tux's picture
Second Push
9fec05b
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.5968165993690491,
"min": 0.5571640729904175,
"max": 0.6767531037330627,
"count": 40
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6059.47900390625,
"min": 5325.931640625,
"max": 6923.18408203125,
"count": 40
},
"SnowballTarget.Step.mean": {
"value": 799936.0,
"min": 409960.0,
"max": 799936.0,
"count": 40
},
"SnowballTarget.Step.sum": {
"value": 799936.0,
"min": 409960.0,
"max": 799936.0,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.41425609588623,
"min": 13.004890441894531,
"max": 13.57406234741211,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2602.36572265625,
"min": 2496.93896484375,
"max": 2773.11474609375,
"count": 40
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 40
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 40
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.061910159999635936,
"min": 0.061336681612666845,
"max": 0.07427937125746623,
"count": 40
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24764063999854374,
"min": 0.2468815198483165,
"max": 0.3713968562873311,
"count": 40
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19015458178724728,
"min": 0.17026756718462588,
"max": 0.21914647823455286,
"count": 40
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7606183271489891,
"min": 0.6810702687385035,
"max": 1.0957323911727643,
"count": 40
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 6.315993685000017e-07,
"min": 6.315993685000017e-07,
"max": 4.93065506935e-05,
"count": 40
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 2.526397474000007e-06,
"min": 2.526397474000007e-06,
"max": 0.00024034525965500002,
"count": 40
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.1006315,
"min": 0.1006315,
"max": 0.14930650000000004,
"count": 40
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.402526,
"min": 0.402526,
"max": 0.7403449999999999,
"count": 40
},
"SnowballTarget.Policy.Beta.mean": {
"value": 4.151185000000009e-05,
"min": 4.151185000000009e-05,
"max": 0.0024703943500000002,
"count": 40
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00016604740000000036,
"min": 0.00016604740000000036,
"max": 0.012043215500000001,
"count": 40
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.227272727272727,
"min": 25.40909090909091,
"max": 26.931818181818183,
"count": 40
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1154.0,
"min": 1118.0,
"max": 1466.0,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.227272727272727,
"min": 25.40909090909091,
"max": 26.931818181818183,
"count": 40
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1154.0,
"min": 1118.0,
"max": 1466.0,
"count": 40
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1687089782",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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 --resume",
"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": "1687090700"
},
"total": 918.2208542879998,
"count": 1,
"self": 0.43315540999992663,
"children": {
"run_training.setup": {
"total": 0.06538150100004714,
"count": 1,
"self": 0.06538150100004714
},
"TrainerController.start_learning": {
"total": 917.7223173769999,
"count": 1,
"self": 1.0854520769435112,
"children": {
"TrainerController._reset_env": {
"total": 4.475140212000042,
"count": 1,
"self": 4.475140212000042
},
"TrainerController.advance": {
"total": 912.0262006520552,
"count": 36403,
"self": 0.5186194420703032,
"children": {
"env_step": {
"total": 911.5075812099849,
"count": 36403,
"self": 661.585453451039,
"children": {
"SubprocessEnvManager._take_step": {
"total": 249.4243560518662,
"count": 36403,
"self": 3.537187362854638,
"children": {
"TorchPolicy.evaluate": {
"total": 245.88716868901156,
"count": 36403,
"self": 245.88716868901156
}
}
},
"workers": {
"total": 0.49777170707966434,
"count": 36403,
"self": 0.0,
"children": {
"worker_root": {
"total": 914.748001949014,
"count": 36403,
"is_parallel": true,
"self": 431.38485729802323,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0030115030003798893,
"count": 1,
"is_parallel": true,
"self": 0.0008040019993131864,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002207501001066703,
"count": 10,
"is_parallel": true,
"self": 0.002207501001066703
}
}
},
"UnityEnvironment.step": {
"total": 0.04861170599997422,
"count": 1,
"is_parallel": true,
"self": 0.0006083189991841209,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003593700002966216,
"count": 1,
"is_parallel": true,
"self": 0.0003593700002966216
},
"communicator.exchange": {
"total": 0.04547960800027795,
"count": 1,
"is_parallel": true,
"self": 0.04547960800027795
},
"steps_from_proto": {
"total": 0.002164409000215528,
"count": 1,
"is_parallel": true,
"self": 0.0003751030008061207,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017893059994094074,
"count": 10,
"is_parallel": true,
"self": 0.0017893059994094074
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 483.36314465099076,
"count": 36402,
"is_parallel": true,
"self": 20.174957186999563,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 10.086550404983427,
"count": 36402,
"is_parallel": true,
"self": 10.086550404983427
},
"communicator.exchange": {
"total": 385.741071097068,
"count": 36402,
"is_parallel": true,
"self": 385.741071097068
},
"steps_from_proto": {
"total": 67.36056596193976,
"count": 36402,
"is_parallel": true,
"self": 12.244435754751066,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.11613020718869,
"count": 364020,
"is_parallel": true,
"self": 55.11613020718869
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0003044640006919508,
"count": 1,
"self": 0.0003044640006919508,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 904.3236935601626,
"count": 857395,
"is_parallel": true,
"self": 20.16862705125277,
"children": {
"process_trajectory": {
"total": 491.96500578791256,
"count": 857395,
"is_parallel": true,
"self": 489.68250432491277,
"children": {
"RLTrainer._checkpoint": {
"total": 2.2825014629997895,
"count": 8,
"is_parallel": true,
"self": 2.2825014629997895
}
}
},
"_update_policy": {
"total": 392.1900607209973,
"count": 181,
"is_parallel": true,
"self": 149.23636622900904,
"children": {
"TorchPPOOptimizer.update": {
"total": 242.95369449198824,
"count": 9228,
"is_parallel": true,
"self": 242.95369449198824
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1352199720004137,
"count": 1,
"self": 0.0010199400003330084,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13420003200008068,
"count": 1,
"self": 0.13420003200008068
}
}
}
}
}
}
}