yizhangliu's picture
First Push
5fff96c
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9801499247550964,
"min": 0.9801499247550964,
"max": 2.848653793334961,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9358.4716796875,
"min": 9358.4716796875,
"max": 29173.0625,
"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": 12.932892799377441,
"min": 0.45183783769607544,
"max": 12.932892799377441,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2521.9140625,
"min": 87.65653991699219,
"max": 2601.8349609375,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06746099280437692,
"min": 0.06304459071372334,
"max": 0.07384249190862666,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2698439712175077,
"min": 0.25217836285489337,
"max": 0.3504046027766319,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20069045347033762,
"min": 0.12671341734148525,
"max": 0.27639007568359375,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8027618138813505,
"min": 0.506853669365941,
"max": 1.3102136993525075,
"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": 25.75,
"min": 3.727272727272727,
"max": 25.763636363636362,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1133.0,
"min": 164.0,
"max": 1417.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.75,
"min": 3.727272727272727,
"max": 25.763636363636362,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1133.0,
"min": 164.0,
"max": 1417.0,
"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": "1675004097",
"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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1675004552"
},
"total": 454.45679884200007,
"count": 1,
"self": 0.39026429500006543,
"children": {
"run_training.setup": {
"total": 0.11031624999998257,
"count": 1,
"self": 0.11031624999998257
},
"TrainerController.start_learning": {
"total": 453.956218297,
"count": 1,
"self": 0.5524054909954543,
"children": {
"TrainerController._reset_env": {
"total": 10.424001574000044,
"count": 1,
"self": 10.424001574000044
},
"TrainerController.advance": {
"total": 442.8582730060044,
"count": 18204,
"self": 0.2936946260095965,
"children": {
"env_step": {
"total": 442.5645783799948,
"count": 18204,
"self": 287.21356310998874,
"children": {
"SubprocessEnvManager._take_step": {
"total": 155.0687227870053,
"count": 18204,
"self": 1.4754746440131612,
"children": {
"TorchPolicy.evaluate": {
"total": 153.59324814299214,
"count": 18204,
"self": 34.54891021199791,
"children": {
"TorchPolicy.sample_actions": {
"total": 119.04433793099423,
"count": 18204,
"self": 119.04433793099423
}
}
}
}
},
"workers": {
"total": 0.2822924830007878,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 452.7127753230051,
"count": 18204,
"is_parallel": true,
"self": 219.7690805389983,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006800049999981184,
"count": 1,
"is_parallel": true,
"self": 0.003817802999947162,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0029822470000340218,
"count": 10,
"is_parallel": true,
"self": 0.0029822470000340218
}
}
},
"UnityEnvironment.step": {
"total": 0.032203272000003835,
"count": 1,
"is_parallel": true,
"self": 0.0005038289999674816,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002955859999929089,
"count": 1,
"is_parallel": true,
"self": 0.0002955859999929089
},
"communicator.exchange": {
"total": 0.029564854000000196,
"count": 1,
"is_parallel": true,
"self": 0.029564854000000196
},
"steps_from_proto": {
"total": 0.001839003000043249,
"count": 1,
"is_parallel": true,
"self": 0.0004700280001088686,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013689749999343803,
"count": 10,
"is_parallel": true,
"self": 0.0013689749999343803
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 232.94369478400677,
"count": 18203,
"is_parallel": true,
"self": 8.79857449503561,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.374904884992986,
"count": 18203,
"is_parallel": true,
"self": 5.374904884992986
},
"communicator.exchange": {
"total": 186.20539300098648,
"count": 18203,
"is_parallel": true,
"self": 186.20539300098648
},
"steps_from_proto": {
"total": 32.564822402991695,
"count": 18203,
"is_parallel": true,
"self": 6.993897821976873,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.570924581014822,
"count": 182030,
"is_parallel": true,
"self": 25.570924581014822
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.971500004558038e-05,
"count": 1,
"self": 4.971500004558038e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 439.475108999941,
"count": 357429,
"is_parallel": true,
"self": 10.133931925964646,
"children": {
"process_trajectory": {
"total": 253.55296981897658,
"count": 357429,
"is_parallel": true,
"self": 252.73258213897662,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8203876799999534,
"count": 4,
"is_parallel": true,
"self": 0.8203876799999534
}
}
},
"_update_policy": {
"total": 175.7882072549998,
"count": 90,
"is_parallel": true,
"self": 41.76263768199931,
"children": {
"TorchPPOOptimizer.update": {
"total": 134.0255695730005,
"count": 4587,
"is_parallel": true,
"self": 134.0255695730005
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12148851100005231,
"count": 1,
"self": 0.0008301630000460136,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1206583480000063,
"count": 1,
"self": 0.1206583480000063
}
}
}
}
}
}
}