mojoee's picture
First Push
b7e5f0c
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3153068721294403,
"min": 0.31278035044670105,
"max": 1.465382695198059,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 9449.1162109375,
"min": 9332.412109375,
"max": 44453.84765625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989905.0,
"min": 29983.0,
"max": 989905.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989905.0,
"min": 29983.0,
"max": 989905.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6149446368217468,
"min": -0.10659858584403992,
"max": 0.6149446368217468,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 171.56954956054688,
"min": -25.583660125732422,
"max": 174.93862915039062,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.04858509823679924,
"min": 0.0011303691426292062,
"max": 0.5421221852302551,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 13.555242538452148,
"min": 0.30180856585502625,
"max": 129.56719970703125,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06729491278452944,
"min": 0.0654827365402836,
"max": 0.07536516649646541,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9421287789834121,
"min": 0.6029213319717233,
"max": 1.036578950569189,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015664819312015812,
"min": 0.0010944595406687002,
"max": 0.017973490424213066,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21930747036822137,
"min": 0.015322433569361804,
"max": 0.2516288659389829,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.312768991014288e-06,
"min": 7.312768991014288e-06,
"max": 0.000294988426670525,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010237876587420004,
"min": 0.00010237876587420004,
"max": 0.0036348706883765,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10243755714285716,
"min": 0.10243755714285716,
"max": 0.198329475,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4341258000000001,
"min": 1.4341258000000001,
"max": 2.6116235000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002535119585714286,
"min": 0.0002535119585714286,
"max": 0.009833114552500001,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0035491674200000007,
"min": 0.0035491674200000007,
"max": 0.12118118765000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.014688827097415924,
"min": 0.014318633824586868,
"max": 0.49295198917388916,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.20564357936382294,
"min": 0.20564357936382294,
"max": 3.9436159133911133,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 291.8510638297872,
"min": 291.8510638297872,
"max": 987.375,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 27434.0,
"min": 17676.0,
"max": 33700.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.708148921740816,
"min": -0.9176774683498568,
"max": 1.708148921740816,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 160.5659986436367,
"min": -29.039401650428772,
"max": 160.5659986436367,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.708148921740816,
"min": -0.9176774683498568,
"max": 1.708148921740816,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 160.5659986436367,
"min": -29.039401650428772,
"max": 160.5659986436367,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04443721518482755,
"min": 0.04443721518482755,
"max": 9.196099694622191,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.17709822737379,
"min": 4.17709822737379,
"max": 174.72589419782162,
"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": "1675756961",
"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": "1675759253"
},
"total": 2291.427985411,
"count": 1,
"self": 1.3083715120001216,
"children": {
"run_training.setup": {
"total": 0.1990872159999526,
"count": 1,
"self": 0.1990872159999526
},
"TrainerController.start_learning": {
"total": 2289.920526683,
"count": 1,
"self": 1.4155378179948457,
"children": {
"TrainerController._reset_env": {
"total": 6.489424027000041,
"count": 1,
"self": 6.489424027000041
},
"TrainerController.advance": {
"total": 2281.894488836005,
"count": 64072,
"self": 1.4553278800531189,
"children": {
"env_step": {
"total": 1553.1752264109434,
"count": 64072,
"self": 1439.9490908649193,
"children": {
"SubprocessEnvManager._take_step": {
"total": 112.34451876209687,
"count": 64072,
"self": 4.556170255139477,
"children": {
"TorchPolicy.evaluate": {
"total": 107.78834850695739,
"count": 62575,
"self": 36.31983313391265,
"children": {
"TorchPolicy.sample_actions": {
"total": 71.46851537304474,
"count": 62575,
"self": 71.46851537304474
}
}
}
}
},
"workers": {
"total": 0.8816167839272566,
"count": 64072,
"self": 0.0,
"children": {
"worker_root": {
"total": 2284.7118268170675,
"count": 64072,
"is_parallel": true,
"self": 960.0185244931174,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017833419999533362,
"count": 1,
"is_parallel": true,
"self": 0.0006748490002337348,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011084929997196014,
"count": 8,
"is_parallel": true,
"self": 0.0011084929997196014
}
}
},
"UnityEnvironment.step": {
"total": 0.04550423200021214,
"count": 1,
"is_parallel": true,
"self": 0.0005467540001973248,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004969980000169016,
"count": 1,
"is_parallel": true,
"self": 0.0004969980000169016
},
"communicator.exchange": {
"total": 0.04268106099993929,
"count": 1,
"is_parallel": true,
"self": 0.04268106099993929
},
"steps_from_proto": {
"total": 0.001779419000058624,
"count": 1,
"is_parallel": true,
"self": 0.00046080600031928043,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013186129997393436,
"count": 8,
"is_parallel": true,
"self": 0.0013186129997393436
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1324.69330232395,
"count": 64071,
"is_parallel": true,
"self": 31.306181184991374,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.757995801981224,
"count": 64071,
"is_parallel": true,
"self": 22.757995801981224
},
"communicator.exchange": {
"total": 1169.1084357129773,
"count": 64071,
"is_parallel": true,
"self": 1169.1084357129773
},
"steps_from_proto": {
"total": 101.52068962400017,
"count": 64071,
"is_parallel": true,
"self": 22.768846188874704,
"children": {
"_process_rank_one_or_two_observation": {
"total": 78.75184343512547,
"count": 512568,
"is_parallel": true,
"self": 78.75184343512547
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 727.2639345450086,
"count": 64072,
"self": 2.7540945750167793,
"children": {
"process_trajectory": {
"total": 161.04493600499086,
"count": 64072,
"self": 160.82096222399082,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22397378100004062,
"count": 2,
"self": 0.22397378100004062
}
}
},
"_update_policy": {
"total": 563.464903965001,
"count": 460,
"self": 218.0687053139918,
"children": {
"TorchPPOOptimizer.update": {
"total": 345.3961986510092,
"count": 22773,
"self": 345.3961986510092
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1699999049596954e-06,
"count": 1,
"self": 1.1699999049596954e-06
},
"TrainerController._save_models": {
"total": 0.1210748319999766,
"count": 1,
"self": 0.001898115999665606,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11917671600031099,
"count": 1,
"self": 0.11917671600031099
}
}
}
}
}
}
}