ppo-Huggy / run_logs /timers.json
sugafree's picture
Huggy
f15535c
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4030297994613647,
"min": 1.4030297994613647,
"max": 1.4252352714538574,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69629.5625,
"min": 68202.0390625,
"max": 78011.640625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 103.31808731808732,
"min": 83.64516129032258,
"max": 378.02272727272725,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49696.0,
"min": 48968.0,
"max": 50006.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999458.0,
"min": 49299.0,
"max": 1999458.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999458.0,
"min": 49299.0,
"max": 1999458.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.390728712081909,
"min": 0.002951327245682478,
"max": 2.459357261657715,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1149.9405517578125,
"min": 0.3866238594055176,
"max": 1429.69873046875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6370017938703114,
"min": 1.7735662809537567,
"max": 3.928108692916918,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1749.3978628516197,
"min": 232.33718280494213,
"max": 2201.1481588482857,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6370017938703114,
"min": 1.7735662809537567,
"max": 3.928108692916918,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1749.3978628516197,
"min": 232.33718280494213,
"max": 2201.1481588482857,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01672118107445486,
"min": 0.0134627977553464,
"max": 0.02035787896068844,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05016354322336458,
"min": 0.0269255955106928,
"max": 0.05687262094579637,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04617120967143112,
"min": 0.023722480920453867,
"max": 0.05977843956400951,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.13851362901429334,
"min": 0.04744496184090773,
"max": 0.16957001735766727,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6717987761000015e-06,
"min": 3.6717987761000015e-06,
"max": 0.0002953362765545749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1015396328300005e-05,
"min": 1.1015396328300005e-05,
"max": 0.00084422026859325,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10122390000000002,
"min": 0.10122390000000002,
"max": 0.198445425,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30367170000000004,
"min": 0.20757460000000003,
"max": 0.5814067500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.107261000000002e-05,
"min": 7.107261000000002e-05,
"max": 0.0049224267075,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021321783000000005,
"min": 0.00021321783000000005,
"max": 0.014072196825000001,
"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": "1688284399",
"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": "1688286761"
},
"total": 2361.89126591,
"count": 1,
"self": 0.4357370800003082,
"children": {
"run_training.setup": {
"total": 0.04223014699999794,
"count": 1,
"self": 0.04223014699999794
},
"TrainerController.start_learning": {
"total": 2361.413298683,
"count": 1,
"self": 4.131426482945699,
"children": {
"TrainerController._reset_env": {
"total": 4.10326625700003,
"count": 1,
"self": 4.10326625700003
},
"TrainerController.advance": {
"total": 2353.0543438690543,
"count": 232250,
"self": 4.386574133008253,
"children": {
"env_step": {
"total": 1825.576041069975,
"count": 232250,
"self": 1534.2663465669273,
"children": {
"SubprocessEnvManager._take_step": {
"total": 288.54054277094855,
"count": 232250,
"self": 16.41376009798472,
"children": {
"TorchPolicy.evaluate": {
"total": 272.1267826729638,
"count": 222970,
"self": 272.1267826729638
}
}
},
"workers": {
"total": 2.7691517320992034,
"count": 232250,
"self": 0.0,
"children": {
"worker_root": {
"total": 2353.9327427279336,
"count": 232250,
"is_parallel": true,
"self": 1102.6644317509554,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000925687000005837,
"count": 1,
"is_parallel": true,
"self": 0.00023368399996570588,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006920030000401312,
"count": 2,
"is_parallel": true,
"self": 0.0006920030000401312
}
}
},
"UnityEnvironment.step": {
"total": 0.028404261999980918,
"count": 1,
"is_parallel": true,
"self": 0.00034533099994860095,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002394609999782915,
"count": 1,
"is_parallel": true,
"self": 0.0002394609999782915
},
"communicator.exchange": {
"total": 0.02709101800002145,
"count": 1,
"is_parallel": true,
"self": 0.02709101800002145
},
"steps_from_proto": {
"total": 0.0007284520000325756,
"count": 1,
"is_parallel": true,
"self": 0.00020739800004321296,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005210539999893626,
"count": 2,
"is_parallel": true,
"self": 0.0005210539999893626
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1251.2683109769782,
"count": 232249,
"is_parallel": true,
"self": 38.660044901959736,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 76.77659978311306,
"count": 232249,
"is_parallel": true,
"self": 76.77659978311306
},
"communicator.exchange": {
"total": 1042.1707901269283,
"count": 232249,
"is_parallel": true,
"self": 1042.1707901269283
},
"steps_from_proto": {
"total": 93.66087616497731,
"count": 232249,
"is_parallel": true,
"self": 32.89182770492312,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.769048460054194,
"count": 464498,
"is_parallel": true,
"self": 60.769048460054194
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 523.091728666071,
"count": 232250,
"self": 6.742764992023353,
"children": {
"process_trajectory": {
"total": 135.2631049160472,
"count": 232250,
"self": 133.95277041904666,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3103344970005537,
"count": 10,
"self": 1.3103344970005537
}
}
},
"_update_policy": {
"total": 381.0858587580005,
"count": 97,
"self": 321.2448157569964,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.841043001004095,
"count": 2910,
"self": 59.841043001004095
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4150000424706377e-06,
"count": 1,
"self": 1.4150000424706377e-06
},
"TrainerController._save_models": {
"total": 0.12426065899990135,
"count": 1,
"self": 0.0019123619999845687,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12234829699991678,
"count": 1,
"self": 0.12234829699991678
}
}
}
}
}
}
}