ppo-Huggy / run_logs /timers.json
zbenmo's picture
Huggy
bb11069
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4070043563842773,
"min": 1.4070043563842773,
"max": 1.4313724040985107,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69831.03125,
"min": 68811.1015625,
"max": 75604.40625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 97.08840864440079,
"min": 91.16206261510129,
"max": 434.0782608695652,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49418.0,
"min": 49008.0,
"max": 50060.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999864.0,
"min": 49284.0,
"max": 1999864.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999864.0,
"min": 49284.0,
"max": 1999864.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3104734420776367,
"min": 0.14982560276985168,
"max": 2.393707752227783,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1176.031005859375,
"min": 17.08011817932129,
"max": 1247.257080078125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5920239350884744,
"min": 1.9320995308328093,
"max": 3.9836859756773646,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1828.3401829600334,
"min": 220.25934651494026,
"max": 2011.0246612429619,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5920239350884744,
"min": 1.9320995308328093,
"max": 3.9836859756773646,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1828.3401829600334,
"min": 220.25934651494026,
"max": 2011.0246612429619,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.0158718422464416,
"min": 0.012858793873844358,
"max": 0.019483559935664137,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0476155267393248,
"min": 0.025717587747688717,
"max": 0.05845067980699241,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05218025371432305,
"min": 0.021427816618233918,
"max": 0.05443189702928066,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15654076114296914,
"min": 0.042855633236467836,
"max": 0.1620222806930542,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5560488146833296e-06,
"min": 3.5560488146833296e-06,
"max": 0.000295293376568875,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0668146444049988e-05,
"min": 1.0668146444049988e-05,
"max": 0.0008441839686053498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10118531666666669,
"min": 0.10118531666666669,
"max": 0.19843112499999999,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3035559500000001,
"min": 0.2075106,
"max": 0.58139465,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.914730166666662e-05,
"min": 6.914730166666662e-05,
"max": 0.0049217131375,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020744190499999985,
"min": 0.00020744190499999985,
"max": 0.014071593034999996,
"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": "1670510452",
"python_version": "3.8.15 (default, Oct 12 2022, 19:14:39) \n[GCC 7.5.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1670513102"
},
"total": 2650.1295689870003,
"count": 1,
"self": 0.45149043400033406,
"children": {
"run_training.setup": {
"total": 0.11419707200002449,
"count": 1,
"self": 0.11419707200002449
},
"TrainerController.start_learning": {
"total": 2649.563881481,
"count": 1,
"self": 5.271305883029072,
"children": {
"TrainerController._reset_env": {
"total": 9.628309725999998,
"count": 1,
"self": 9.628309725999998
},
"TrainerController.advance": {
"total": 2634.5392699169706,
"count": 231470,
"self": 5.614806846922875,
"children": {
"env_step": {
"total": 2113.52177070403,
"count": 231470,
"self": 1774.5585111909904,
"children": {
"SubprocessEnvManager._take_step": {
"total": 335.5897688609746,
"count": 231470,
"self": 18.01884956391052,
"children": {
"TorchPolicy.evaluate": {
"total": 317.57091929706405,
"count": 222908,
"self": 79.00317530500354,
"children": {
"TorchPolicy.sample_actions": {
"total": 238.5677439920605,
"count": 222908,
"self": 238.5677439920605
}
}
}
}
},
"workers": {
"total": 3.3734906520651293,
"count": 231470,
"self": 0.0,
"children": {
"worker_root": {
"total": 2639.9134274501125,
"count": 231470,
"is_parallel": true,
"self": 1192.6724602220515,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00177699500000017,
"count": 1,
"is_parallel": true,
"self": 0.0004125370001020201,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013644579998981499,
"count": 2,
"is_parallel": true,
"self": 0.0013644579998981499
}
}
},
"UnityEnvironment.step": {
"total": 0.030536300999983723,
"count": 1,
"is_parallel": true,
"self": 0.00031005699997876945,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002081160000670934,
"count": 1,
"is_parallel": true,
"self": 0.0002081160000670934
},
"communicator.exchange": {
"total": 0.029242178999993484,
"count": 1,
"is_parallel": true,
"self": 0.029242178999993484
},
"steps_from_proto": {
"total": 0.0007759489999443758,
"count": 1,
"is_parallel": true,
"self": 0.0002791389998719751,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004968100000724007,
"count": 2,
"is_parallel": true,
"self": 0.0004968100000724007
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1447.240967228061,
"count": 231469,
"is_parallel": true,
"self": 40.55180397190179,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 90.91846108409288,
"count": 231469,
"is_parallel": true,
"self": 90.91846108409288
},
"communicator.exchange": {
"total": 1205.131810860075,
"count": 231469,
"is_parallel": true,
"self": 1205.131810860075
},
"steps_from_proto": {
"total": 110.63889131199142,
"count": 231469,
"is_parallel": true,
"self": 47.52766672276425,
"children": {
"_process_rank_one_or_two_observation": {
"total": 63.11122458922716,
"count": 462938,
"is_parallel": true,
"self": 63.11122458922716
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 515.4026923660176,
"count": 231470,
"self": 8.132441647061114,
"children": {
"process_trajectory": {
"total": 172.62604176295702,
"count": 231470,
"self": 172.108274005957,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5177677570000014,
"count": 4,
"self": 0.5177677570000014
}
}
},
"_update_policy": {
"total": 334.6442089559995,
"count": 97,
"self": 277.51310337499365,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.13110558100584,
"count": 2910,
"self": 57.13110558100584
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.34000127017498e-07,
"count": 1,
"self": 9.34000127017498e-07
},
"TrainerController._save_models": {
"total": 0.12499502099990423,
"count": 1,
"self": 0.002099062000070262,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12289595899983397,
"count": 1,
"self": 0.12289595899983397
}
}
}
}
}
}
}