schirmacher's picture
First Push
e30a59b
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0355924367904663,
"min": 1.0355924367904663,
"max": 2.873522996902466,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9899.2275390625,
"min": 9899.2275390625,
"max": 29427.75,
"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": 12.56982421875,
"min": 0.23421280086040497,
"max": 12.56982421875,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2451.11572265625,
"min": 45.43728256225586,
"max": 2558.04052734375,
"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": 0.0729952815020749,
"min": 0.060373977550554236,
"max": 0.0729952815020749,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2919811260082996,
"min": 0.24149591020221695,
"max": 0.36090660127685587,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19935917416039636,
"min": 0.09856465959569949,
"max": 0.2954301895464168,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7974366966415855,
"min": 0.39425863838279795,
"max": 1.3588270951135486,
"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": 24.681818181818183,
"min": 2.977272727272727,
"max": 24.795454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1086.0,
"min": 131.0,
"max": 1349.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.681818181818183,
"min": 2.977272727272727,
"max": 24.795454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1086.0,
"min": 131.0,
"max": 1349.0,
"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": "1690054969",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"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": "1690055438"
},
"total": 469.26173766899996,
"count": 1,
"self": 0.4816974180000102,
"children": {
"run_training.setup": {
"total": 0.04920606999996835,
"count": 1,
"self": 0.04920606999996835
},
"TrainerController.start_learning": {
"total": 468.730834181,
"count": 1,
"self": 0.521263438011033,
"children": {
"TrainerController._reset_env": {
"total": 4.997108217999994,
"count": 1,
"self": 4.997108217999994
},
"TrainerController.advance": {
"total": 463.0742297289888,
"count": 18201,
"self": 0.2591047589842219,
"children": {
"env_step": {
"total": 462.8151249700046,
"count": 18201,
"self": 337.3761406440171,
"children": {
"SubprocessEnvManager._take_step": {
"total": 125.17285294699957,
"count": 18201,
"self": 1.6916856340013737,
"children": {
"TorchPolicy.evaluate": {
"total": 123.4811673129982,
"count": 18201,
"self": 123.4811673129982
}
}
},
"workers": {
"total": 0.26613137898795003,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 467.25168795999895,
"count": 18201,
"is_parallel": true,
"self": 223.61884661900012,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002781287000004795,
"count": 1,
"is_parallel": true,
"self": 0.0006781250000358341,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002103161999968961,
"count": 10,
"is_parallel": true,
"self": 0.002103161999968961
}
}
},
"UnityEnvironment.step": {
"total": 0.04567124499999409,
"count": 1,
"is_parallel": true,
"self": 0.0006560290000834357,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000328955999975733,
"count": 1,
"is_parallel": true,
"self": 0.000328955999975733
},
"communicator.exchange": {
"total": 0.042387644999962504,
"count": 1,
"is_parallel": true,
"self": 0.042387644999962504
},
"steps_from_proto": {
"total": 0.002298614999972415,
"count": 1,
"is_parallel": true,
"self": 0.0005464149999738765,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017521999999985383,
"count": 10,
"is_parallel": true,
"self": 0.0017521999999985383
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 243.63284134099882,
"count": 18200,
"is_parallel": true,
"self": 10.404343766009674,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.140114824996488,
"count": 18200,
"is_parallel": true,
"self": 5.140114824996488
},
"communicator.exchange": {
"total": 193.47667416599882,
"count": 18200,
"is_parallel": true,
"self": 193.47667416599882
},
"steps_from_proto": {
"total": 34.611708583993845,
"count": 18200,
"is_parallel": true,
"self": 6.348669215000257,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.26303936899359,
"count": 182000,
"is_parallel": true,
"self": 28.26303936899359
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001597660000243195,
"count": 1,
"self": 0.0001597660000243195,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 459.154669220019,
"count": 428879,
"is_parallel": true,
"self": 9.929764077003938,
"children": {
"process_trajectory": {
"total": 249.33494972701516,
"count": 428879,
"is_parallel": true,
"self": 247.9997545500152,
"children": {
"RLTrainer._checkpoint": {
"total": 1.335195176999946,
"count": 4,
"is_parallel": true,
"self": 1.335195176999946
}
}
},
"_update_policy": {
"total": 199.8899554159999,
"count": 90,
"is_parallel": true,
"self": 82.89979149700554,
"children": {
"TorchPPOOptimizer.update": {
"total": 116.99016391899437,
"count": 4587,
"is_parallel": true,
"self": 116.99016391899437
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13807303000010052,
"count": 1,
"self": 0.0009127850000822946,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13716024500001822,
"count": 1,
"self": 0.13716024500001822
}
}
}
}
}
}
}