ppo-Pyramids / run_logs /timers.json
robotman0's picture
First push
ea39974
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.40288931131362915,
"min": 0.4010867774486542,
"max": 1.5102291107177734,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12170.48046875,
"min": 12077.525390625,
"max": 45814.30859375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989919.0,
"min": 29914.0,
"max": 989919.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989919.0,
"min": 29914.0,
"max": 989919.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5135869979858398,
"min": -0.09541986882686615,
"max": 0.5539620518684387,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 140.72283935546875,
"min": -22.900768280029297,
"max": 152.33956909179688,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.02740642800927162,
"min": -0.0381057932972908,
"max": 0.17480121552944183,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 7.509361267089844,
"min": -10.136140823364258,
"max": 41.952293395996094,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07054058476351202,
"min": 0.0653048978440763,
"max": 0.07520934263621235,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0581087714526802,
"min": 0.5086942826629879,
"max": 1.091625958341562,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01841895796759572,
"min": 0.0001937613274648397,
"max": 0.01841895796759572,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.27628436951393576,
"min": 0.002263156109023451,
"max": 0.27628436951393576,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.560657479813333e-06,
"min": 7.560657479813333e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011340986219719999,
"min": 0.00011340986219719999,
"max": 0.0032594468135177996,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10252018666666667,
"min": 0.10252018666666667,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5378028,
"min": 1.3886848,
"max": 2.5273411000000006,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.000261766648,
"min": 0.000261766648,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00392649972,
"min": 0.00392649972,
"max": 0.10866957178,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.007845134474337101,
"min": 0.007650338113307953,
"max": 0.3309972584247589,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.11767701059579849,
"min": 0.10710473358631134,
"max": 2.3169808387756348,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 367.7654320987654,
"min": 342.9887640449438,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29789.0,
"min": 16841.0,
"max": 33538.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5087407146706993,
"min": -0.9999806972280625,
"max": 1.5446112194422925,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 122.20799788832664,
"min": -31.997201651334763,
"max": 137.47039853036404,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5087407146706993,
"min": -0.9999806972280625,
"max": 1.5446112194422925,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 122.20799788832664,
"min": -31.997201651334763,
"max": 137.47039853036404,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.029903462017961076,
"min": 0.02750641659452852,
"max": 6.427782424232539,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.422180423454847,
"min": 2.4076854368977365,
"max": 109.27230121195316,
"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": "1675182810",
"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": "1675184808"
},
"total": 1998.0449856110001,
"count": 1,
"self": 0.3833817839997664,
"children": {
"run_training.setup": {
"total": 0.09547951300010027,
"count": 1,
"self": 0.09547951300010027
},
"TrainerController.start_learning": {
"total": 1997.5661243140003,
"count": 1,
"self": 1.1407022610576405,
"children": {
"TrainerController._reset_env": {
"total": 5.827710047999972,
"count": 1,
"self": 5.827710047999972
},
"TrainerController.advance": {
"total": 1990.5181007799426,
"count": 63743,
"self": 1.184563573983496,
"children": {
"env_step": {
"total": 1355.7159409269464,
"count": 63743,
"self": 1256.4522739329961,
"children": {
"SubprocessEnvManager._take_step": {
"total": 98.54657221294042,
"count": 63743,
"self": 3.9640127118661894,
"children": {
"TorchPolicy.evaluate": {
"total": 94.58255950107423,
"count": 62560,
"self": 31.60515122910192,
"children": {
"TorchPolicy.sample_actions": {
"total": 62.97740827197231,
"count": 62560,
"self": 62.97740827197231
}
}
}
}
},
"workers": {
"total": 0.7170947810097914,
"count": 63743,
"self": 0.0,
"children": {
"worker_root": {
"total": 1994.8710345049644,
"count": 63743,
"is_parallel": true,
"self": 828.0359216209806,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0016320730001098127,
"count": 1,
"is_parallel": true,
"self": 0.0005900010003188072,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010420719997910055,
"count": 8,
"is_parallel": true,
"self": 0.0010420719997910055
}
}
},
"UnityEnvironment.step": {
"total": 0.044336030999829745,
"count": 1,
"is_parallel": true,
"self": 0.0005731079997985944,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004249969999818859,
"count": 1,
"is_parallel": true,
"self": 0.0004249969999818859
},
"communicator.exchange": {
"total": 0.041850004000025365,
"count": 1,
"is_parallel": true,
"self": 0.041850004000025365
},
"steps_from_proto": {
"total": 0.0014879220000239002,
"count": 1,
"is_parallel": true,
"self": 0.0003870070006541937,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011009149993697065,
"count": 8,
"is_parallel": true,
"self": 0.0011009149993697065
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1166.8351128839838,
"count": 63742,
"is_parallel": true,
"self": 26.386677122058927,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 20.82206777092165,
"count": 63742,
"is_parallel": true,
"self": 20.82206777092165
},
"communicator.exchange": {
"total": 1033.9213887280575,
"count": 63742,
"is_parallel": true,
"self": 1033.9213887280575
},
"steps_from_proto": {
"total": 85.7049792629457,
"count": 63742,
"is_parallel": true,
"self": 19.814140387758698,
"children": {
"_process_rank_one_or_two_observation": {
"total": 65.890838875187,
"count": 509936,
"is_parallel": true,
"self": 65.890838875187
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 633.6175962790128,
"count": 63743,
"self": 2.187064913012364,
"children": {
"process_trajectory": {
"total": 136.55067967999935,
"count": 63743,
"self": 136.36776741699964,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1829122629997073,
"count": 2,
"self": 0.1829122629997073
}
}
},
"_update_policy": {
"total": 494.8798516860011,
"count": 448,
"self": 185.0999364590309,
"children": {
"TorchPPOOptimizer.update": {
"total": 309.77991522697016,
"count": 22851,
"self": 309.77991522697016
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.189998309011571e-07,
"count": 1,
"self": 9.189998309011571e-07
},
"TrainerController._save_models": {
"total": 0.07961030600017693,
"count": 1,
"self": 0.0012944330001118942,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07831587300006504,
"count": 1,
"self": 0.07831587300006504
}
}
}
}
}
}
}