SebastianS's picture
First Push
35fab6b
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8463424444198608,
"min": 0.8463424444198608,
"max": 2.8637967109680176,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8080.8779296875,
"min": 8080.8779296875,
"max": 29454.150390625,
"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": 13.019500732421875,
"min": 0.38318145275115967,
"max": 13.019500732421875,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2538.802734375,
"min": 74.33720397949219,
"max": 2647.3583984375,
"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": 0.06698385346188683,
"min": 0.059828251793777446,
"max": 0.07177303997534681,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2679354138475473,
"min": 0.25132078356845716,
"max": 0.3539253678172827,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21567971712233974,
"min": 0.10263377746028424,
"max": 0.28430878721615843,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.862718868489359,
"min": 0.41053510984113695,
"max": 1.3469297599558738,
"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": 25.136363636363637,
"min": 3.1363636363636362,
"max": 25.854545454545455,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1106.0,
"min": 138.0,
"max": 1422.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.136363636363637,
"min": 3.1363636363636362,
"max": 25.854545454545455,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1106.0,
"min": 138.0,
"max": 1422.0,
"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": "1677358065",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.22.4",
"end_time_seconds": "1677358534"
},
"total": 468.45359840799983,
"count": 1,
"self": 0.37807077499974184,
"children": {
"run_training.setup": {
"total": 0.17035824200002025,
"count": 1,
"self": 0.17035824200002025
},
"TrainerController.start_learning": {
"total": 467.9051693910001,
"count": 1,
"self": 0.6096110519806643,
"children": {
"TrainerController._reset_env": {
"total": 6.701837172000069,
"count": 1,
"self": 6.701837172000069
},
"TrainerController.advance": {
"total": 460.4690131860193,
"count": 18201,
"self": 0.2963213430689393,
"children": {
"env_step": {
"total": 460.17269184295037,
"count": 18201,
"self": 318.6896281050376,
"children": {
"SubprocessEnvManager._take_step": {
"total": 141.19303283994532,
"count": 18201,
"self": 1.5418389629530793,
"children": {
"TorchPolicy.evaluate": {
"total": 139.65119387699224,
"count": 18201,
"self": 30.96793973695776,
"children": {
"TorchPolicy.sample_actions": {
"total": 108.68325414003448,
"count": 18201,
"self": 108.68325414003448
}
}
}
}
},
"workers": {
"total": 0.2900308979674264,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 466.30022365498735,
"count": 18201,
"is_parallel": true,
"self": 223.31751402199689,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0028386889998728293,
"count": 1,
"is_parallel": true,
"self": 0.000884532999862131,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019541560000106983,
"count": 10,
"is_parallel": true,
"self": 0.0019541560000106983
}
}
},
"UnityEnvironment.step": {
"total": 0.034933153000110906,
"count": 1,
"is_parallel": true,
"self": 0.00037245100020300015,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00030266499970821314,
"count": 1,
"is_parallel": true,
"self": 0.00030266499970821314
},
"communicator.exchange": {
"total": 0.033088149999912275,
"count": 1,
"is_parallel": true,
"self": 0.033088149999912275
},
"steps_from_proto": {
"total": 0.0011698870002874173,
"count": 1,
"is_parallel": true,
"self": 0.00027919600006498513,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008906910002224322,
"count": 10,
"is_parallel": true,
"self": 0.0008906910002224322
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 242.98270963299046,
"count": 18200,
"is_parallel": true,
"self": 9.55030154991482,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.337346145015545,
"count": 18200,
"is_parallel": true,
"self": 5.337346145015545
},
"communicator.exchange": {
"total": 195.64190557300662,
"count": 18200,
"is_parallel": true,
"self": 195.64190557300662
},
"steps_from_proto": {
"total": 32.453156365053474,
"count": 18200,
"is_parallel": true,
"self": 7.265629285949217,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.187527079104257,
"count": 182000,
"is_parallel": true,
"self": 25.187527079104257
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016122500028359354,
"count": 1,
"self": 0.00016122500028359354,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 457.1131288471083,
"count": 413519,
"is_parallel": true,
"self": 10.22531366516796,
"children": {
"process_trajectory": {
"total": 264.1655664099385,
"count": 413519,
"is_parallel": true,
"self": 263.1427733429382,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0227930670002934,
"count": 4,
"is_parallel": true,
"self": 1.0227930670002934
}
}
},
"_update_policy": {
"total": 182.72224877200188,
"count": 90,
"is_parallel": true,
"self": 61.651405768982386,
"children": {
"TorchPPOOptimizer.update": {
"total": 121.07084300301949,
"count": 4587,
"is_parallel": true,
"self": 121.07084300301949
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12454675599974507,
"count": 1,
"self": 0.001195870999708859,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12335088500003621,
"count": 1,
"self": 0.12335088500003621
}
}
}
}
}
}
}