Gonke's picture
First Push
2c56b3d verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0850038528442383,
"min": 1.0850038528442383,
"max": 2.869781732559204,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10371.5517578125,
"min": 10371.5517578125,
"max": 29389.43359375,
"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": 12.032890319824219,
"min": 0.3384926915168762,
"max": 12.032890319824219,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2346.41357421875,
"min": 65.6675796508789,
"max": 2430.65771484375,
"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": 0.07019995339913865,
"min": 0.06289033501382743,
"max": 0.07401728908264298,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2807998135965546,
"min": 0.2515613400553097,
"max": 0.3669944091548221,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21645069538670425,
"min": 0.12410172006097056,
"max": 0.2784049698535133,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.865802781546817,
"min": 0.49640688024388224,
"max": 1.3920248492675666,
"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": 24.272727272727273,
"min": 3.7045454545454546,
"max": 24.272727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1068.0,
"min": 163.0,
"max": 1300.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.272727272727273,
"min": 3.7045454545454546,
"max": 24.272727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1068.0,
"min": 163.0,
"max": 1300.0,
"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": "1711994311",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1711994756"
},
"total": 445.1456564189999,
"count": 1,
"self": 0.43744705999984035,
"children": {
"run_training.setup": {
"total": 0.054947181999978056,
"count": 1,
"self": 0.054947181999978056
},
"TrainerController.start_learning": {
"total": 444.6532621770001,
"count": 1,
"self": 0.5504575940025234,
"children": {
"TrainerController._reset_env": {
"total": 2.78350956700001,
"count": 1,
"self": 2.78350956700001
},
"TrainerController.advance": {
"total": 441.2261627559976,
"count": 18200,
"self": 0.26535605699689313,
"children": {
"env_step": {
"total": 440.9608066990007,
"count": 18200,
"self": 284.93171189399436,
"children": {
"SubprocessEnvManager._take_step": {
"total": 155.743945464003,
"count": 18200,
"self": 1.465946285013274,
"children": {
"TorchPolicy.evaluate": {
"total": 154.27799917898972,
"count": 18200,
"self": 154.27799917898972
}
}
},
"workers": {
"total": 0.2851493410033754,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 443.56355799998073,
"count": 18200,
"is_parallel": true,
"self": 222.12589816698733,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00573743999996168,
"count": 1,
"is_parallel": true,
"self": 0.004109852999931718,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001627587000029962,
"count": 10,
"is_parallel": true,
"self": 0.001627587000029962
}
}
},
"UnityEnvironment.step": {
"total": 0.05252401000007012,
"count": 1,
"is_parallel": true,
"self": 0.0006969910000407253,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004759810000223297,
"count": 1,
"is_parallel": true,
"self": 0.0004759810000223297
},
"communicator.exchange": {
"total": 0.049355761000015264,
"count": 1,
"is_parallel": true,
"self": 0.049355761000015264
},
"steps_from_proto": {
"total": 0.001995276999991802,
"count": 1,
"is_parallel": true,
"self": 0.0004103859997712789,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001584891000220523,
"count": 10,
"is_parallel": true,
"self": 0.001584891000220523
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 221.4376598329934,
"count": 18199,
"is_parallel": true,
"self": 10.145801679998954,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.366759517989749,
"count": 18199,
"is_parallel": true,
"self": 5.366759517989749
},
"communicator.exchange": {
"total": 172.05677751499695,
"count": 18199,
"is_parallel": true,
"self": 172.05677751499695
},
"steps_from_proto": {
"total": 33.86832112000775,
"count": 18199,
"is_parallel": true,
"self": 6.37981326402894,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.48850785597881,
"count": 181990,
"is_parallel": true,
"self": 27.48850785597881
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.869600004691165e-05,
"count": 1,
"self": 3.869600004691165e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 435.5752975519616,
"count": 673635,
"is_parallel": true,
"self": 14.380429485922036,
"children": {
"process_trajectory": {
"total": 240.4234888170397,
"count": 673635,
"is_parallel": true,
"self": 239.85330930603936,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5701795110003332,
"count": 4,
"is_parallel": true,
"self": 0.5701795110003332
}
}
},
"_update_policy": {
"total": 180.7713792489999,
"count": 90,
"is_parallel": true,
"self": 51.90269581000041,
"children": {
"TorchPPOOptimizer.update": {
"total": 128.86868343899948,
"count": 4587,
"is_parallel": true,
"self": 128.86868343899948
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09309356399990065,
"count": 1,
"self": 0.0010939429998870764,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09199962100001358,
"count": 1,
"self": 0.09199962100001358
}
}
}
}
}
}
}