ppo-Huggy / run_logs /timers.json
Newbeder's picture
Huggy
b6fb314
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.405300259590149,
"min": 1.405300259590149,
"max": 1.4257264137268066,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71143.328125,
"min": 68635.9375,
"max": 77904.2265625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 70.74461979913917,
"min": 70.74461979913917,
"max": 375.83458646616543,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49309.0,
"min": 49207.0,
"max": 49986.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999966.0,
"min": 49738.0,
"max": 1999966.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999966.0,
"min": 49738.0,
"max": 1999966.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5711090564727783,
"min": 0.14714427292346954,
"max": 2.5711090564727783,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1792.06298828125,
"min": 19.423044204711914,
"max": 1792.06298828125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 4.061317209790393,
"min": 1.6754069980798345,
"max": 4.091540168580555,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2830.7380952239037,
"min": 221.15372374653816,
"max": 2830.7380952239037,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 4.061317209790393,
"min": 1.6754069980798345,
"max": 4.091540168580555,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2830.7380952239037,
"min": 221.15372374653816,
"max": 2830.7380952239037,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01690876129367906,
"min": 0.013695698397350499,
"max": 0.022734792168193962,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.050726283881037185,
"min": 0.027391396794700998,
"max": 0.05544159555574879,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06416115044719643,
"min": 0.020619328568379086,
"max": 0.06883475165814162,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.19248345134158928,
"min": 0.04123865713675817,
"max": 0.19248345134158928,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.784598738500002e-06,
"min": 3.784598738500002e-06,
"max": 0.00029537820154059997,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1353796215500005e-05,
"min": 1.1353796215500005e-05,
"max": 0.0008441674686108497,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1012615,
"min": 0.1012615,
"max": 0.1984594,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037845,
"min": 0.20765540000000005,
"max": 0.5813891500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.294885000000004e-05,
"min": 7.294885000000004e-05,
"max": 0.004923124060000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021884655000000013,
"min": 0.00021884655000000013,
"max": 0.014071318585000003,
"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": "1686891141",
"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": "1686893737"
},
"total": 2596.43882158,
"count": 1,
"self": 0.44168347800041374,
"children": {
"run_training.setup": {
"total": 0.060465243999942686,
"count": 1,
"self": 0.060465243999942686
},
"TrainerController.start_learning": {
"total": 2595.936672858,
"count": 1,
"self": 4.8119962848741125,
"children": {
"TrainerController._reset_env": {
"total": 5.222686274999887,
"count": 1,
"self": 5.222686274999887
},
"TrainerController.advance": {
"total": 2585.7810945341257,
"count": 233448,
"self": 4.876294484270147,
"children": {
"env_step": {
"total": 2021.7850563689353,
"count": 233448,
"self": 1703.6351775848286,
"children": {
"SubprocessEnvManager._take_step": {
"total": 315.09118188708453,
"count": 233448,
"self": 18.00055218908983,
"children": {
"TorchPolicy.evaluate": {
"total": 297.0906296979947,
"count": 222974,
"self": 297.0906296979947
}
}
},
"workers": {
"total": 3.0586968970221733,
"count": 233448,
"self": 0.0,
"children": {
"worker_root": {
"total": 2587.3817623680566,
"count": 233448,
"is_parallel": true,
"self": 1198.1799087399313,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011230309999064048,
"count": 1,
"is_parallel": true,
"self": 0.00033552599984432163,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007875050000620831,
"count": 2,
"is_parallel": true,
"self": 0.0007875050000620831
}
}
},
"UnityEnvironment.step": {
"total": 0.030746661999955904,
"count": 1,
"is_parallel": true,
"self": 0.00034003100017798715,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023849999979574932,
"count": 1,
"is_parallel": true,
"self": 0.00023849999979574932
},
"communicator.exchange": {
"total": 0.02930540700003803,
"count": 1,
"is_parallel": true,
"self": 0.02930540700003803
},
"steps_from_proto": {
"total": 0.0008627239999441372,
"count": 1,
"is_parallel": true,
"self": 0.00026221400003123563,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006005099999129015,
"count": 2,
"is_parallel": true,
"self": 0.0006005099999129015
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1389.2018536281253,
"count": 233447,
"is_parallel": true,
"self": 40.92255351105723,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.98916781796424,
"count": 233447,
"is_parallel": true,
"self": 85.98916781796424
},
"communicator.exchange": {
"total": 1160.6622117150011,
"count": 233447,
"is_parallel": true,
"self": 1160.6622117150011
},
"steps_from_proto": {
"total": 101.62792058410264,
"count": 233447,
"is_parallel": true,
"self": 38.7130534249809,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.91486715912174,
"count": 466894,
"is_parallel": true,
"self": 62.91486715912174
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 559.1197436809202,
"count": 233448,
"self": 7.397081618106085,
"children": {
"process_trajectory": {
"total": 154.5424851378134,
"count": 233448,
"self": 153.08442168381362,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4580634539997845,
"count": 10,
"self": 1.4580634539997845
}
}
},
"_update_policy": {
"total": 397.18017692500075,
"count": 97,
"self": 335.4841776940025,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.69599923099827,
"count": 2910,
"self": 61.69599923099827
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3930002751294523e-06,
"count": 1,
"self": 1.3930002751294523e-06
},
"TrainerController._save_models": {
"total": 0.12089437099984934,
"count": 1,
"self": 0.0018895620000876079,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11900480899976174,
"count": 1,
"self": 0.11900480899976174
}
}
}
}
}
}
}