ppo-Pyramids / run_logs /timers.json
chenmertens's picture
Initial commit
0e155b1
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 1.00198233127594,
"min": 0.9921206831932068,
"max": 1.4485609531402588,
"count": 4
},
"Pyramids.Policy.Entropy.sum": {
"value": 30011.375,
"min": 30011.375,
"max": 43943.546875,
"count": 4
},
"Pyramids.Step.mean": {
"value": 119947.0,
"min": 29914.0,
"max": 119947.0,
"count": 4
},
"Pyramids.Step.sum": {
"value": 119947.0,
"min": 29914.0,
"max": 119947.0,
"count": 4
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.08380933851003647,
"min": -0.08380933851003647,
"max": 0.03136281296610832,
"count": 4
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -20.2818603515625,
"min": -20.2818603515625,
"max": 7.432986259460449,
"count": 4
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.08611355721950531,
"min": 0.08611355721950531,
"max": 0.2662358582019806,
"count": 4
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 20.839481353759766,
"min": 20.839481353759766,
"max": 64.4290771484375,
"count": 4
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06898505029814996,
"min": 0.06898505029814996,
"max": 0.07291630261307913,
"count": 4
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.8968056538759493,
"min": 0.583330420904633,
"max": 0.9145981951577791,
"count": 4
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.001384501303736123,
"min": 0.001384501303736123,
"max": 0.007094622672303227,
"count": 4
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.0179985169485696,
"min": 0.0179985169485696,
"max": 0.056756981378425816,
"count": 4
},
"Pyramids.Policy.LearningRate.mean": {
"value": 0.0002893945189197769,
"min": 0.0002893945189197769,
"max": 0.0002984042755319083,
"count": 4
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0037621287459570995,
"min": 0.0023872342042552666,
"max": 0.0038025975324674994,
"count": 4
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1964648384615385,
"min": 0.1964648384615385,
"max": 0.19946809166666668,
"count": 4
},
"Pyramids.Policy.Epsilon.sum": {
"value": 2.5540429000000007,
"min": 1.5957447333333334,
"max": 2.5675324999999996,
"count": 4
},
"Pyramids.Policy.Beta.mean": {
"value": 0.009646837362307693,
"min": 0.009646837362307693,
"max": 0.009946862357499999,
"count": 4
},
"Pyramids.Policy.Beta.sum": {
"value": 0.12540888571,
"min": 0.07957489885999999,
"max": 0.12675649675,
"count": 4
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.07624217122793198,
"min": 0.07624217122793198,
"max": 0.5006290078163147,
"count": 4
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.9911482334136963,
"min": 0.9911482334136963,
"max": 4.005032062530518,
"count": 4
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 952.6470588235294,
"min": 952.6470588235294,
"max": 996.625,
"count": 4
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 32390.0,
"min": 15946.0,
"max": 32800.0,
"count": 4
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.8358471086796593,
"min": -0.8725625551305711,
"max": -0.7976242969885017,
"count": 4
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -28.418801695108414,
"min": -28.830801710486412,
"max": -13.961000882089138,
"count": 4
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.8358471086796593,
"min": -0.8725625551305711,
"max": -0.7976242969885017,
"count": 4
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -28.418801695108414,
"min": -28.830801710486412,
"max": -13.961000882089138,
"count": 4
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.7794637884944677,
"min": 0.7794637884944677,
"max": 10.226822283118963,
"count": 4
},
"Pyramids.Policy.RndReward.sum": {
"value": 26.501768808811903,
"min": 26.501768808811903,
"max": 163.6291565299034,
"count": 4
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 4
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 4
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1674467848",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1674468135"
},
"total": 286.8594396850001,
"count": 1,
"self": 0.30682105500000034,
"children": {
"run_training.setup": {
"total": 0.10416299700000309,
"count": 1,
"self": 0.10416299700000309
},
"TrainerController.start_learning": {
"total": 286.4484556330001,
"count": 1,
"self": 0.17793223698390648,
"children": {
"TrainerController._reset_env": {
"total": 6.174762633,
"count": 1,
"self": 6.174762633
},
"TrainerController.advance": {
"total": 279.9142511180162,
"count": 9324,
"self": 0.1896541740087514,
"children": {
"env_step": {
"total": 183.5860191530079,
"count": 9324,
"self": 167.853302513024,
"children": {
"SubprocessEnvManager._take_step": {
"total": 15.622803599992949,
"count": 9324,
"self": 0.6379715359952343,
"children": {
"TorchPolicy.evaluate": {
"total": 14.984832063997715,
"count": 9288,
"self": 5.023445084994023,
"children": {
"TorchPolicy.sample_actions": {
"total": 9.961386979003692,
"count": 9288,
"self": 9.961386979003692
}
}
}
}
},
"workers": {
"total": 0.1099130399909427,
"count": 9323,
"self": 0.0,
"children": {
"worker_root": {
"total": 285.7027269049919,
"count": 9323,
"is_parallel": true,
"self": 132.44011913698967,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018625420000262238,
"count": 1,
"is_parallel": true,
"self": 0.0007037320000335967,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011588099999926271,
"count": 8,
"is_parallel": true,
"self": 0.0011588099999926271
}
}
},
"UnityEnvironment.step": {
"total": 0.045178636999935406,
"count": 1,
"is_parallel": true,
"self": 0.0005328179997832194,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004357630000413337,
"count": 1,
"is_parallel": true,
"self": 0.0004357630000413337
},
"communicator.exchange": {
"total": 0.04249145200003568,
"count": 1,
"is_parallel": true,
"self": 0.04249145200003568
},
"steps_from_proto": {
"total": 0.0017186040000751746,
"count": 1,
"is_parallel": true,
"self": 0.0004508870001700416,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001267716999905133,
"count": 8,
"is_parallel": true,
"self": 0.001267716999905133
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 153.26260776800223,
"count": 9322,
"is_parallel": true,
"self": 4.146317096021221,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.5863848909863236,
"count": 9322,
"is_parallel": true,
"self": 3.5863848909863236
},
"communicator.exchange": {
"total": 130.14465234200338,
"count": 9322,
"is_parallel": true,
"self": 130.14465234200338
},
"steps_from_proto": {
"total": 15.385253438991299,
"count": 9322,
"is_parallel": true,
"self": 3.410272352995321,
"children": {
"_process_rank_one_or_two_observation": {
"total": 11.974981085995978,
"count": 74576,
"is_parallel": true,
"self": 11.974981085995978
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 96.13857779099953,
"count": 9323,
"self": 0.2502447500029348,
"children": {
"process_trajectory": {
"total": 21.763189877997547,
"count": 9323,
"self": 21.763189877997547
},
"_update_policy": {
"total": 74.12514316299905,
"count": 56,
"self": 27.909818004999693,
"children": {
"TorchPPOOptimizer.update": {
"total": 46.21532515799936,
"count": 3393,
"self": 46.21532515799936
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3010001111979363e-06,
"count": 1,
"self": 1.3010001111979363e-06
},
"TrainerController._save_models": {
"total": 0.18150834399989435,
"count": 1,
"self": 0.0018405879998226737,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17966775600007168,
"count": 1,
"self": 0.17966775600007168
}
}
}
}
}
}
}