Allen Isaac Jose
First Push
1f29d2e
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9530745148658752,
"min": 0.9530745148658752,
"max": 2.864516019821167,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9089.4716796875,
"min": 9089.4716796875,
"max": 29335.509765625,
"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": 12.766042709350586,
"min": 0.20049236714839935,
"max": 12.798537254333496,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2489.37841796875,
"min": 38.8955192565918,
"max": 2623.7001953125,
"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": 0.06913585778948247,
"min": 0.05863117256096802,
"max": 0.0780450091691569,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2765434311579299,
"min": 0.2562365591635599,
"max": 0.3605320039098967,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1925745240467436,
"min": 0.1333204638715103,
"max": 0.2996260090639778,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7702980961869744,
"min": 0.5332818554860412,
"max": 1.3890616499325807,
"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": 25.295454545454547,
"min": 3.227272727272727,
"max": 25.30909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1113.0,
"min": 142.0,
"max": 1392.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.295454545454547,
"min": 3.227272727272727,
"max": 25.30909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1113.0,
"min": 142.0,
"max": 1392.0,
"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": "1673638086",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "1673638511"
},
"total": 425.005321289,
"count": 1,
"self": 0.3876845540000886,
"children": {
"run_training.setup": {
"total": 0.1127530910000587,
"count": 1,
"self": 0.1127530910000587
},
"TrainerController.start_learning": {
"total": 424.50488364399985,
"count": 1,
"self": 0.5140585289930186,
"children": {
"TrainerController._reset_env": {
"total": 9.216224494000016,
"count": 1,
"self": 9.216224494000016
},
"TrainerController.advance": {
"total": 414.6480519020067,
"count": 18201,
"self": 0.24539332200924946,
"children": {
"env_step": {
"total": 414.4026585799975,
"count": 18201,
"self": 270.64105265299895,
"children": {
"SubprocessEnvManager._take_step": {
"total": 143.4990146579978,
"count": 18201,
"self": 1.355350737990193,
"children": {
"TorchPolicy.evaluate": {
"total": 142.1436639200076,
"count": 18201,
"self": 32.14050911299796,
"children": {
"TorchPolicy.sample_actions": {
"total": 110.00315480700965,
"count": 18201,
"self": 110.00315480700965
}
}
}
}
},
"workers": {
"total": 0.2625912690007226,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 423.40809923302095,
"count": 18201,
"is_parallel": true,
"self": 205.6340764820443,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006396113999926456,
"count": 1,
"is_parallel": true,
"self": 0.003923117000113052,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002472996999813404,
"count": 10,
"is_parallel": true,
"self": 0.002472996999813404
}
}
},
"UnityEnvironment.step": {
"total": 0.03925066000010702,
"count": 1,
"is_parallel": true,
"self": 0.000524775000030786,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002362210000228515,
"count": 1,
"is_parallel": true,
"self": 0.0002362210000228515
},
"communicator.exchange": {
"total": 0.03662973099994815,
"count": 1,
"is_parallel": true,
"self": 0.03662973099994815
},
"steps_from_proto": {
"total": 0.0018599330001052294,
"count": 1,
"is_parallel": true,
"self": 0.0004047989998525736,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014551340002526558,
"count": 10,
"is_parallel": true,
"self": 0.0014551340002526558
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 217.77402275097666,
"count": 18200,
"is_parallel": true,
"self": 8.297309188978488,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.934001914997225,
"count": 18200,
"is_parallel": true,
"self": 4.934001914997225
},
"communicator.exchange": {
"total": 172.3905750969932,
"count": 18200,
"is_parallel": true,
"self": 172.3905750969932
},
"steps_from_proto": {
"total": 32.152136550007754,
"count": 18200,
"is_parallel": true,
"self": 6.404167893053682,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.74796865695407,
"count": 182000,
"is_parallel": true,
"self": 25.74796865695407
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.329000012148754e-05,
"count": 1,
"self": 4.329000012148754e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 411.85274590902463,
"count": 333896,
"is_parallel": true,
"self": 8.813797692023854,
"children": {
"process_trajectory": {
"total": 235.60109547400134,
"count": 333896,
"is_parallel": true,
"self": 234.88471862600113,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7163768480002091,
"count": 4,
"is_parallel": true,
"self": 0.7163768480002091
}
}
},
"_update_policy": {
"total": 167.43785274299944,
"count": 90,
"is_parallel": true,
"self": 43.631197302996725,
"children": {
"TorchPPOOptimizer.update": {
"total": 123.80665544000271,
"count": 4587,
"is_parallel": true,
"self": 123.80665544000271
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12650542899996253,
"count": 1,
"self": 0.0008503879998897901,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12565504100007274,
"count": 1,
"self": 0.12565504100007274
}
}
}
}
}
}
}