ppo-Huggy / run_logs /timers.json
sam133's picture
Huggy
743ec85
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.404543399810791,
"min": 1.404543399810791,
"max": 1.4278950691223145,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71555.8671875,
"min": 67919.953125,
"max": 77244.3046875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 85.56920415224913,
"min": 81.38056013179572,
"max": 402.5,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49459.0,
"min": 49160.0,
"max": 50219.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999988.0,
"min": 49874.0,
"max": 1999988.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999988.0,
"min": 49874.0,
"max": 1999988.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.426701545715332,
"min": 0.061537306755781174,
"max": 2.5073742866516113,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1402.633544921875,
"min": 7.569088935852051,
"max": 1458.395263671875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7445409659902116,
"min": 1.7818361179130833,
"max": 3.956689861450812,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2164.3446783423424,
"min": 219.16584250330925,
"max": 2292.638631105423,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7445409659902116,
"min": 1.7818361179130833,
"max": 3.956689861450812,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2164.3446783423424,
"min": 219.16584250330925,
"max": 2292.638631105423,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017527782936748632,
"min": 0.014575744253913095,
"max": 0.021757579064554496,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0525833488102459,
"min": 0.02927444480689398,
"max": 0.05641414194251411,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05537765940858258,
"min": 0.02149428597961863,
"max": 0.05962520912289619,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16613297822574774,
"min": 0.04298857195923726,
"max": 0.17180900325377782,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.811898729399999e-06,
"min": 3.811898729399999e-06,
"max": 0.000295350526549825,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1435696188199996e-05,
"min": 1.1435696188199996e-05,
"max": 0.0008443101185632998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10127060000000003,
"min": 0.10127060000000003,
"max": 0.198450175,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3038118000000001,
"min": 0.2076677,
"max": 0.5814366999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.340294e-05,
"min": 7.340294e-05,
"max": 0.004922663732500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022020882,
"min": 0.00022020882,
"max": 0.01407369133,
"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": "1671134777",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \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_1 --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": "1671137036"
},
"total": 2259.1690343489995,
"count": 1,
"self": 0.44527066699993156,
"children": {
"run_training.setup": {
"total": 0.10670225099966046,
"count": 1,
"self": 0.10670225099966046
},
"TrainerController.start_learning": {
"total": 2258.617061431,
"count": 1,
"self": 3.9605715219991,
"children": {
"TrainerController._reset_env": {
"total": 11.509993202999794,
"count": 1,
"self": 11.509993202999794
},
"TrainerController.advance": {
"total": 2243.025850184001,
"count": 232728,
"self": 4.26766530107534,
"children": {
"env_step": {
"total": 1771.5139365959772,
"count": 232728,
"self": 1484.5858898530114,
"children": {
"SubprocessEnvManager._take_step": {
"total": 284.23544932095183,
"count": 232728,
"self": 14.633224437064655,
"children": {
"TorchPolicy.evaluate": {
"total": 269.6022248838872,
"count": 223084,
"self": 67.62565564379929,
"children": {
"TorchPolicy.sample_actions": {
"total": 201.97656924008788,
"count": 223084,
"self": 201.97656924008788
}
}
}
}
},
"workers": {
"total": 2.6925974220139324,
"count": 232728,
"self": 0.0,
"children": {
"worker_root": {
"total": 2250.6009758532964,
"count": 232728,
"is_parallel": true,
"self": 1033.7467740643847,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002099507999901107,
"count": 1,
"is_parallel": true,
"self": 0.00033020399996530614,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017693039999358007,
"count": 2,
"is_parallel": true,
"self": 0.0017693039999358007
}
}
},
"UnityEnvironment.step": {
"total": 0.026465450000159763,
"count": 1,
"is_parallel": true,
"self": 0.00027045699971495196,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002389960000073188,
"count": 1,
"is_parallel": true,
"self": 0.0002389960000073188
},
"communicator.exchange": {
"total": 0.025246221000088553,
"count": 1,
"is_parallel": true,
"self": 0.025246221000088553
},
"steps_from_proto": {
"total": 0.0007097760003489384,
"count": 1,
"is_parallel": true,
"self": 0.0002408540003671078,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004689219999818306,
"count": 2,
"is_parallel": true,
"self": 0.0004689219999818306
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1216.8542017889117,
"count": 232727,
"is_parallel": true,
"self": 35.09994004256896,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.35490335312352,
"count": 232727,
"is_parallel": true,
"self": 78.35490335312352
},
"communicator.exchange": {
"total": 1007.5012621281121,
"count": 232727,
"is_parallel": true,
"self": 1007.5012621281121
},
"steps_from_proto": {
"total": 95.89809626510714,
"count": 232727,
"is_parallel": true,
"self": 41.245613794083056,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.652482471024086,
"count": 465454,
"is_parallel": true,
"self": 54.652482471024086
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 467.2442482869483,
"count": 232728,
"self": 6.063702458825901,
"children": {
"process_trajectory": {
"total": 152.6610444461253,
"count": 232728,
"self": 151.46532072612536,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1957237199999327,
"count": 10,
"self": 1.1957237199999327
}
}
},
"_update_policy": {
"total": 308.5195013819971,
"count": 97,
"self": 255.32169174999808,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.19780963199901,
"count": 2910,
"self": 53.19780963199901
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.449997039861046e-07,
"count": 1,
"self": 8.449997039861046e-07
},
"TrainerController._save_models": {
"total": 0.12064567700053885,
"count": 1,
"self": 0.0021726670011048554,
"children": {
"RLTrainer._checkpoint": {
"total": 0.118473009999434,
"count": 1,
"self": 0.118473009999434
}
}
}
}
}
}
}