optimopium's picture
First Push
2f246c7
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0373671054840088,
"min": 1.0373671054840088,
"max": 2.8679897785186768,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9939.0146484375,
"min": 9939.0146484375,
"max": 29465.7265625,
"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": 12.31035041809082,
"min": 0.29193130135536194,
"max": 12.31035041809082,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2400.518310546875,
"min": 56.63467025756836,
"max": 2493.271728515625,
"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": 0.06996883067825133,
"min": 0.0631797912184779,
"max": 0.07366838738217826,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2798753227130053,
"min": 0.2527191648739116,
"max": 0.36834193691089134,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2082163757261108,
"min": 0.14083522064930887,
"max": 0.2828599001847062,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8328655029044432,
"min": 0.5633408825972355,
"max": 1.4142995009235309,
"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": 24.09090909090909,
"min": 3.659090909090909,
"max": 24.4,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1060.0,
"min": 161.0,
"max": 1342.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.09090909090909,
"min": 3.659090909090909,
"max": 24.4,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1060.0,
"min": 161.0,
"max": 1342.0,
"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": "1685778371",
"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": "1685778811"
},
"total": 440.10187804400005,
"count": 1,
"self": 0.7356649369999104,
"children": {
"run_training.setup": {
"total": 0.040486737000037465,
"count": 1,
"self": 0.040486737000037465
},
"TrainerController.start_learning": {
"total": 439.3257263700001,
"count": 1,
"self": 0.49398462200497306,
"children": {
"TrainerController._reset_env": {
"total": 3.762239983000086,
"count": 1,
"self": 3.762239983000086
},
"TrainerController.advance": {
"total": 434.8550025029947,
"count": 18219,
"self": 0.23066091098633024,
"children": {
"env_step": {
"total": 434.62434159200836,
"count": 18219,
"self": 315.06998974299586,
"children": {
"SubprocessEnvManager._take_step": {
"total": 119.31374258801031,
"count": 18219,
"self": 1.7429673970142403,
"children": {
"TorchPolicy.evaluate": {
"total": 117.57077519099607,
"count": 18219,
"self": 117.57077519099607
}
}
},
"workers": {
"total": 0.2406092610021915,
"count": 18219,
"self": 0.0,
"children": {
"worker_root": {
"total": 437.81309070100065,
"count": 18219,
"is_parallel": true,
"self": 205.64713390499674,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005628617000070335,
"count": 1,
"is_parallel": true,
"self": 0.003996925000137708,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016316919999326274,
"count": 10,
"is_parallel": true,
"self": 0.0016316919999326274
}
}
},
"UnityEnvironment.step": {
"total": 0.039535407000016676,
"count": 1,
"is_parallel": true,
"self": 0.00048051699991447094,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00032130500005678186,
"count": 1,
"is_parallel": true,
"self": 0.00032130500005678186
},
"communicator.exchange": {
"total": 0.03721936600004483,
"count": 1,
"is_parallel": true,
"self": 0.03721936600004483
},
"steps_from_proto": {
"total": 0.001514219000000594,
"count": 1,
"is_parallel": true,
"self": 0.0002976049999006136,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012166140000999803,
"count": 10,
"is_parallel": true,
"self": 0.0012166140000999803
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 232.1659567960039,
"count": 18218,
"is_parallel": true,
"self": 9.461176620995388,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.001224023996656,
"count": 18218,
"is_parallel": true,
"self": 5.001224023996656
},
"communicator.exchange": {
"total": 186.03944737599898,
"count": 18218,
"is_parallel": true,
"self": 186.03944737599898
},
"steps_from_proto": {
"total": 31.664108775012892,
"count": 18218,
"is_parallel": true,
"self": 6.020913195024718,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.643195579988173,
"count": 182180,
"is_parallel": true,
"self": 25.643195579988173
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013188900015848048,
"count": 1,
"self": 0.00013188900015848048,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 431.54911563901476,
"count": 413602,
"is_parallel": true,
"self": 9.232992904003936,
"children": {
"process_trajectory": {
"total": 237.49508263201074,
"count": 413602,
"is_parallel": true,
"self": 235.92726421401073,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5678184180000017,
"count": 4,
"is_parallel": true,
"self": 1.5678184180000017
}
}
},
"_update_policy": {
"total": 184.8210401030001,
"count": 90,
"is_parallel": true,
"self": 65.25956338999958,
"children": {
"TorchPPOOptimizer.update": {
"total": 119.5614767130005,
"count": 4587,
"is_parallel": true,
"self": 119.5614767130005
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.2143673730001865,
"count": 1,
"self": 0.0011210520003714919,
"children": {
"RLTrainer._checkpoint": {
"total": 0.213246320999815,
"count": 1,
"self": 0.213246320999815
}
}
}
}
}
}
}