999928292
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1290.6686135829707,
"count": 232191,
"is_parallel": true,
"self": 39.69133420402409,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.91173718800951,
"count": 232191,
"is_parallel": true,
"self": 81.91173718800951
},
"communicator.exchange": {
"total": 1071.501990165006,
"count": 232191,
"is_parallel": true,
"self": 1071.501990165006
},
"steps_from_proto": {
"total": 97.56355202593102,
"count": 232191,
"is_parallel": true,
"self": 34.169639407856096,
"children": {
"_process_rank_one_or_two_observation": {
"total": 63.39391261807492,
"count": 464382,
"is_parallel": true,
"self": 63.39391261807492
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 553.1255014769556,
"count": 232192,
"self": 6.639711878902062,
"children": {
"process_trajectory": {
"total": 137.47867412705415,
"count": 232192,
"self": 136.0683391300542,
"children": {
"RLTrainer._checkpoint": {
"total": 1.41033499699995,
"count": 10,
"self": 1.41033499699995
}
}
},
"_update_policy": {
"total": 409.00711547099945,
"count": 97,
"self": 348.1923903770002,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.81472509399924,
"count": 2910,
"self": 60.81472509399924
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1709998943842947e-06,
"count": 1,
"self": 1.1709998943842947e-06
},
"TrainerController._save_models": {
"total": 0.1222020780001003,
"count": 1,
"self": 0.0018598980004753685,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12034217999962493,
"count": 1,
"self": 0.12034217999962493
}
}
}
}
}
}
}