Frorozcol's picture
First Push
6eb4b6d
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.1537280082702637,
"min": 1.1537280082702637,
"max": 2.859524726867676,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 11015.794921875,
"min": 11015.794921875,
"max": 29378.7578125,
"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": 11.899356842041016,
"min": 0.2650832235813141,
"max": 11.899356842041016,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2320.37451171875,
"min": 51.4261474609375,
"max": 2361.65234375,
"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": 0.06538104034495751,
"min": 0.0619205400170804,
"max": 0.0758219649764143,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26152416137983003,
"min": 0.24777641676793755,
"max": 0.3639248702332706,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22554820301193818,
"min": 0.11853166633769505,
"max": 0.2730792259760932,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9021928120477527,
"min": 0.4741266653507802,
"max": 1.33697257789911,
"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": 24.227272727272727,
"min": 3.409090909090909,
"max": 24.227272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1066.0,
"min": 150.0,
"max": 1275.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.227272727272727,
"min": 3.409090909090909,
"max": 24.227272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1066.0,
"min": 150.0,
"max": 1275.0,
"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": "1684417082",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1684417525"
},
"total": 443.071859987,
"count": 1,
"self": 0.43424033900004133,
"children": {
"run_training.setup": {
"total": 0.04012749399998938,
"count": 1,
"self": 0.04012749399998938
},
"TrainerController.start_learning": {
"total": 442.59749215399995,
"count": 1,
"self": 0.4897861799959742,
"children": {
"TrainerController._reset_env": {
"total": 3.79991589399998,
"count": 1,
"self": 3.79991589399998
},
"TrainerController.advance": {
"total": 438.1754404700039,
"count": 18201,
"self": 0.23193787700472512,
"children": {
"env_step": {
"total": 437.94350259299915,
"count": 18201,
"self": 318.67186763999104,
"children": {
"SubprocessEnvManager._take_step": {
"total": 119.02644232300469,
"count": 18201,
"self": 1.651348755007291,
"children": {
"TorchPolicy.evaluate": {
"total": 117.3750935679974,
"count": 18201,
"self": 117.3750935679974
}
}
},
"workers": {
"total": 0.24519263000343017,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 441.2454036259967,
"count": 18201,
"is_parallel": true,
"self": 209.7166741120006,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005354994000015267,
"count": 1,
"is_parallel": true,
"self": 0.004033570999922631,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013214230000926364,
"count": 10,
"is_parallel": true,
"self": 0.0013214230000926364
}
}
},
"UnityEnvironment.step": {
"total": 0.03652758799995581,
"count": 1,
"is_parallel": true,
"self": 0.0005720199999359465,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039184999997132763,
"count": 1,
"is_parallel": true,
"self": 0.00039184999997132763
},
"communicator.exchange": {
"total": 0.033540884000046844,
"count": 1,
"is_parallel": true,
"self": 0.033540884000046844
},
"steps_from_proto": {
"total": 0.0020228340000016942,
"count": 1,
"is_parallel": true,
"self": 0.00039329499998075335,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016295390000209409,
"count": 10,
"is_parallel": true,
"self": 0.0016295390000209409
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 231.5287295139961,
"count": 18200,
"is_parallel": true,
"self": 9.160689358000468,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.018248543006109,
"count": 18200,
"is_parallel": true,
"self": 5.018248543006109
},
"communicator.exchange": {
"total": 186.09655039799514,
"count": 18200,
"is_parallel": true,
"self": 186.09655039799514
},
"steps_from_proto": {
"total": 31.253241214994375,
"count": 18200,
"is_parallel": true,
"self": 5.795779145010613,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.457462069983762,
"count": 182000,
"is_parallel": true,
"self": 25.457462069983762
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.876700005406747e-05,
"count": 1,
"self": 9.876700005406747e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 434.87593091102053,
"count": 409756,
"is_parallel": true,
"self": 9.033682787069665,
"children": {
"process_trajectory": {
"total": 236.97745262295064,
"count": 409756,
"is_parallel": true,
"self": 235.92218633795062,
"children": {
"RLTrainer._checkpoint": {
"total": 1.055266285000016,
"count": 4,
"is_parallel": true,
"self": 1.055266285000016
}
}
},
"_update_policy": {
"total": 188.86479550100023,
"count": 90,
"is_parallel": true,
"self": 74.3703111679996,
"children": {
"TorchPPOOptimizer.update": {
"total": 114.49448433300063,
"count": 4587,
"is_parallel": true,
"self": 114.49448433300063
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1322508430000653,
"count": 1,
"self": 0.0008068400001093323,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13144400299995596,
"count": 1,
"self": 0.13144400299995596
}
}
}
}
}
}
}