ppo-Pyramids1 / run_logs /timers.json
jmurphy97's picture
First Push
4c7e103
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5131139755249023,
"min": 0.4367370009422302,
"max": 1.397188425064087,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 15368.7890625,
"min": 13088.134765625,
"max": 42385.109375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989991.0,
"min": 29952.0,
"max": 989991.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989991.0,
"min": 29952.0,
"max": 989991.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4246329665184021,
"min": -0.08565536886453629,
"max": 0.4246329665184021,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 113.37699890136719,
"min": -20.471633911132812,
"max": 113.37699890136719,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.2508496940135956,
"min": -0.10995645076036453,
"max": 0.49438565969467163,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 66.97686767578125,
"min": -28.478721618652344,
"max": 118.65255737304688,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06610573649279367,
"min": 0.06517848716161792,
"max": 0.07943117762434121,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9915860473919049,
"min": 0.48692259363911716,
"max": 1.047561117496419,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.023517332603588847,
"min": 0.0004826190122153175,
"max": 0.023517332603588847,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.3527599890538327,
"min": 0.006274047158799128,
"max": 0.3527599890538327,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.535757488113332e-06,
"min": 7.535757488113332e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011303636232169998,
"min": 0.00011303636232169998,
"max": 0.0035069432310189993,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10251188666666665,
"min": 0.10251188666666665,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5376782999999998,
"min": 1.3691136000000002,
"max": 2.568981,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.000260937478,
"min": 0.000260937478,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0039140621700000005,
"min": 0.0039140621700000005,
"max": 0.1169212019,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.04613911733031273,
"min": 0.04269443824887276,
"max": 0.6518697142601013,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.6920867562294006,
"min": 0.5990122556686401,
"max": 4.5630879402160645,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 413.25,
"min": 413.25,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28101.0,
"min": 15984.0,
"max": 33986.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4717825898441717,
"min": -1.0000000521540642,
"max": 1.4717825898441717,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 101.55299869924784,
"min": -32.000001668930054,
"max": 101.55299869924784,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4717825898441717,
"min": -1.0000000521540642,
"max": 1.4717825898441717,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 101.55299869924784,
"min": -32.000001668930054,
"max": 101.55299869924784,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.19427635908747712,
"min": 0.19427635908747712,
"max": 13.461702583357692,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 13.405068777035922,
"min": 12.117998759262264,
"max": 215.38724133372307,
"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": "1681283885",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1681285953"
},
"total": 2067.82999345,
"count": 1,
"self": 0.9379970780000804,
"children": {
"run_training.setup": {
"total": 0.10860353600014605,
"count": 1,
"self": 0.10860353600014605
},
"TrainerController.start_learning": {
"total": 2066.7833928359996,
"count": 1,
"self": 1.3508368869984224,
"children": {
"TrainerController._reset_env": {
"total": 3.783311969000124,
"count": 1,
"self": 3.783311969000124
},
"TrainerController.advance": {
"total": 2061.5039812420014,
"count": 63509,
"self": 1.5122579460530687,
"children": {
"env_step": {
"total": 1436.6831371029837,
"count": 63509,
"self": 1330.0114551999923,
"children": {
"SubprocessEnvManager._take_step": {
"total": 105.85915436702476,
"count": 63509,
"self": 4.668681647988251,
"children": {
"TorchPolicy.evaluate": {
"total": 101.1904727190365,
"count": 62550,
"self": 101.1904727190365
}
}
},
"workers": {
"total": 0.8125275359666375,
"count": 63509,
"self": 0.0,
"children": {
"worker_root": {
"total": 2061.892406423084,
"count": 63509,
"is_parallel": true,
"self": 842.1365186930823,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001831290000154695,
"count": 1,
"is_parallel": true,
"self": 0.0005640940000830597,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012671960000716354,
"count": 8,
"is_parallel": true,
"self": 0.0012671960000716354
}
}
},
"UnityEnvironment.step": {
"total": 0.04818915600003493,
"count": 1,
"is_parallel": true,
"self": 0.000560971000140853,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005057379999016121,
"count": 1,
"is_parallel": true,
"self": 0.0005057379999016121
},
"communicator.exchange": {
"total": 0.045363748999989184,
"count": 1,
"is_parallel": true,
"self": 0.045363748999989184
},
"steps_from_proto": {
"total": 0.0017586980000032781,
"count": 1,
"is_parallel": true,
"self": 0.00038115499978630396,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013775430002169742,
"count": 8,
"is_parallel": true,
"self": 0.0013775430002169742
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1219.7558877300019,
"count": 63508,
"is_parallel": true,
"self": 32.078787451977405,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.684350297072342,
"count": 63508,
"is_parallel": true,
"self": 22.684350297072342
},
"communicator.exchange": {
"total": 1072.2818266599734,
"count": 63508,
"is_parallel": true,
"self": 1072.2818266599734
},
"steps_from_proto": {
"total": 92.71092332097874,
"count": 63508,
"is_parallel": true,
"self": 19.416475177934444,
"children": {
"_process_rank_one_or_two_observation": {
"total": 73.29444814304429,
"count": 508064,
"is_parallel": true,
"self": 73.29444814304429
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 623.3085861929646,
"count": 63509,
"self": 2.429314370907605,
"children": {
"process_trajectory": {
"total": 106.51269975306059,
"count": 63509,
"self": 106.25525932106075,
"children": {
"RLTrainer._checkpoint": {
"total": 0.25744043199983935,
"count": 2,
"self": 0.25744043199983935
}
}
},
"_update_policy": {
"total": 514.3665720689964,
"count": 443,
"self": 329.1817946309909,
"children": {
"TorchPPOOptimizer.update": {
"total": 185.18477743800554,
"count": 22767,
"self": 185.18477743800554
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1470001481939107e-06,
"count": 1,
"self": 1.1470001481939107e-06
},
"TrainerController._save_models": {
"total": 0.1452615909997803,
"count": 1,
"self": 0.001986700999623281,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14327489000015703,
"count": 1,
"self": 0.14327489000015703
}
}
}
}
}
}
}