ppo-Huggy / run_logs /timers.json
mythrex's picture
Huggy
4542287
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4052010774612427,
"min": 1.4052010774612427,
"max": 1.4284987449645996,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71444.640625,
"min": 68955.140625,
"max": 75710.765625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 81.75331125827815,
"min": 77.71293375394322,
"max": 386.39230769230767,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49379.0,
"min": 49031.0,
"max": 50231.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999960.0,
"min": 49824.0,
"max": 1999960.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999960.0,
"min": 49824.0,
"max": 1999960.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.453012228012085,
"min": 0.13314975798130035,
"max": 2.5260684490203857,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1481.619384765625,
"min": 17.176319122314453,
"max": 1540.1396484375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8315181938425593,
"min": 1.8249669677989429,
"max": 4.032144339427643,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2314.236989080906,
"min": 235.4207388460636,
"max": 2452.0424534082413,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8315181938425593,
"min": 1.8249669677989429,
"max": 4.032144339427643,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2314.236989080906,
"min": 235.4207388460636,
"max": 2452.0424534082413,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01886242330333011,
"min": 0.012939753369331205,
"max": 0.019587256972833228,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.056587269909990336,
"min": 0.02587950673866241,
"max": 0.056587269909990336,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.053134475731187396,
"min": 0.02183669131870071,
"max": 0.05927323897679647,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15940342719356218,
"min": 0.04367338263740142,
"max": 0.17732900579770405,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5608488130833343e-06,
"min": 3.5608488130833343e-06,
"max": 0.0002952642015785999,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0682546439250003e-05,
"min": 1.0682546439250003e-05,
"max": 0.0008440146186618001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10118691666666667,
"min": 0.10118691666666667,
"max": 0.1984214,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30356075,
"min": 0.20749869999999998,
"max": 0.5813381999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.922714166666669e-05,
"min": 6.922714166666669e-05,
"max": 0.00492122786,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020768142500000004,
"min": 0.00020768142500000004,
"max": 0.014068776179999997,
"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": "1693307893",
"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": "1693310330"
},
"total": 2436.6717765639996,
"count": 1,
"self": 0.44145309199984695,
"children": {
"run_training.setup": {
"total": 0.07601616700003433,
"count": 1,
"self": 0.07601616700003433
},
"TrainerController.start_learning": {
"total": 2436.1543073049997,
"count": 1,
"self": 4.361621583929264,
"children": {
"TrainerController._reset_env": {
"total": 4.650755879000144,
"count": 1,
"self": 4.650755879000144
},
"TrainerController.advance": {
"total": 2427.0201070330704,
"count": 232777,
"self": 4.506887232181725,
"children": {
"env_step": {
"total": 1867.6239202998981,
"count": 232777,
"self": 1578.172693893952,
"children": {
"SubprocessEnvManager._take_step": {
"total": 286.6053089019822,
"count": 232777,
"self": 16.642947900123772,
"children": {
"TorchPolicy.evaluate": {
"total": 269.9623610018584,
"count": 222978,
"self": 269.9623610018584
}
}
},
"workers": {
"total": 2.8459175039638467,
"count": 232777,
"self": 0.0,
"children": {
"worker_root": {
"total": 2428.8528349819803,
"count": 232777,
"is_parallel": true,
"self": 1138.5057885789242,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010807440000917268,
"count": 1,
"is_parallel": true,
"self": 0.0003264950003085687,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007542489997831581,
"count": 2,
"is_parallel": true,
"self": 0.0007542489997831581
}
}
},
"UnityEnvironment.step": {
"total": 0.029297852999889074,
"count": 1,
"is_parallel": true,
"self": 0.0003122740001799684,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020688599988716305,
"count": 1,
"is_parallel": true,
"self": 0.00020688599988716305
},
"communicator.exchange": {
"total": 0.028047742999888214,
"count": 1,
"is_parallel": true,
"self": 0.028047742999888214
},
"steps_from_proto": {
"total": 0.0007309499999337277,
"count": 1,
"is_parallel": true,
"self": 0.00020007199987048807,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005308780000632396,
"count": 2,
"is_parallel": true,
"self": 0.0005308780000632396
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1290.347046403056,
"count": 232776,
"is_parallel": true,
"self": 39.403999618108855,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.76993815492688,
"count": 232776,
"is_parallel": true,
"self": 80.76993815492688
},
"communicator.exchange": {
"total": 1072.3127426619249,
"count": 232776,
"is_parallel": true,
"self": 1072.3127426619249
},
"steps_from_proto": {
"total": 97.8603659680955,
"count": 232776,
"is_parallel": true,
"self": 35.172426588152575,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.68793937994292,
"count": 465552,
"is_parallel": true,
"self": 62.68793937994292
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 554.8892995009903,
"count": 232777,
"self": 6.476626041945337,
"children": {
"process_trajectory": {
"total": 141.18820688704386,
"count": 232777,
"self": 139.50176648504475,
"children": {
"RLTrainer._checkpoint": {
"total": 1.686440401999107,
"count": 10,
"self": 1.686440401999107
}
}
},
"_update_policy": {
"total": 407.2244665720011,
"count": 97,
"self": 346.521445705009,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.70302086699212,
"count": 2910,
"self": 60.70302086699212
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.479999789618887e-07,
"count": 1,
"self": 9.479999789618887e-07
},
"TrainerController._save_models": {
"total": 0.12182186100017134,
"count": 1,
"self": 0.001973436000298534,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1198484249998728,
"count": 1,
"self": 0.1198484249998728
}
}
}
}
}
}
}