aw-infoprojekt's picture
First Push
768e46f verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9673565626144409,
"min": 0.9673565626144409,
"max": 2.860013484954834,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9225.6796875,
"min": 9225.6796875,
"max": 29320.859375,
"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": 12.704121589660645,
"min": 0.29314249753952026,
"max": 12.704121589660645,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2477.3037109375,
"min": 56.86964416503906,
"max": 2554.0546875,
"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": 0.06793912428867199,
"min": 0.06367373538794745,
"max": 0.07586225057249049,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27175649715468797,
"min": 0.2546949415517898,
"max": 0.3793112528624525,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20891147420979014,
"min": 0.13269121472166814,
"max": 0.28883854285174726,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8356458968391606,
"min": 0.5307648588866726,
"max": 1.4184024897860545,
"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": 25.431818181818183,
"min": 3.477272727272727,
"max": 25.431818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1119.0,
"min": 153.0,
"max": 1381.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.431818181818183,
"min": 3.477272727272727,
"max": 25.431818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1119.0,
"min": 153.0,
"max": 1381.0,
"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": "1714108650",
"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 --force",
"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": "1714109106"
},
"total": 456.23129453699994,
"count": 1,
"self": 0.47607895399994504,
"children": {
"run_training.setup": {
"total": 0.053554671000028975,
"count": 1,
"self": 0.053554671000028975
},
"TrainerController.start_learning": {
"total": 455.70166091199997,
"count": 1,
"self": 0.8611858169933271,
"children": {
"TrainerController._reset_env": {
"total": 3.013446643000009,
"count": 1,
"self": 3.013446643000009
},
"TrainerController.advance": {
"total": 451.7457786420067,
"count": 18203,
"self": 0.41034910600922103,
"children": {
"env_step": {
"total": 451.3354295359975,
"count": 18203,
"self": 346.6691229490078,
"children": {
"SubprocessEnvManager._take_step": {
"total": 104.27881590999021,
"count": 18203,
"self": 1.9783636919866012,
"children": {
"TorchPolicy.evaluate": {
"total": 102.30045221800361,
"count": 18203,
"self": 102.30045221800361
}
}
},
"workers": {
"total": 0.387490676999505,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 453.99288731499365,
"count": 18203,
"is_parallel": true,
"self": 206.65463636298819,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005353409000008469,
"count": 1,
"is_parallel": true,
"self": 0.004259918999991896,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010934900000165726,
"count": 10,
"is_parallel": true,
"self": 0.0010934900000165726
}
}
},
"UnityEnvironment.step": {
"total": 0.03541200000000799,
"count": 1,
"is_parallel": true,
"self": 0.0005758700000342287,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005340999999816631,
"count": 1,
"is_parallel": true,
"self": 0.0005340999999816631
},
"communicator.exchange": {
"total": 0.03260330000000522,
"count": 1,
"is_parallel": true,
"self": 0.03260330000000522
},
"steps_from_proto": {
"total": 0.001698729999986881,
"count": 1,
"is_parallel": true,
"self": 0.00035847999998850355,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013402499999983775,
"count": 10,
"is_parallel": true,
"self": 0.0013402499999983775
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 247.33825095200547,
"count": 18202,
"is_parallel": true,
"self": 11.689530898007206,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.185472160996483,
"count": 18202,
"is_parallel": true,
"self": 7.185472160996483
},
"communicator.exchange": {
"total": 196.35914138199558,
"count": 18202,
"is_parallel": true,
"self": 196.35914138199558
},
"steps_from_proto": {
"total": 32.104106511006194,
"count": 18202,
"is_parallel": true,
"self": 6.785229871977435,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.31887663902876,
"count": 182020,
"is_parallel": true,
"self": 25.31887663902876
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00018121099992640666,
"count": 1,
"self": 0.00018121099992640666,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 447.1681715460405,
"count": 664562,
"is_parallel": true,
"self": 12.569154553086037,
"children": {
"process_trajectory": {
"total": 256.9849658589543,
"count": 664562,
"is_parallel": true,
"self": 256.36413846595417,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6208273930001269,
"count": 4,
"is_parallel": true,
"self": 0.6208273930001269
}
}
},
"_update_policy": {
"total": 177.6140511340002,
"count": 90,
"is_parallel": true,
"self": 41.560678828003745,
"children": {
"TorchPPOOptimizer.update": {
"total": 136.05337230599645,
"count": 4587,
"is_parallel": true,
"self": 136.05337230599645
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08106859899999108,
"count": 1,
"self": 0.0010656780000317667,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08000292099995931,
"count": 1,
"self": 0.08000292099995931
}
}
}
}
}
}
}