rebolforces's picture
Initial Push
2924f70
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0507440567016602,
"min": 1.0279178619384766,
"max": 2.8620150089263916,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10044.0625,
"min": 10044.0625,
"max": 29309.896484375,
"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": 13.123291969299316,
"min": 0.3443656265735626,
"max": 13.123291969299316,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2559.0419921875,
"min": 66.80693054199219,
"max": 2646.619873046875,
"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": 0.06705838615829741,
"min": 0.06464204673470436,
"max": 0.07882937087903402,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26823354463318966,
"min": 0.26267959363416166,
"max": 0.37097052939740627,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20454933881467463,
"min": 0.10039981273596413,
"max": 0.2713680083260817,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8181973552586985,
"min": 0.4015992509438565,
"max": 1.2938416141505333,
"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": 25.363636363636363,
"min": 3.1363636363636362,
"max": 25.745454545454546,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1116.0,
"min": 138.0,
"max": 1416.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.363636363636363,
"min": 3.1363636363636362,
"max": 25.745454545454546,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1116.0,
"min": 138.0,
"max": 1416.0,
"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": "1679107082",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1679107541"
},
"total": 458.20935819,
"count": 1,
"self": 0.3841303549999111,
"children": {
"run_training.setup": {
"total": 0.10384222000004684,
"count": 1,
"self": 0.10384222000004684
},
"TrainerController.start_learning": {
"total": 457.72138561500003,
"count": 1,
"self": 0.5038365209906033,
"children": {
"TrainerController._reset_env": {
"total": 9.319284405999952,
"count": 1,
"self": 9.319284405999952
},
"TrainerController.advance": {
"total": 447.76986574800935,
"count": 18201,
"self": 0.26067714700718625,
"children": {
"env_step": {
"total": 447.50918860100217,
"count": 18201,
"self": 325.0281545649849,
"children": {
"SubprocessEnvManager._take_step": {
"total": 122.22505225601287,
"count": 18201,
"self": 1.889892879012109,
"children": {
"TorchPolicy.evaluate": {
"total": 120.33515937700076,
"count": 18201,
"self": 120.33515937700076
}
}
},
"workers": {
"total": 0.2559817800043902,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 456.42363654698875,
"count": 18201,
"is_parallel": true,
"self": 222.91041280098125,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005906058000050507,
"count": 1,
"is_parallel": true,
"self": 0.0044714940000858405,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014345639999646664,
"count": 10,
"is_parallel": true,
"self": 0.0014345639999646664
}
}
},
"UnityEnvironment.step": {
"total": 0.046607407000010426,
"count": 1,
"is_parallel": true,
"self": 0.0003994700000475859,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003982270000051358,
"count": 1,
"is_parallel": true,
"self": 0.0003982270000051358
},
"communicator.exchange": {
"total": 0.04403934200001913,
"count": 1,
"is_parallel": true,
"self": 0.04403934200001913
},
"steps_from_proto": {
"total": 0.0017703679999385713,
"count": 1,
"is_parallel": true,
"self": 0.00036680899972907355,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014035590002094978,
"count": 10,
"is_parallel": true,
"self": 0.0014035590002094978
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 233.5132237460075,
"count": 18200,
"is_parallel": true,
"self": 9.200669092021599,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.120827867999196,
"count": 18200,
"is_parallel": true,
"self": 5.120827867999196
},
"communicator.exchange": {
"total": 188.6720567959967,
"count": 18200,
"is_parallel": true,
"self": 188.6720567959967
},
"steps_from_proto": {
"total": 30.519669989990007,
"count": 18200,
"is_parallel": true,
"self": 6.0027046949279566,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.51696529506205,
"count": 182000,
"is_parallel": true,
"self": 24.51696529506205
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014313600013338146,
"count": 1,
"self": 0.00014313600013338146,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 444.58518809697625,
"count": 376434,
"is_parallel": true,
"self": 9.460768364959108,
"children": {
"process_trajectory": {
"total": 247.11052112301763,
"count": 376434,
"is_parallel": true,
"self": 245.25525365801786,
"children": {
"RLTrainer._checkpoint": {
"total": 1.8552674649997698,
"count": 4,
"is_parallel": true,
"self": 1.8552674649997698
}
}
},
"_update_policy": {
"total": 188.0138986089995,
"count": 90,
"is_parallel": true,
"self": 73.89668115200027,
"children": {
"TorchPPOOptimizer.update": {
"total": 114.11721745699924,
"count": 4587,
"is_parallel": true,
"self": 114.11721745699924
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12825580399999126,
"count": 1,
"self": 0.0008348489998297737,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12742095500016148,
"count": 1,
"self": 0.12742095500016148
}
}
}
}
}
}
}