ppo-Huggy / run_logs /timers.json
DarkRodry's picture
tutorial huggy model
8712396
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4030922651290894,
"min": 1.4030922651290894,
"max": 1.4256162643432617,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71686.7890625,
"min": 69236.6015625,
"max": 76694.15625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 73.36404160475483,
"min": 73.36404160475483,
"max": 389.953125,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49374.0,
"min": 49201.0,
"max": 49989.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999997.0,
"min": 49503.0,
"max": 1999997.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999997.0,
"min": 49503.0,
"max": 1999997.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.467633008956909,
"min": 0.08488917350769043,
"max": 2.547585964202881,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1660.717041015625,
"min": 10.780924797058105,
"max": 1660.717041015625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8737232709001823,
"min": 1.7510839400328988,
"max": 3.9669188137428004,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2607.0157613158226,
"min": 222.38766038417816,
"max": 2607.0157613158226,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8737232709001823,
"min": 1.7510839400328988,
"max": 3.9669188137428004,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2607.0157613158226,
"min": 222.38766038417816,
"max": 2607.0157613158226,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017553188084437153,
"min": 0.013739818821037867,
"max": 0.018993020708633897,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.052659564253311454,
"min": 0.027479637642075734,
"max": 0.05689361851254944,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05747892885572381,
"min": 0.02175907182196776,
"max": 0.06406351957056257,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17243678656717143,
"min": 0.04351814364393552,
"max": 0.19219055871168772,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.015548661516665e-06,
"min": 4.015548661516665e-06,
"max": 0.00029537422654192497,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.2046645984549995e-05,
"min": 1.2046645984549995e-05,
"max": 0.0008442672185775998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10133848333333334,
"min": 0.10133848333333334,
"max": 0.198458075,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30401545,
"min": 0.20780170000000003,
"max": 0.5814224,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.67903183333333e-05,
"min": 7.67903183333333e-05,
"max": 0.004923057942500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002303709549999999,
"min": 0.0002303709549999999,
"max": 0.014072977760000003,
"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": "1687538991",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"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": "1687541491"
},
"total": 2499.5892965810003,
"count": 1,
"self": 0.44301615200038214,
"children": {
"run_training.setup": {
"total": 0.06462037700021028,
"count": 1,
"self": 0.06462037700021028
},
"TrainerController.start_learning": {
"total": 2499.0816600519997,
"count": 1,
"self": 4.529608271674988,
"children": {
"TrainerController._reset_env": {
"total": 5.27320192399975,
"count": 1,
"self": 5.27320192399975
},
"TrainerController.advance": {
"total": 2489.1475479833252,
"count": 233223,
"self": 4.839210571816693,
"children": {
"env_step": {
"total": 1934.4172895947772,
"count": 233223,
"self": 1629.075013297756,
"children": {
"SubprocessEnvManager._take_step": {
"total": 302.42195447314543,
"count": 233223,
"self": 17.787022745994364,
"children": {
"TorchPolicy.evaluate": {
"total": 284.63493172715107,
"count": 222980,
"self": 284.63493172715107
}
}
},
"workers": {
"total": 2.920321823875838,
"count": 233223,
"self": 0.0,
"children": {
"worker_root": {
"total": 2491.174065913932,
"count": 233223,
"is_parallel": true,
"self": 1161.4519978288686,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001041567999891413,
"count": 1,
"is_parallel": true,
"self": 0.0002935649995379208,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007480030003534921,
"count": 2,
"is_parallel": true,
"self": 0.0007480030003534921
}
}
},
"UnityEnvironment.step": {
"total": 0.029146203999971476,
"count": 1,
"is_parallel": true,
"self": 0.0003473959995972109,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00024323600018760771,
"count": 1,
"is_parallel": true,
"self": 0.00024323600018760771
},
"communicator.exchange": {
"total": 0.027853439999944385,
"count": 1,
"is_parallel": true,
"self": 0.027853439999944385
},
"steps_from_proto": {
"total": 0.0007021320002422726,
"count": 1,
"is_parallel": true,
"self": 0.00019427400047788979,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005078579997643828,
"count": 2,
"is_parallel": true,
"self": 0.0005078579997643828
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1329.7220680850633,
"count": 233222,
"is_parallel": true,
"self": 41.27879200483176,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.09112988821198,
"count": 233222,
"is_parallel": true,
"self": 81.09112988821198
},
"communicator.exchange": {
"total": 1108.7419766059356,
"count": 233222,
"is_parallel": true,
"self": 1108.7419766059356
},
"steps_from_proto": {
"total": 98.61016958608388,
"count": 233222,
"is_parallel": true,
"self": 35.18438521270218,
"children": {
"_process_rank_one_or_two_observation": {
"total": 63.4257843733817,
"count": 466444,
"is_parallel": true,
"self": 63.4257843733817
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 549.8910478167313,
"count": 233223,
"self": 6.597570693834314,
"children": {
"process_trajectory": {
"total": 144.28472820389425,
"count": 233223,
"self": 142.93620211789494,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3485260859993105,
"count": 10,
"self": 1.3485260859993105
}
}
},
"_update_policy": {
"total": 399.00874891900276,
"count": 97,
"self": 338.0083694979994,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.000379421003345,
"count": 2910,
"self": 61.000379421003345
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1889997040270828e-06,
"count": 1,
"self": 1.1889997040270828e-06
},
"TrainerController._save_models": {
"total": 0.13130068400005257,
"count": 1,
"self": 0.002137403000233462,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1291632809998191,
"count": 1,
"self": 0.1291632809998191
}
}
}
}
}
}
}