marik0's picture
First Push
de86753
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8780258297920227,
"min": 0.8780258297920227,
"max": 2.867992639541626,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8383.390625,
"min": 8383.390625,
"max": 29371.11328125,
"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": 12.787982940673828,
"min": 0.4528235197067261,
"max": 12.787982940673828,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2493.65673828125,
"min": 87.84776306152344,
"max": 2603.345703125,
"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": 0.06778489762947691,
"min": 0.06213343218387665,
"max": 0.07645673040054082,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27113959051790765,
"min": 0.2485337287355066,
"max": 0.3822836520027041,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2005099270711927,
"min": 0.11085948285500646,
"max": 0.2734623821634873,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8020397082847708,
"min": 0.44343793142002585,
"max": 1.3302678629463793,
"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": 25.295454545454547,
"min": 3.022727272727273,
"max": 25.295454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1113.0,
"min": 133.0,
"max": 1385.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.295454545454547,
"min": 3.022727272727273,
"max": 25.295454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1113.0,
"min": 133.0,
"max": 1385.0,
"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": "1673716520",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
"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": "1673716937"
},
"total": 417.0942635600004,
"count": 1,
"self": 0.37354927599972143,
"children": {
"run_training.setup": {
"total": 0.1083973770000739,
"count": 1,
"self": 0.1083973770000739
},
"TrainerController.start_learning": {
"total": 416.6123169070006,
"count": 1,
"self": 0.48820574104775005,
"children": {
"TrainerController._reset_env": {
"total": 10.22961567099992,
"count": 1,
"self": 10.22961567099992
},
"TrainerController.advance": {
"total": 405.77802187895213,
"count": 18203,
"self": 0.2546760139202888,
"children": {
"env_step": {
"total": 405.52334586503184,
"count": 18203,
"self": 263.4346334240063,
"children": {
"SubprocessEnvManager._take_step": {
"total": 141.83569667307256,
"count": 18203,
"self": 1.3115037710222168,
"children": {
"TorchPolicy.evaluate": {
"total": 140.52419290205034,
"count": 18203,
"self": 32.15772143106551,
"children": {
"TorchPolicy.sample_actions": {
"total": 108.36647147098483,
"count": 18203,
"self": 108.36647147098483
}
}
}
}
},
"workers": {
"total": 0.25301576795300207,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 415.43854770598773,
"count": 18203,
"is_parallel": true,
"self": 201.6699093000525,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017755110002326546,
"count": 1,
"is_parallel": true,
"self": 0.0006110809999881894,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011644300002444652,
"count": 10,
"is_parallel": true,
"self": 0.0011644300002444652
}
}
},
"UnityEnvironment.step": {
"total": 0.03093505400011054,
"count": 1,
"is_parallel": true,
"self": 0.0005337140009942232,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039636200017412193,
"count": 1,
"is_parallel": true,
"self": 0.00039636200017412193
},
"communicator.exchange": {
"total": 0.02817023099942162,
"count": 1,
"is_parallel": true,
"self": 0.02817023099942162
},
"steps_from_proto": {
"total": 0.0018347469995205756,
"count": 1,
"is_parallel": true,
"self": 0.00041550099831511034,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014192460012054653,
"count": 10,
"is_parallel": true,
"self": 0.0014192460012054653
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 213.76863840593523,
"count": 18202,
"is_parallel": true,
"self": 8.160139072861966,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.8427887460711645,
"count": 18202,
"is_parallel": true,
"self": 4.8427887460711645
},
"communicator.exchange": {
"total": 168.11427480797374,
"count": 18202,
"is_parallel": true,
"self": 168.11427480797374
},
"steps_from_proto": {
"total": 32.65143577902836,
"count": 18202,
"is_parallel": true,
"self": 6.8929902949457755,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.758445484082586,
"count": 182020,
"is_parallel": true,
"self": 25.758445484082586
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.1465000322205015e-05,
"count": 1,
"self": 4.1465000322205015e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 403.100688165493,
"count": 332381,
"is_parallel": true,
"self": 8.419066954695154,
"children": {
"process_trajectory": {
"total": 230.9688971398018,
"count": 332381,
"is_parallel": true,
"self": 230.23210775580174,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7367893840000761,
"count": 4,
"is_parallel": true,
"self": 0.7367893840000761
}
}
},
"_update_policy": {
"total": 163.71272407099605,
"count": 90,
"is_parallel": true,
"self": 42.591972994984644,
"children": {
"TorchPPOOptimizer.update": {
"total": 121.1207510760114,
"count": 4587,
"is_parallel": true,
"self": 121.1207510760114
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1164321510004811,
"count": 1,
"self": 0.0008568230005039368,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11557532799997716,
"count": 1,
"self": 0.11557532799997716
}
}
}
}
}
}
}