manmyung's picture
First Push
972524b
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5778467655181885,
"min": 0.5644880533218384,
"max": 1.0903167724609375,
"count": 27
},
"Pyramids.Policy.Entropy.sum": {
"value": 17113.509765625,
"min": 14867.677734375,
"max": 32803.0390625,
"count": 27
},
"Pyramids.Step.mean": {
"value": 989926.0,
"min": 209991.0,
"max": 989926.0,
"count": 27
},
"Pyramids.Step.sum": {
"value": 989926.0,
"min": 209991.0,
"max": 989926.0,
"count": 27
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.39801111817359924,
"min": -0.10163868963718414,
"max": 0.39801111817359924,
"count": 27
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 107.06498718261719,
"min": -24.5965633392334,
"max": 107.06498718261719,
"count": 27
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.11363773047924042,
"min": -0.05971188470721245,
"max": 0.11363773047924042,
"count": 27
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 30.56855010986328,
"min": -16.002784729003906,
"max": 30.56855010986328,
"count": 27
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06602687373790932,
"min": 0.06602687373790932,
"max": 0.0725631415288219,
"count": 27
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9243762323307304,
"min": 0.21228088629626046,
"max": 1.07178095341078,
"count": 27
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.016520114454025618,
"min": 0.0006235202636397278,
"max": 0.016520114454025618,
"count": 27
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.23128160235635867,
"min": 0.0023454733289251335,
"max": 0.23128160235635867,
"count": 27
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.6023974659e-06,
"min": 7.6023974659e-06,
"max": 0.00023887712037429993,
"count": 27
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001064335645226,
"min": 0.0001064335645226,
"max": 0.0027838167720612003,
"count": 27
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1025341,
"min": 0.1025341,
"max": 0.17962570000000003,
"count": 27
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4354774000000001,
"min": 0.5388771000000001,
"max": 2.2747844,
"count": 27
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002631565900000001,
"min": 0.0002631565900000001,
"max": 0.00796460743,
"count": 27
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036841922600000013,
"min": 0.0036841922600000013,
"max": 0.09283108612,
"count": 27
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.008909021504223347,
"min": 0.008909021504223347,
"max": 0.03914414346218109,
"count": 27
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1247262954711914,
"min": 0.11743243038654327,
"max": 0.3834875822067261,
"count": 27
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 434.23943661971833,
"min": 434.23943661971833,
"max": 999.0,
"count": 27
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30831.0,
"min": 15984.0,
"max": 33030.0,
"count": 27
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.368518294687842,
"min": -1.0000000521540642,
"max": 1.4634382135289556,
"count": 27
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 97.16479892283678,
"min": -28.924801647663116,
"max": 99.51379851996899,
"count": 27
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.368518294687842,
"min": -1.0000000521540642,
"max": 1.4634382135289556,
"count": 27
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 97.16479892283678,
"min": -28.924801647663116,
"max": 99.51379851996899,
"count": 27
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03918409688820145,
"min": 0.03918409688820145,
"max": 0.38616177391712414,
"count": 27
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.782070879062303,
"min": 0.3267418332397938,
"max": 12.743338539265096,
"count": 27
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 27
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 27
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1689474029",
"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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume",
"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": "1689475872"
},
"total": 1843.0409032699995,
"count": 1,
"self": 1.365671194999777,
"children": {
"run_training.setup": {
"total": 0.04236321200005477,
"count": 1,
"self": 0.04236321200005477
},
"TrainerController.start_learning": {
"total": 1841.6328688629997,
"count": 1,
"self": 1.1762784020093022,
"children": {
"TrainerController._reset_env": {
"total": 4.134572570000273,
"count": 1,
"self": 4.134572570000273
},
"TrainerController.advance": {
"total": 1836.1390447609897,
"count": 51208,
"self": 1.229169223957797,
"children": {
"env_step": {
"total": 1297.7533023260148,
"count": 51208,
"self": 1201.0127104020044,
"children": {
"SubprocessEnvManager._take_step": {
"total": 96.03883649498175,
"count": 51208,
"self": 3.965214081995782,
"children": {
"TorchPolicy.evaluate": {
"total": 92.07362241298597,
"count": 50348,
"self": 92.07362241298597
}
}
},
"workers": {
"total": 0.701755429028708,
"count": 51208,
"self": 0.0,
"children": {
"worker_root": {
"total": 1836.9434975340218,
"count": 51208,
"is_parallel": true,
"self": 732.3744857390957,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020213419998071913,
"count": 1,
"is_parallel": true,
"self": 0.0006635869999627175,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013577549998444738,
"count": 8,
"is_parallel": true,
"self": 0.0013577549998444738
}
}
},
"UnityEnvironment.step": {
"total": 0.051140615999884176,
"count": 1,
"is_parallel": true,
"self": 0.0005900709998059028,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004880229998889263,
"count": 1,
"is_parallel": true,
"self": 0.0004880229998889263
},
"communicator.exchange": {
"total": 0.04812828800004354,
"count": 1,
"is_parallel": true,
"self": 0.04812828800004354
},
"steps_from_proto": {
"total": 0.001934234000145807,
"count": 1,
"is_parallel": true,
"self": 0.0003475619996606838,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015866720004851231,
"count": 8,
"is_parallel": true,
"self": 0.0015866720004851231
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1104.5690117949262,
"count": 51207,
"is_parallel": true,
"self": 28.940049437850575,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 19.14033584301842,
"count": 51207,
"is_parallel": true,
"self": 19.14033584301842
},
"communicator.exchange": {
"total": 967.6035714390009,
"count": 51207,
"is_parallel": true,
"self": 967.6035714390009
},
"steps_from_proto": {
"total": 88.88505507505624,
"count": 51207,
"is_parallel": true,
"self": 17.27394227902687,
"children": {
"_process_rank_one_or_two_observation": {
"total": 71.61111279602937,
"count": 409656,
"is_parallel": true,
"self": 71.61111279602937
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 537.1565732110171,
"count": 51208,
"self": 2.3467337829865755,
"children": {
"process_trajectory": {
"total": 90.33775859803154,
"count": 51208,
"self": 90.05513052603146,
"children": {
"RLTrainer._checkpoint": {
"total": 0.28262807200007956,
"count": 2,
"self": 0.28262807200007956
}
}
},
"_update_policy": {
"total": 444.47208082999896,
"count": 364,
"self": 285.10498347500425,
"children": {
"TorchPPOOptimizer.update": {
"total": 159.3670973549947,
"count": 18294,
"self": 159.3670973549947
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2210002751089633e-06,
"count": 1,
"self": 1.2210002751089633e-06
},
"TrainerController._save_models": {
"total": 0.18297190900011628,
"count": 1,
"self": 0.004209181000078388,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1787627280000379,
"count": 1,
"self": 0.1787627280000379
}
}
}
}
}
}
}