asubiabre's picture
First Push
bcf7bc9
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9724612832069397,
"min": 0.9724612832069397,
"max": 2.8692870140075684,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9285.060546875,
"min": 9285.060546875,
"max": 29447.4921875,
"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": 12.825143814086914,
"min": 0.3441714644432068,
"max": 12.825143814086914,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2500.903076171875,
"min": 66.7692642211914,
"max": 2606.40185546875,
"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": 0.06800684303672432,
"min": 0.06483693970243193,
"max": 0.07519464534404915,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27202737214689726,
"min": 0.2593477588097277,
"max": 0.35783123639960057,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1969524847672266,
"min": 0.13625906355902734,
"max": 0.27082096273992573,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7878099390689064,
"min": 0.5450362542361094,
"max": 1.3230704749916111,
"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": 24.954545454545453,
"min": 3.840909090909091,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1098.0,
"min": 169.0,
"max": 1395.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.954545454545453,
"min": 3.840909090909091,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1098.0,
"min": 169.0,
"max": 1395.0,
"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": "1681305569",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1681306030"
},
"total": 460.794939,
"count": 1,
"self": 0.43410736900005986,
"children": {
"run_training.setup": {
"total": 0.10791987199996811,
"count": 1,
"self": 0.10791987199996811
},
"TrainerController.start_learning": {
"total": 460.25291175899997,
"count": 1,
"self": 0.5724274830039917,
"children": {
"TrainerController._reset_env": {
"total": 4.177920207999989,
"count": 1,
"self": 4.177920207999989
},
"TrainerController.advance": {
"total": 455.367405976996,
"count": 18201,
"self": 0.27892240099936316,
"children": {
"env_step": {
"total": 455.08848357599663,
"count": 18201,
"self": 333.52438552999433,
"children": {
"SubprocessEnvManager._take_step": {
"total": 121.28648581099975,
"count": 18201,
"self": 1.6604697630004353,
"children": {
"TorchPolicy.evaluate": {
"total": 119.62601604799931,
"count": 18201,
"self": 119.62601604799931
}
}
},
"workers": {
"total": 0.2776122350025503,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 458.51660710400023,
"count": 18201,
"is_parallel": true,
"self": 213.57772685999976,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005029286000024058,
"count": 1,
"is_parallel": true,
"self": 0.003591030000052342,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001438255999971716,
"count": 10,
"is_parallel": true,
"self": 0.001438255999971716
}
}
},
"UnityEnvironment.step": {
"total": 0.1043417099999715,
"count": 1,
"is_parallel": true,
"self": 0.0006198369999310671,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00048051300001361597,
"count": 1,
"is_parallel": true,
"self": 0.00048051300001361597
},
"communicator.exchange": {
"total": 0.10154244400001744,
"count": 1,
"is_parallel": true,
"self": 0.10154244400001744
},
"steps_from_proto": {
"total": 0.0016989160000093761,
"count": 1,
"is_parallel": true,
"self": 0.00034227699995881267,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013566390000505635,
"count": 10,
"is_parallel": true,
"self": 0.0013566390000505635
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 244.93888024400047,
"count": 18200,
"is_parallel": true,
"self": 10.093886306995898,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.341057600012675,
"count": 18200,
"is_parallel": true,
"self": 5.341057600012675
},
"communicator.exchange": {
"total": 197.83208475898914,
"count": 18200,
"is_parallel": true,
"self": 197.83208475898914
},
"steps_from_proto": {
"total": 31.67185157800276,
"count": 18200,
"is_parallel": true,
"self": 6.403613946998348,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.26823763100441,
"count": 182000,
"is_parallel": true,
"self": 25.26823763100441
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001290679999783606,
"count": 1,
"self": 0.0001290679999783606,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 452.09922046303836,
"count": 412427,
"is_parallel": true,
"self": 9.70056882505537,
"children": {
"process_trajectory": {
"total": 248.46145756398312,
"count": 412427,
"is_parallel": true,
"self": 247.7142565219831,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7472010420000288,
"count": 4,
"is_parallel": true,
"self": 0.7472010420000288
}
}
},
"_update_policy": {
"total": 193.93719407399988,
"count": 90,
"is_parallel": true,
"self": 72.66001472200048,
"children": {
"TorchPPOOptimizer.update": {
"total": 121.2771793519994,
"count": 4587,
"is_parallel": true,
"self": 121.2771793519994
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1350290230000155,
"count": 1,
"self": 0.0008797490000915786,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13414927399992393,
"count": 1,
"self": 0.13414927399992393
}
}
}
}
}
}
}