brahamdp's picture
First Push
f6074c1
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0916725397109985,
"min": 1.0916725397109985,
"max": 2.866286039352417,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10495.33984375,
"min": 10495.33984375,
"max": 29385.1640625,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.83810806274414,
"min": 0.3127480447292328,
"max": 12.83810806274414,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2503.43115234375,
"min": 60.67312240600586,
"max": 2570.5498046875,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06463308151704077,
"min": 0.061557856241997076,
"max": 0.07594923340551687,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25853232606816307,
"min": 0.25120711955013597,
"max": 0.36050626894176074,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20678827349169582,
"min": 0.13724413788968734,
"max": 0.29390164347840286,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8271530939667833,
"min": 0.5489765515587494,
"max": 1.3626218219013775,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.272727272727273,
"min": 3.727272727272727,
"max": 25.272727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1112.0,
"min": 164.0,
"max": 1381.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.272727272727273,
"min": 3.727272727272727,
"max": 25.272727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1112.0,
"min": 164.0,
"max": 1381.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1678908832",
"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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1678909436"
},
"total": 603.1570942130002,
"count": 1,
"self": 0.9671351340007277,
"children": {
"run_training.setup": {
"total": 0.12644409799986533,
"count": 1,
"self": 0.12644409799986533
},
"TrainerController.start_learning": {
"total": 602.0635149809996,
"count": 1,
"self": 0.8805759500223758,
"children": {
"TrainerController._reset_env": {
"total": 11.085533170999952,
"count": 1,
"self": 11.085533170999952
},
"TrainerController.advance": {
"total": 589.8449245879779,
"count": 18230,
"self": 0.44751812599861296,
"children": {
"env_step": {
"total": 589.3974064619792,
"count": 18230,
"self": 474.8945632559662,
"children": {
"SubprocessEnvManager._take_step": {
"total": 114.09492809697122,
"count": 18230,
"self": 3.5316315960212705,
"children": {
"TorchPolicy.evaluate": {
"total": 110.56329650094995,
"count": 18230,
"self": 110.56329650094995
}
}
},
"workers": {
"total": 0.4079151090418236,
"count": 18230,
"self": 0.0,
"children": {
"worker_root": {
"total": 599.8327695670823,
"count": 18230,
"is_parallel": true,
"self": 271.6171097900715,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.009185656000227027,
"count": 1,
"is_parallel": true,
"self": 0.005951879000804183,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003233776999422844,
"count": 10,
"is_parallel": true,
"self": 0.003233776999422844
}
}
},
"UnityEnvironment.step": {
"total": 0.04327836300035415,
"count": 1,
"is_parallel": true,
"self": 0.0007077100003698433,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004848149997087603,
"count": 1,
"is_parallel": true,
"self": 0.0004848149997087603
},
"communicator.exchange": {
"total": 0.0397660920002636,
"count": 1,
"is_parallel": true,
"self": 0.0397660920002636
},
"steps_from_proto": {
"total": 0.0023197460000119463,
"count": 1,
"is_parallel": true,
"self": 0.0004484420001062972,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001871303999905649,
"count": 10,
"is_parallel": true,
"self": 0.001871303999905649
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 328.21565977701084,
"count": 18229,
"is_parallel": true,
"self": 13.897658324981876,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.400764338950921,
"count": 18229,
"is_parallel": true,
"self": 7.400764338950921
},
"communicator.exchange": {
"total": 262.9759060730298,
"count": 18229,
"is_parallel": true,
"self": 262.9759060730298
},
"steps_from_proto": {
"total": 43.941331040048226,
"count": 18229,
"is_parallel": true,
"self": 9.077348758828975,
"children": {
"_process_rank_one_or_two_observation": {
"total": 34.86398228121925,
"count": 182290,
"is_parallel": true,
"self": 34.86398228121925
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00017810600002121646,
"count": 1,
"self": 0.00017810600002121646,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 584.8032918843987,
"count": 569829,
"is_parallel": true,
"self": 15.046348148558536,
"children": {
"process_trajectory": {
"total": 315.64055471284155,
"count": 569829,
"is_parallel": true,
"self": 313.40893543484117,
"children": {
"RLTrainer._checkpoint": {
"total": 2.2316192780003803,
"count": 4,
"is_parallel": true,
"self": 2.2316192780003803
}
}
},
"_update_policy": {
"total": 254.11638902299865,
"count": 90,
"is_parallel": true,
"self": 85.02930216099685,
"children": {
"TorchPPOOptimizer.update": {
"total": 169.0870868620018,
"count": 4587,
"is_parallel": true,
"self": 169.0870868620018
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.25230316599936486,
"count": 1,
"self": 0.00143773199943098,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2508654339999339,
"count": 1,
"self": 0.2508654339999339
}
}
}
}
}
}
}