ppo-Huggy / run_logs /timers.json
mojtabak's picture
Huggy
131496b
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4035598039627075,
"min": 1.4035598039627075,
"max": 1.4321383237838745,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70607.4765625,
"min": 67112.2109375,
"max": 78636.0703125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 81.06896551724138,
"min": 78.19968304278922,
"max": 420.9495798319328,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49371.0,
"min": 49015.0,
"max": 50093.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999907.0,
"min": 49774.0,
"max": 1999907.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999907.0,
"min": 49774.0,
"max": 1999907.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.429989814758301,
"min": 0.1741056889295578,
"max": 2.524200439453125,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1479.86376953125,
"min": 20.544471740722656,
"max": 1542.1649169921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.827528145512924,
"min": 1.6526838270789486,
"max": 4.0089728878580635,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2330.9646406173706,
"min": 195.01669159531593,
"max": 2438.928957760334,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.827528145512924,
"min": 1.6526838270789486,
"max": 4.0089728878580635,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2330.9646406173706,
"min": 195.01669159531593,
"max": 2438.928957760334,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016806639880653368,
"min": 0.013356112829771722,
"max": 0.018820657141239077,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.050419919641960104,
"min": 0.027000492869410662,
"max": 0.056461971423717235,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06026248505545987,
"min": 0.021288969181478025,
"max": 0.06429752819240094,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18078745516637962,
"min": 0.04257793836295605,
"max": 0.1876900705198447,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.479598840166657e-06,
"min": 3.479598840166657e-06,
"max": 0.0002953518765493751,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.043879652049997e-05,
"min": 1.043879652049997e-05,
"max": 0.0008440002186666002,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10115983333333332,
"min": 0.10115983333333332,
"max": 0.198450625,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30347949999999996,
"min": 0.2074575500000001,
"max": 0.5813334000000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.787568333333318e-05,
"min": 6.787568333333318e-05,
"max": 0.004922686187500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020362704999999954,
"min": 0.00020362704999999954,
"max": 0.01406853666,
"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": "1690298258",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"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": "1690300780"
},
"total": 2521.8070929749997,
"count": 1,
"self": 0.44365933299968674,
"children": {
"run_training.setup": {
"total": 0.033166469999969195,
"count": 1,
"self": 0.033166469999969195
},
"TrainerController.start_learning": {
"total": 2521.330267172,
"count": 1,
"self": 4.576008284936961,
"children": {
"TrainerController._reset_env": {
"total": 6.390571144999967,
"count": 1,
"self": 6.390571144999967
},
"TrainerController.advance": {
"total": 2510.2415802890623,
"count": 232875,
"self": 4.785388546148624,
"children": {
"env_step": {
"total": 1935.396931720887,
"count": 232875,
"self": 1638.0716006218827,
"children": {
"SubprocessEnvManager._take_step": {
"total": 294.20674635398774,
"count": 232875,
"self": 17.209631372978492,
"children": {
"TorchPolicy.evaluate": {
"total": 276.99711498100925,
"count": 222950,
"self": 276.99711498100925
}
}
},
"workers": {
"total": 3.1185847450166193,
"count": 232875,
"self": 0.0,
"children": {
"worker_root": {
"total": 2513.337767725095,
"count": 232875,
"is_parallel": true,
"self": 1176.8541387399948,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001116428999978325,
"count": 1,
"is_parallel": true,
"self": 0.0002592179999965083,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008572109999818167,
"count": 2,
"is_parallel": true,
"self": 0.0008572109999818167
}
}
},
"UnityEnvironment.step": {
"total": 0.07143449599999485,
"count": 1,
"is_parallel": true,
"self": 0.0004166389999795683,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00026137499997958,
"count": 1,
"is_parallel": true,
"self": 0.00026137499997958
},
"communicator.exchange": {
"total": 0.06998461400002043,
"count": 1,
"is_parallel": true,
"self": 0.06998461400002043
},
"steps_from_proto": {
"total": 0.0007718680000152744,
"count": 1,
"is_parallel": true,
"self": 0.00023956699999416742,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000532301000021107,
"count": 2,
"is_parallel": true,
"self": 0.000532301000021107
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1336.4836289851003,
"count": 232874,
"is_parallel": true,
"self": 40.99569176426098,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.22463794298324,
"count": 232874,
"is_parallel": true,
"self": 81.22463794298324
},
"communicator.exchange": {
"total": 1114.6553237729393,
"count": 232874,
"is_parallel": true,
"self": 1114.6553237729393
},
"steps_from_proto": {
"total": 99.6079755049168,
"count": 232874,
"is_parallel": true,
"self": 35.84557947484461,
"children": {
"_process_rank_one_or_two_observation": {
"total": 63.76239603007218,
"count": 465748,
"is_parallel": true,
"self": 63.76239603007218
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 570.0592600220266,
"count": 232875,
"self": 6.9320009421014674,
"children": {
"process_trajectory": {
"total": 144.5071270739253,
"count": 232875,
"self": 142.93404056192605,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5730865119992359,
"count": 10,
"self": 1.5730865119992359
}
}
},
"_update_policy": {
"total": 418.62013200599984,
"count": 97,
"self": 357.36005829900046,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.26007370699938,
"count": 2910,
"self": 61.26007370699938
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.43000031838892e-07,
"count": 1,
"self": 9.43000031838892e-07
},
"TrainerController._save_models": {
"total": 0.12210651000032158,
"count": 1,
"self": 0.002075570000215521,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12003094000010606,
"count": 1,
"self": 0.12003094000010606
}
}
}
}
}
}
}