c72599's picture
First Push
db4fb85
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.932823657989502,
"min": 0.932823657989502,
"max": 2.8705639839172363,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8916.861328125,
"min": 8916.861328125,
"max": 29397.4453125,
"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": 12.712503433227539,
"min": 0.4094078242778778,
"max": 12.754109382629395,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2478.938232421875,
"min": 79.42511749267578,
"max": 2601.83837890625,
"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": 0.07686127456919148,
"min": 0.06167914487441165,
"max": 0.07686127456919148,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3074450982767659,
"min": 0.2467165794976466,
"max": 0.3764901345757786,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21387779106404267,
"min": 0.10819555682646037,
"max": 0.29195954044367756,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8555111642561707,
"min": 0.4327822273058415,
"max": 1.44863534645707,
"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": 24.818181818181817,
"min": 3.0681818181818183,
"max": 25.29090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1092.0,
"min": 135.0,
"max": 1391.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.818181818181817,
"min": 3.0681818181818183,
"max": 25.29090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1092.0,
"min": 135.0,
"max": 1391.0,
"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": "1688750744",
"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",
"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": "1688751266"
},
"total": 521.504368556,
"count": 1,
"self": 0.4374246239999593,
"children": {
"run_training.setup": {
"total": 0.04335389900006703,
"count": 1,
"self": 0.04335389900006703
},
"TrainerController.start_learning": {
"total": 521.023590033,
"count": 1,
"self": 0.6232666339882371,
"children": {
"TrainerController._reset_env": {
"total": 4.083958187999997,
"count": 1,
"self": 4.083958187999997
},
"TrainerController.advance": {
"total": 516.1646947400118,
"count": 18202,
"self": 0.3163864030168497,
"children": {
"env_step": {
"total": 515.8483083369949,
"count": 18202,
"self": 374.9713479040104,
"children": {
"SubprocessEnvManager._take_step": {
"total": 140.56644765299086,
"count": 18202,
"self": 2.089119516978826,
"children": {
"TorchPolicy.evaluate": {
"total": 138.47732813601203,
"count": 18202,
"self": 138.47732813601203
}
}
},
"workers": {
"total": 0.31051277999370086,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 519.2761485059938,
"count": 18202,
"is_parallel": true,
"self": 245.15994847099148,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00626207000004797,
"count": 1,
"is_parallel": true,
"self": 0.004308811000100832,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019532589999471384,
"count": 10,
"is_parallel": true,
"self": 0.0019532589999471384
}
}
},
"UnityEnvironment.step": {
"total": 0.04769031900002574,
"count": 1,
"is_parallel": true,
"self": 0.0007404919999771664,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003676720000385103,
"count": 1,
"is_parallel": true,
"self": 0.0003676720000385103
},
"communicator.exchange": {
"total": 0.04352880900000855,
"count": 1,
"is_parallel": true,
"self": 0.04352880900000855
},
"steps_from_proto": {
"total": 0.003053346000001511,
"count": 1,
"is_parallel": true,
"self": 0.0005927890000521074,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0024605569999494037,
"count": 10,
"is_parallel": true,
"self": 0.0024605569999494037
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 274.1162000350023,
"count": 18201,
"is_parallel": true,
"self": 11.523521149006456,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.003918475998034,
"count": 18201,
"is_parallel": true,
"self": 6.003918475998034
},
"communicator.exchange": {
"total": 215.0373808709977,
"count": 18201,
"is_parallel": true,
"self": 215.0373808709977
},
"steps_from_proto": {
"total": 41.551379539000095,
"count": 18201,
"is_parallel": true,
"self": 7.45318238703112,
"children": {
"_process_rank_one_or_two_observation": {
"total": 34.098197151968975,
"count": 182010,
"is_parallel": true,
"self": 34.098197151968975
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00017772799992599175,
"count": 1,
"self": 0.00017772799992599175,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 511.7890118839583,
"count": 504122,
"is_parallel": true,
"self": 11.954311730890367,
"children": {
"process_trajectory": {
"total": 281.8135777050686,
"count": 504122,
"is_parallel": true,
"self": 280.73557729606864,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0780004089999693,
"count": 4,
"is_parallel": true,
"self": 1.0780004089999693
}
}
},
"_update_policy": {
"total": 218.02112244799935,
"count": 90,
"is_parallel": true,
"self": 86.9125078640019,
"children": {
"TorchPPOOptimizer.update": {
"total": 131.10861458399745,
"count": 4587,
"is_parallel": true,
"self": 131.10861458399745
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15149274300006255,
"count": 1,
"self": 0.0009553659999710362,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1505373770000915,
"count": 1,
"self": 0.1505373770000915
}
}
}
}
}
}
}