ppo-Huggy / run_logs /timers.json
JunghwanRo's picture
Huggy
a603f0a
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4079447984695435,
"min": 1.4079447984695435,
"max": 1.4339426755905151,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71418.0,
"min": 67917.2890625,
"max": 76894.3046875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 98.99600798403193,
"min": 90.41316270566728,
"max": 390.484375,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49597.0,
"min": 48969.0,
"max": 50122.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999375.0,
"min": 49951.0,
"max": 1999375.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999375.0,
"min": 49951.0,
"max": 1999375.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.407759189605713,
"min": 0.15897688269615173,
"max": 2.417886257171631,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1206.287353515625,
"min": 20.1900634765625,
"max": 1322.583740234375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6286974294694834,
"min": 1.703626365877512,
"max": 3.8523038324268386,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1817.9774121642113,
"min": 216.36054846644402,
"max": 2101.698570072651,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6286974294694834,
"min": 1.703626365877512,
"max": 3.8523038324268386,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1817.9774121642113,
"min": 216.36054846644402,
"max": 2101.698570072651,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015248169361439069,
"min": 0.013195793900134353,
"max": 0.019549984371406027,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.030496338722878137,
"min": 0.02801413285002733,
"max": 0.05783794375893195,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0527564941594998,
"min": 0.0199610591866076,
"max": 0.06296794731169938,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1055129883189996,
"min": 0.0399221183732152,
"max": 0.1711225983997186,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.515398494899994e-06,
"min": 4.515398494899994e-06,
"max": 0.000295346626551125,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.030796989799989e-06,
"min": 9.030796989799989e-06,
"max": 0.0008440975686341499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10150510000000001,
"min": 0.10150510000000001,
"max": 0.19844887500000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20301020000000003,
"min": 0.20301020000000003,
"max": 0.5813658499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.51044899999999e-05,
"min": 8.51044899999999e-05,
"max": 0.0049225988625000005,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001702089799999998,
"min": 0.0001702089799999998,
"max": 0.014070155915000002,
"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": "1698413984",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1698416339"
},
"total": 2354.304562832,
"count": 1,
"self": 0.4415858520001166,
"children": {
"run_training.setup": {
"total": 0.042464684000151465,
"count": 1,
"self": 0.042464684000151465
},
"TrainerController.start_learning": {
"total": 2353.820512296,
"count": 1,
"self": 4.205693877007889,
"children": {
"TrainerController._reset_env": {
"total": 8.604598855999939,
"count": 1,
"self": 8.604598855999939
},
"TrainerController.advance": {
"total": 2340.9126338219917,
"count": 231672,
"self": 4.486001837211461,
"children": {
"env_step": {
"total": 1867.6973058158048,
"count": 231672,
"self": 1532.2999036759063,
"children": {
"SubprocessEnvManager._take_step": {
"total": 332.65393628497236,
"count": 231672,
"self": 16.698740123978496,
"children": {
"TorchPolicy.evaluate": {
"total": 315.95519616099386,
"count": 223020,
"self": 315.95519616099386
}
}
},
"workers": {
"total": 2.7434658549261712,
"count": 231672,
"self": 0.0,
"children": {
"worker_root": {
"total": 2346.1588453450445,
"count": 231672,
"is_parallel": true,
"self": 1099.1305473600569,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000831715999993321,
"count": 1,
"is_parallel": true,
"self": 0.00022960499995861028,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006021110000347107,
"count": 2,
"is_parallel": true,
"self": 0.0006021110000347107
}
}
},
"UnityEnvironment.step": {
"total": 0.03103272999987894,
"count": 1,
"is_parallel": true,
"self": 0.0002985829996760003,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020690399992417952,
"count": 1,
"is_parallel": true,
"self": 0.00020690399992417952
},
"communicator.exchange": {
"total": 0.029841069000212883,
"count": 1,
"is_parallel": true,
"self": 0.029841069000212883
},
"steps_from_proto": {
"total": 0.0006861740000658756,
"count": 1,
"is_parallel": true,
"self": 0.00018396899986328208,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005022050002025935,
"count": 2,
"is_parallel": true,
"self": 0.0005022050002025935
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1247.0282979849876,
"count": 231671,
"is_parallel": true,
"self": 39.11622547300408,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.8089579229536,
"count": 231671,
"is_parallel": true,
"self": 82.8089579229536
},
"communicator.exchange": {
"total": 1036.2646661720514,
"count": 231671,
"is_parallel": true,
"self": 1036.2646661720514
},
"steps_from_proto": {
"total": 88.83844841697851,
"count": 231671,
"is_parallel": true,
"self": 32.98556088191344,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.852887535065065,
"count": 463342,
"is_parallel": true,
"self": 55.852887535065065
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 468.7293261689756,
"count": 231672,
"self": 6.652529645063169,
"children": {
"process_trajectory": {
"total": 145.22323446291057,
"count": 231672,
"self": 144.0202925159108,
"children": {
"RLTrainer._checkpoint": {
"total": 1.202941946999772,
"count": 10,
"self": 1.202941946999772
}
}
},
"_update_policy": {
"total": 316.85356206100187,
"count": 96,
"self": 256.3745293689972,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.479032692004694,
"count": 2880,
"self": 60.479032692004694
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.860000318440143e-07,
"count": 1,
"self": 9.860000318440143e-07
},
"TrainerController._save_models": {
"total": 0.09758475500029817,
"count": 1,
"self": 0.0018252160002703022,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09575953900002787,
"count": 1,
"self": 0.09575953900002787
}
}
}
}
}
}
}