ppo-Huggy / run_logs /timers.json
edures's picture
Huggy
0870f00
raw
history blame
17.5 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4008057117462158,
"min": 1.4008057117462158,
"max": 1.4307318925857544,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71263.1875,
"min": 68896.3984375,
"max": 75881.9140625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 79.42190016103059,
"min": 77.41536050156739,
"max": 414.44628099173553,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49321.0,
"min": 48914.0,
"max": 50214.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999950.0,
"min": 49519.0,
"max": 1999950.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999950.0,
"min": 49519.0,
"max": 1999950.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.497849225997925,
"min": 0.014322114177048206,
"max": 2.5142455101013184,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1551.164306640625,
"min": 1.718653678894043,
"max": 1569.5677490234375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8472918946769887,
"min": 1.6579307767252127,
"max": 3.9892056084183207,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2389.16826659441,
"min": 198.95169320702553,
"max": 2481.51036965847,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8472918946769887,
"min": 1.6579307767252127,
"max": 3.9892056084183207,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2389.16826659441,
"min": 198.95169320702553,
"max": 2481.51036965847,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014213855464671118,
"min": 0.013931433216304058,
"max": 0.019170161157954783,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.042641566394013355,
"min": 0.027959753883381684,
"max": 0.057510483473864345,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05526612280971474,
"min": 0.02290771384206083,
"max": 0.06333133060899045,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16579836842914422,
"min": 0.0461216302588582,
"max": 0.18999399182697135,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6050487983499957e-06,
"min": 3.6050487983499957e-06,
"max": 0.0002952944265685249,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0815146395049987e-05,
"min": 1.0815146395049987e-05,
"max": 0.0008438001187333,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10120164999999998,
"min": 0.10120164999999998,
"max": 0.19843147500000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30360494999999993,
"min": 0.20753870000000005,
"max": 0.5812667,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.996233499999991e-05,
"min": 6.996233499999991e-05,
"max": 0.0049217306025000004,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020988700499999975,
"min": 0.00020988700499999975,
"max": 0.014065208330000002,
"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": "1688910329",
"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": "1688912957"
},
"total": 2627.462079198,
"count": 1,
"self": 0.43117608300008214,
"children": {
"run_training.setup": {
"total": 0.042533843999990495,
"count": 1,
"self": 0.042533843999990495
},
"TrainerController.start_learning": {
"total": 2626.988369271,
"count": 1,
"self": 4.680200711982707,
"children": {
"TrainerController._reset_env": {
"total": 4.1781582579999395,
"count": 1,
"self": 4.1781582579999395
},
"TrainerController.advance": {
"total": 2617.9938317310175,
"count": 232923,
"self": 4.8987015440161485,
"children": {
"env_step": {
"total": 2040.1632411390522,
"count": 232923,
"self": 1723.6379406510032,
"children": {
"SubprocessEnvManager._take_step": {
"total": 313.4040132090339,
"count": 232923,
"self": 18.379522741895812,
"children": {
"TorchPolicy.evaluate": {
"total": 295.0244904671381,
"count": 222962,
"self": 295.0244904671381
}
}
},
"workers": {
"total": 3.1212872790151778,
"count": 232923,
"self": 0.0,
"children": {
"worker_root": {
"total": 2618.524507989916,
"count": 232923,
"is_parallel": true,
"self": 1211.5705480039037,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010630709999759347,
"count": 1,
"is_parallel": true,
"self": 0.0002903370000240102,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007727339999519245,
"count": 2,
"is_parallel": true,
"self": 0.0007727339999519245
}
}
},
"UnityEnvironment.step": {
"total": 0.036750014999938685,
"count": 1,
"is_parallel": true,
"self": 0.000381714999889482,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002458360000900939,
"count": 1,
"is_parallel": true,
"self": 0.0002458360000900939
},
"communicator.exchange": {
"total": 0.03528340599996227,
"count": 1,
"is_parallel": true,
"self": 0.03528340599996227
},
"steps_from_proto": {
"total": 0.0008390579999968395,
"count": 1,
"is_parallel": true,
"self": 0.000241039999991699,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005980180000051405,
"count": 2,
"is_parallel": true,
"self": 0.0005980180000051405
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1406.9539599860123,
"count": 232922,
"is_parallel": true,
"self": 41.926956776864245,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 89.61321510117091,
"count": 232922,
"is_parallel": true,
"self": 89.61321510117091
},
"communicator.exchange": {
"total": 1170.9008466900177,
"count": 232922,
"is_parallel": true,
"self": 1170.9008466900177
},
"steps_from_proto": {
"total": 104.5129414179595,
"count": 232922,
"is_parallel": true,
"self": 39.23988771188533,
"children": {
"_process_rank_one_or_two_observation": {
"total": 65.27305370607417,
"count": 465844,
"is_parallel": true,
"self": 65.27305370607417
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 572.9318890479492,
"count": 232923,
"self": 7.115194129069209,
"children": {
"process_trajectory": {
"total": 151.7699030678807,
"count": 232923,
"self": 150.47110993288106,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2987931349996416,
"count": 10,
"self": 1.2987931349996416
}
}
},
"_update_policy": {
"total": 414.0467918509993,
"count": 97,
"self": 352.26625323200244,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.78053861899684,
"count": 2910,
"self": 61.78053861899684
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.225999767484609e-06,
"count": 1,
"self": 1.225999767484609e-06
},
"TrainerController._save_models": {
"total": 0.13617734399986148,
"count": 1,
"self": 0.001823033000164287,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1343543109996972,
"count": 1,
"self": 0.1343543109996972
}
}
}
}
}
}
}