davera-017's picture
First Push
8838a85
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3866507411003113,
"min": 0.3866507411003113,
"max": 1.4091436862945557,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 11704.69140625,
"min": 11704.69140625,
"max": 42747.78125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989957.0,
"min": 29944.0,
"max": 989957.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989957.0,
"min": 29944.0,
"max": 989957.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5551133751869202,
"min": -0.10730387270450592,
"max": 0.5551133751869202,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 155.9868621826172,
"min": -25.860233306884766,
"max": 155.9868621826172,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.010759072378277779,
"min": -0.0014669419033452868,
"max": 0.31864863634109497,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 3.0232994556427,
"min": -0.399008184671402,
"max": 75.51972961425781,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07092652862636549,
"min": 0.06497040626224285,
"max": 0.0732933952177908,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9929714007691169,
"min": 0.4861378174254419,
"max": 1.0823606644510566,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01565486468912457,
"min": 0.0006947119086099437,
"max": 0.016423601630473662,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21916810564774397,
"min": 0.009031254811929268,
"max": 0.2299304228266313,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.64210459552143e-06,
"min": 7.64210459552143e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010698946433730003,
"min": 0.00010698946433730003,
"max": 0.0036320404893199,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10254733571428573,
"min": 0.10254733571428573,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4356627000000002,
"min": 1.3886848,
"max": 2.6173280999999995,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.000264478837857143,
"min": 0.000264478837857143,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003702703730000002,
"min": 0.003702703730000002,
"max": 0.12108694199000003,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.013791213743388653,
"min": 0.013670532032847404,
"max": 0.47153934836387634,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1930769979953766,
"min": 0.19138744473457336,
"max": 3.3007755279541016,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 341.3058823529412,
"min": 341.3058823529412,
"max": 992.4117647058823,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29011.0,
"min": 16871.0,
"max": 32822.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.635157619854983,
"min": -0.9246545975858514,
"max": 1.635157619854983,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 138.98839768767357,
"min": -30.5136017203331,
"max": 146.6437978670001,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.635157619854983,
"min": -0.9246545975858514,
"max": 1.635157619854983,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 138.98839768767357,
"min": -30.5136017203331,
"max": 146.6437978670001,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04810991270744981,
"min": 0.04810991270744981,
"max": 9.364630454603363,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.089342580133234,
"min": 4.089342580133234,
"max": 159.19871772825718,
"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": "1693506802",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"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": "0.31.0.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": "1693509033"
},
"total": 2231.405844742,
"count": 1,
"self": 1.282258684000226,
"children": {
"run_training.setup": {
"total": 0.09641765000014857,
"count": 1,
"self": 0.09641765000014857
},
"TrainerController.start_learning": {
"total": 2230.027168408,
"count": 1,
"self": 1.3157134680600393,
"children": {
"TrainerController._reset_env": {
"total": 5.8091715699999895,
"count": 1,
"self": 5.8091715699999895
},
"TrainerController.advance": {
"total": 2222.74691952294,
"count": 63755,
"self": 1.3386191629592759,
"children": {
"env_step": {
"total": 1535.906563924978,
"count": 63755,
"self": 1425.327376544907,
"children": {
"SubprocessEnvManager._take_step": {
"total": 109.77534604204834,
"count": 63755,
"self": 4.71703806204232,
"children": {
"TorchPolicy.evaluate": {
"total": 105.05830798000602,
"count": 62562,
"self": 105.05830798000602
}
}
},
"workers": {
"total": 0.8038413380224938,
"count": 63755,
"self": 0.0,
"children": {
"worker_root": {
"total": 2224.760314419008,
"count": 63755,
"is_parallel": true,
"self": 914.0351173629788,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002911290999918492,
"count": 1,
"is_parallel": true,
"self": 0.0009792439998363989,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019320470000820933,
"count": 8,
"is_parallel": true,
"self": 0.0019320470000820933
}
}
},
"UnityEnvironment.step": {
"total": 0.049870986000087214,
"count": 1,
"is_parallel": true,
"self": 0.0005976679999548651,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005303390000790387,
"count": 1,
"is_parallel": true,
"self": 0.0005303390000790387
},
"communicator.exchange": {
"total": 0.04680639399998654,
"count": 1,
"is_parallel": true,
"self": 0.04680639399998654
},
"steps_from_proto": {
"total": 0.0019365850000667706,
"count": 1,
"is_parallel": true,
"self": 0.0003965850005442917,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001539999999522479,
"count": 8,
"is_parallel": true,
"self": 0.001539999999522479
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1310.7251970560292,
"count": 63754,
"is_parallel": true,
"self": 34.54873338699372,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.552889270966716,
"count": 63754,
"is_parallel": true,
"self": 23.552889270966716
},
"communicator.exchange": {
"total": 1145.1498516740662,
"count": 63754,
"is_parallel": true,
"self": 1145.1498516740662
},
"steps_from_proto": {
"total": 107.47372272400253,
"count": 63754,
"is_parallel": true,
"self": 20.872826298745622,
"children": {
"_process_rank_one_or_two_observation": {
"total": 86.6008964252569,
"count": 510032,
"is_parallel": true,
"self": 86.6008964252569
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 685.5017364350026,
"count": 63755,
"self": 2.5345659970037104,
"children": {
"process_trajectory": {
"total": 114.02076878199932,
"count": 63755,
"self": 113.69622951999963,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3245392619996892,
"count": 2,
"self": 0.3245392619996892
}
}
},
"_update_policy": {
"total": 568.9464016559996,
"count": 455,
"self": 370.21830893499737,
"children": {
"TorchPPOOptimizer.update": {
"total": 198.7280927210022,
"count": 22785,
"self": 198.7280927210022
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0779999684018549e-06,
"count": 1,
"self": 1.0779999684018549e-06
},
"TrainerController._save_models": {
"total": 0.15536276900002122,
"count": 1,
"self": 0.0019503660000737,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15341240299994752,
"count": 1,
"self": 0.15341240299994752
}
}
}
}
}
}
}