ppo-Huggy / run_logs /timers.json
BreakSilence's picture
Huggy
1ea3de2 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3999348878860474,
"min": 1.3999348878860474,
"max": 1.4277690649032593,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69593.5625,
"min": 68353.8359375,
"max": 77265.125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 114.16359447004608,
"min": 109.51901565995526,
"max": 398.6984126984127,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49547.0,
"min": 48955.0,
"max": 50247.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999782.0,
"min": 49801.0,
"max": 1999782.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999782.0,
"min": 49801.0,
"max": 1999782.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2670583724975586,
"min": -0.034622758626937866,
"max": 2.353341817855835,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 983.9033203125,
"min": -4.327844619750977,
"max": 1037.82373046875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.4431548273783124,
"min": 1.7988640224933625,
"max": 3.708330342750899,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1494.3291950821877,
"min": 224.8580028116703,
"max": 1592.2614362835884,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.4431548273783124,
"min": 1.7988640224933625,
"max": 3.708330342750899,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1494.3291950821877,
"min": 224.8580028116703,
"max": 1592.2614362835884,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01752248662620938,
"min": 0.012764374917242093,
"max": 0.019652867964274873,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03504497325241876,
"min": 0.025528749834484186,
"max": 0.05529443340201397,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04747647239516179,
"min": 0.022046675470968086,
"max": 0.05409220730264982,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09495294479032358,
"min": 0.04409335094193617,
"max": 0.16227662190794945,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.2246985918000125e-06,
"min": 4.2246985918000125e-06,
"max": 0.00029530357656547507,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.449397183600025e-06,
"min": 8.449397183600025e-06,
"max": 0.0008437471687509498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10140820000000003,
"min": 0.10140820000000003,
"max": 0.19843452500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20281640000000006,
"min": 0.20281640000000006,
"max": 0.58124905,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.026918000000022e-05,
"min": 8.026918000000022e-05,
"max": 0.0049218827975,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016053836000000043,
"min": 0.00016053836000000043,
"max": 0.014064327594999999,
"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": "1724608627",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1724611058"
},
"total": 2430.9909268090005,
"count": 1,
"self": 0.4890311240005758,
"children": {
"run_training.setup": {
"total": 0.06362858599982246,
"count": 1,
"self": 0.06362858599982246
},
"TrainerController.start_learning": {
"total": 2430.438267099,
"count": 1,
"self": 4.354525032951187,
"children": {
"TrainerController._reset_env": {
"total": 2.85535304799987,
"count": 1,
"self": 2.85535304799987
},
"TrainerController.advance": {
"total": 2423.099230307049,
"count": 230257,
"self": 4.686195404023692,
"children": {
"env_step": {
"total": 1923.9971967080105,
"count": 230257,
"self": 1584.2904861680984,
"children": {
"SubprocessEnvManager._take_step": {
"total": 336.8383880409624,
"count": 230257,
"self": 18.463162502970818,
"children": {
"TorchPolicy.evaluate": {
"total": 318.3752255379916,
"count": 222943,
"self": 318.3752255379916
}
}
},
"workers": {
"total": 2.8683224989497376,
"count": 230257,
"self": 0.0,
"children": {
"worker_root": {
"total": 2423.2816607420814,
"count": 230257,
"is_parallel": true,
"self": 1141.714353243154,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009407180000380322,
"count": 1,
"is_parallel": true,
"self": 0.00023336400022344606,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007073539998145861,
"count": 2,
"is_parallel": true,
"self": 0.0007073539998145861
}
}
},
"UnityEnvironment.step": {
"total": 0.029239323999945555,
"count": 1,
"is_parallel": true,
"self": 0.0003906730000835523,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002555859998665255,
"count": 1,
"is_parallel": true,
"self": 0.0002555859998665255
},
"communicator.exchange": {
"total": 0.027814968000029694,
"count": 1,
"is_parallel": true,
"self": 0.027814968000029694
},
"steps_from_proto": {
"total": 0.0007780969999657827,
"count": 1,
"is_parallel": true,
"self": 0.00022190200024851947,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005561949997172633,
"count": 2,
"is_parallel": true,
"self": 0.0005561949997172633
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1281.5673074989274,
"count": 230256,
"is_parallel": true,
"self": 38.551111068996306,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.7222148249898,
"count": 230256,
"is_parallel": true,
"self": 80.7222148249898
},
"communicator.exchange": {
"total": 1071.1363658350006,
"count": 230256,
"is_parallel": true,
"self": 1071.1363658350006
},
"steps_from_proto": {
"total": 91.15761576994078,
"count": 230256,
"is_parallel": true,
"self": 32.59550108997064,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.562114679970136,
"count": 460512,
"is_parallel": true,
"self": 58.562114679970136
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 494.41583819501466,
"count": 230257,
"self": 7.009437149074074,
"children": {
"process_trajectory": {
"total": 149.6202096249408,
"count": 230257,
"self": 148.26796417394007,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3522454510007265,
"count": 10,
"self": 1.3522454510007265
}
}
},
"_update_policy": {
"total": 337.7861914209998,
"count": 96,
"self": 273.43516297600354,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.35102844499625,
"count": 2880,
"self": 64.35102844499625
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.120000529743265e-07,
"count": 1,
"self": 8.120000529743265e-07
},
"TrainerController._save_models": {
"total": 0.1291578989998925,
"count": 1,
"self": 0.0018921169998975529,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12726578199999494,
"count": 1,
"self": 0.12726578199999494
}
}
}
}
}
}
}