ppo-Pyramids / run_logs /timers.json
akghxhs55's picture
first commit
c7731d1
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5240244269371033,
"min": 0.5240244269371033,
"max": 1.5604443550109863,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 15603.3505859375,
"min": 15603.3505859375,
"max": 49934.21875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989827.0,
"min": 29912.0,
"max": 989827.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989827.0,
"min": 29912.0,
"max": 989827.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.47195708751678467,
"min": -0.11839296668767929,
"max": 0.5243668556213379,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 73.15335083007812,
"min": -14.088763236999512,
"max": 79.17939758300781,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.034837398678064346,
"min": 0.014649661257863045,
"max": 0.41853392124176025,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 5.399796962738037,
"min": 2.0949015617370605,
"max": 49.805538177490234,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.04392328329101604,
"min": 0.04392328329101604,
"max": 0.05385815075984552,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.3074629830371123,
"min": 0.16157445227953657,
"max": 0.4029338099547507,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.017007534372775506,
"min": 0.001628449542701528,
"max": 0.019308498711325228,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.11905274060942854,
"min": 0.011399146798910695,
"max": 0.1351594909792766,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.620140317128576e-06,
"min": 7.620140317128576e-06,
"max": 0.00029516160161279994,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 5.334098221990003e-05,
"min": 5.334098221990003e-05,
"max": 0.0018782307739230995,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10254001428571431,
"min": 0.10254001428571431,
"max": 0.19838719999999999,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 0.7177801000000001,
"min": 0.5951616,
"max": 1.3260769000000001,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002637474271428573,
"min": 0.0002637474271428573,
"max": 0.009838881280000001,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0018462319900000013,
"min": 0.0018462319900000013,
"max": 0.06261508231,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.017371272668242455,
"min": 0.01701119728386402,
"max": 0.7396652102470398,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.12159890681505203,
"min": 0.1190783753991127,
"max": 2.2189955711364746,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 385.2987012987013,
"min": 348.7011494252874,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29668.0,
"min": 17236.0,
"max": 33706.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5107844003609248,
"min": -1.0000000596046448,
"max": 1.5876545325502174,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 116.33039882779121,
"min": -27.664801836013794,
"max": 135.34819811582565,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5107844003609248,
"min": -1.0000000596046448,
"max": 1.5876545325502174,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 116.33039882779121,
"min": -27.664801836013794,
"max": 135.34819811582565,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.06773548879261528,
"min": 0.06295230909584804,
"max": 11.090575384057086,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 5.215632637031376,
"min": 4.847327800380299,
"max": 255.083233833313,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1674368628",
"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": "1674370414"
},
"total": 1785.822968471,
"count": 1,
"self": 0.47895825499995226,
"children": {
"run_training.setup": {
"total": 0.09914366099997096,
"count": 1,
"self": 0.09914366099997096
},
"TrainerController.start_learning": {
"total": 1785.244866555,
"count": 1,
"self": 1.1131324259840767,
"children": {
"TrainerController._reset_env": {
"total": 6.06497550600011,
"count": 1,
"self": 6.06497550600011
},
"TrainerController.advance": {
"total": 1777.9846226120155,
"count": 63720,
"self": 1.146976587987865,
"children": {
"env_step": {
"total": 1249.3115349429675,
"count": 63720,
"self": 1150.9779937049723,
"children": {
"SubprocessEnvManager._take_step": {
"total": 97.62427970501813,
"count": 63720,
"self": 4.068538166007329,
"children": {
"TorchPolicy.evaluate": {
"total": 93.5557415390108,
"count": 62590,
"self": 31.474505881949653,
"children": {
"TorchPolicy.sample_actions": {
"total": 62.08123565706114,
"count": 62590,
"self": 62.08123565706114
}
}
}
}
},
"workers": {
"total": 0.7092615329770524,
"count": 63720,
"self": 0.0,
"children": {
"worker_root": {
"total": 1781.4459608130917,
"count": 63720,
"is_parallel": true,
"self": 720.5651224371013,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001775920000000042,
"count": 1,
"is_parallel": true,
"self": 0.0006120049999935873,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011639150000064546,
"count": 8,
"is_parallel": true,
"self": 0.0011639150000064546
}
}
},
"UnityEnvironment.step": {
"total": 0.04738303699991775,
"count": 1,
"is_parallel": true,
"self": 0.0004737369999929797,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042197099992336007,
"count": 1,
"is_parallel": true,
"self": 0.00042197099992336007
},
"communicator.exchange": {
"total": 0.0447465419999844,
"count": 1,
"is_parallel": true,
"self": 0.0447465419999844
},
"steps_from_proto": {
"total": 0.0017407870000170078,
"count": 1,
"is_parallel": true,
"self": 0.0004731369999717572,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012676500000452506,
"count": 8,
"is_parallel": true,
"self": 0.0012676500000452506
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1060.8808383759904,
"count": 63719,
"is_parallel": true,
"self": 26.506139344005533,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 20.98834946001216,
"count": 63719,
"is_parallel": true,
"self": 20.98834946001216
},
"communicator.exchange": {
"total": 918.392368103008,
"count": 63719,
"is_parallel": true,
"self": 918.392368103008
},
"steps_from_proto": {
"total": 94.99398146896465,
"count": 63719,
"is_parallel": true,
"self": 20.362303769981963,
"children": {
"_process_rank_one_or_two_observation": {
"total": 74.63167769898268,
"count": 509752,
"is_parallel": true,
"self": 74.63167769898268
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 527.5261110810602,
"count": 63720,
"self": 2.2673867050991703,
"children": {
"process_trajectory": {
"total": 125.55169884495604,
"count": 63720,
"self": 125.36900244295589,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18269640200014692,
"count": 2,
"self": 0.18269640200014692
}
}
},
"_update_policy": {
"total": 399.707025531005,
"count": 228,
"self": 188.07272992402272,
"children": {
"TorchPPOOptimizer.update": {
"total": 211.63429560698228,
"count": 11385,
"self": 211.63429560698228
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.430003279296216e-07,
"count": 1,
"self": 7.430003279296216e-07
},
"TrainerController._save_models": {
"total": 0.08213526800000182,
"count": 1,
"self": 0.0013929020001341996,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08074236599986762,
"count": 1,
"self": 0.08074236599986762
}
}
}
}
}
}
}