jrnold's picture
First Push
70216df
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9764333963394165,
"min": 0.9764333963394165,
"max": 2.8634543418884277,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9344.4677734375,
"min": 9344.4677734375,
"max": 29419.12890625,
"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": 12.810406684875488,
"min": 0.2905351519584656,
"max": 12.810406684875488,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2498.029296875,
"min": 56.36381912231445,
"max": 2570.40869140625,
"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": 0.07262009583235554,
"min": 0.06126292719943426,
"max": 0.07262009583235554,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29048038332942216,
"min": 0.24505170879773705,
"max": 0.36069020125147544,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1984475943095544,
"min": 0.13509145235715836,
"max": 0.2658771337247362,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7937903772382175,
"min": 0.5403658094286334,
"max": 1.3293856686236811,
"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": 25.477272727272727,
"min": 4.0227272727272725,
"max": 25.477272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1121.0,
"min": 177.0,
"max": 1395.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.477272727272727,
"min": 4.0227272727272725,
"max": 25.477272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1121.0,
"min": 177.0,
"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": "1674151097",
"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": "1.21.6",
"end_time_seconds": "1674151459"
},
"total": 361.66684057,
"count": 1,
"self": 0.38695967599994674,
"children": {
"run_training.setup": {
"total": 0.09340923100000964,
"count": 1,
"self": 0.09340923100000964
},
"TrainerController.start_learning": {
"total": 361.186471663,
"count": 1,
"self": 0.5045474649956532,
"children": {
"TrainerController._reset_env": {
"total": 4.7979507210000065,
"count": 1,
"self": 4.7979507210000065
},
"TrainerController.advance": {
"total": 355.7999851500043,
"count": 18204,
"self": 0.24738274000958427,
"children": {
"env_step": {
"total": 355.55260240999473,
"count": 18204,
"self": 280.3186387180043,
"children": {
"SubprocessEnvManager._take_step": {
"total": 74.9678002509977,
"count": 18204,
"self": 1.157098130002737,
"children": {
"TorchPolicy.evaluate": {
"total": 73.81070212099496,
"count": 18204,
"self": 14.145801769998116,
"children": {
"TorchPolicy.sample_actions": {
"total": 59.664900350996845,
"count": 18204,
"self": 59.664900350996845
}
}
}
}
},
"workers": {
"total": 0.2661634409927274,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 360.30798468899286,
"count": 18204,
"is_parallel": true,
"self": 160.00501042499047,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004304199999978664,
"count": 1,
"is_parallel": true,
"self": 0.0024825699998700657,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018216300001085983,
"count": 10,
"is_parallel": true,
"self": 0.0018216300001085983
}
}
},
"UnityEnvironment.step": {
"total": 0.04208319600002142,
"count": 1,
"is_parallel": true,
"self": 0.0003879590000224198,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00025012000003243884,
"count": 1,
"is_parallel": true,
"self": 0.00025012000003243884
},
"communicator.exchange": {
"total": 0.04007338700000673,
"count": 1,
"is_parallel": true,
"self": 0.04007338700000673
},
"steps_from_proto": {
"total": 0.0013717299999598254,
"count": 1,
"is_parallel": true,
"self": 0.00028799799997614173,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010837319999836836,
"count": 10,
"is_parallel": true,
"self": 0.0010837319999836836
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 200.3029742640024,
"count": 18203,
"is_parallel": true,
"self": 7.349147241005767,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.465515454999263,
"count": 18203,
"is_parallel": true,
"self": 4.465515454999263
},
"communicator.exchange": {
"total": 160.42274420300464,
"count": 18203,
"is_parallel": true,
"self": 160.42274420300464
},
"steps_from_proto": {
"total": 28.065567364992717,
"count": 18203,
"is_parallel": true,
"self": 5.785874032982974,
"children": {
"_process_rank_one_or_two_observation": {
"total": 22.279693332009742,
"count": 182030,
"is_parallel": true,
"self": 22.279693332009742
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 2.978000009079551e-05,
"count": 1,
"self": 2.978000009079551e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 353.3825749909994,
"count": 336052,
"is_parallel": true,
"self": 7.116512406008269,
"children": {
"process_trajectory": {
"total": 197.73874052299198,
"count": 336052,
"is_parallel": true,
"self": 197.11892774299213,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6198127799998474,
"count": 4,
"is_parallel": true,
"self": 0.6198127799998474
}
}
},
"_update_policy": {
"total": 148.52732206199914,
"count": 90,
"is_parallel": true,
"self": 36.54255732199954,
"children": {
"TorchPPOOptimizer.update": {
"total": 111.9847647399996,
"count": 4587,
"is_parallel": true,
"self": 111.9847647399996
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08395854699995198,
"count": 1,
"self": 0.0012006209999526618,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08275792599999932,
"count": 1,
"self": 0.08275792599999932
}
}
}
}
}
}
}