scarface247's picture
First Push
b5a5c1d verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8614168763160706,
"min": 0.8614168763160706,
"max": 2.8737785816192627,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8224.80859375,
"min": 8224.80859375,
"max": 29430.3671875,
"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": 12.5637845993042,
"min": 0.41138774156570435,
"max": 12.5637845993042,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2449.93798828125,
"min": 79.80921936035156,
"max": 2499.950439453125,
"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": 0.0687858863456732,
"min": 0.060881359333072003,
"max": 0.07634648979623235,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2751435453826928,
"min": 0.24908137792269422,
"max": 0.38173244898116176,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19916357983853303,
"min": 0.13139538862057687,
"max": 0.2779856661955516,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7966543193541321,
"min": 0.5255815544823075,
"max": 1.389928330977758,
"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": 25.704545454545453,
"min": 3.8636363636363638,
"max": 25.704545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1131.0,
"min": 170.0,
"max": 1359.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.704545454545453,
"min": 3.8636363636363638,
"max": 25.704545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1131.0,
"min": 170.0,
"max": 1359.0,
"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": "1716190331",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1716190771"
},
"total": 439.45354092499997,
"count": 1,
"self": 0.4500302050000755,
"children": {
"run_training.setup": {
"total": 0.06416042499995456,
"count": 1,
"self": 0.06416042499995456
},
"TrainerController.start_learning": {
"total": 438.93935029499994,
"count": 1,
"self": 0.5288441389986929,
"children": {
"TrainerController._reset_env": {
"total": 3.1318292450000627,
"count": 1,
"self": 3.1318292450000627
},
"TrainerController.advance": {
"total": 435.190598605001,
"count": 18199,
"self": 0.24648384599436213,
"children": {
"env_step": {
"total": 434.94411475900665,
"count": 18199,
"self": 284.5709684140347,
"children": {
"SubprocessEnvManager._take_step": {
"total": 150.10649717300817,
"count": 18199,
"self": 1.3999812090194155,
"children": {
"TorchPolicy.evaluate": {
"total": 148.70651596398875,
"count": 18199,
"self": 148.70651596398875
}
}
},
"workers": {
"total": 0.26664917196376337,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 437.76622135497973,
"count": 18199,
"is_parallel": true,
"self": 220.07845165398226,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005943345000105182,
"count": 1,
"is_parallel": true,
"self": 0.004232747000514792,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017105979995903908,
"count": 10,
"is_parallel": true,
"self": 0.0017105979995903908
}
}
},
"UnityEnvironment.step": {
"total": 0.04910628099992209,
"count": 1,
"is_parallel": true,
"self": 0.0008275499997125735,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041954700009227963,
"count": 1,
"is_parallel": true,
"self": 0.00041954700009227963
},
"communicator.exchange": {
"total": 0.0453367249999701,
"count": 1,
"is_parallel": true,
"self": 0.0453367249999701
},
"steps_from_proto": {
"total": 0.002522459000147137,
"count": 1,
"is_parallel": true,
"self": 0.0006349720001708192,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018874869999763177,
"count": 10,
"is_parallel": true,
"self": 0.0018874869999763177
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 217.68776970099748,
"count": 18198,
"is_parallel": true,
"self": 9.986726268986104,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.19576238800164,
"count": 18198,
"is_parallel": true,
"self": 5.19576238800164
},
"communicator.exchange": {
"total": 170.12304096899948,
"count": 18198,
"is_parallel": true,
"self": 170.12304096899948
},
"steps_from_proto": {
"total": 32.38224007501026,
"count": 18198,
"is_parallel": true,
"self": 5.988824148039157,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.3934159269711,
"count": 181980,
"is_parallel": true,
"self": 26.3934159269711
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00017196900012095284,
"count": 1,
"self": 0.00017196900012095284,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 429.97355859708614,
"count": 659404,
"is_parallel": true,
"self": 13.54660356407544,
"children": {
"process_trajectory": {
"total": 236.63949625701116,
"count": 659404,
"is_parallel": true,
"self": 236.063571134011,
"children": {
"RLTrainer._checkpoint": {
"total": 0.575925123000161,
"count": 4,
"is_parallel": true,
"self": 0.575925123000161
}
}
},
"_update_policy": {
"total": 179.78745877599954,
"count": 90,
"is_parallel": true,
"self": 58.972272953004904,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.81518582299464,
"count": 4587,
"is_parallel": true,
"self": 120.81518582299464
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08790633700004946,
"count": 1,
"self": 0.0009408729999904608,
"children": {
"RLTrainer._checkpoint": {
"total": 0.086965464000059,
"count": 1,
"self": 0.086965464000059
}
}
}
}
}
}
}