Adilbai's picture
First Push
9cac426 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7878355383872986,
"min": 0.7665887475013733,
"max": 2.869081735610962,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7487.5888671875,
"min": 7487.5888671875,
"max": 29287.5859375,
"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": 12.91712474822998,
"min": 0.442545086145401,
"max": 12.91712474822998,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2518.83935546875,
"min": 85.85374450683594,
"max": 2631.32177734375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06811946692459078,
"min": 0.06321964170407121,
"max": 0.0733559273539511,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27247786769836313,
"min": 0.2539280783887222,
"max": 0.36658366354490945,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1825736324284591,
"min": 0.14302233171274922,
"max": 0.28609009496137205,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7302945297138363,
"min": 0.5720893268509969,
"max": 1.3282455962662603,
"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.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.Environment.CumulativeReward.mean": {
"value": 25.318181818181817,
"min": 4.2272727272727275,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1114.0,
"min": 186.0,
"max": 1395.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.318181818181817,
"min": 4.2272727272727275,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1114.0,
"min": 186.0,
"max": 1395.0,
"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": "1749622226",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1749622665"
},
"total": 439.013180401,
"count": 1,
"self": 0.4385041239999623,
"children": {
"run_training.setup": {
"total": 0.023050619000002825,
"count": 1,
"self": 0.023050619000002825
},
"TrainerController.start_learning": {
"total": 438.55162565800003,
"count": 1,
"self": 0.38135282599813536,
"children": {
"TrainerController._reset_env": {
"total": 3.074184215999992,
"count": 1,
"self": 3.074184215999992
},
"TrainerController.advance": {
"total": 435.00663091800186,
"count": 18192,
"self": 0.40778468399059875,
"children": {
"env_step": {
"total": 311.2068387430108,
"count": 18192,
"self": 236.7995562350157,
"children": {
"SubprocessEnvManager._take_step": {
"total": 74.1840773270007,
"count": 18192,
"self": 1.337621998012878,
"children": {
"TorchPolicy.evaluate": {
"total": 72.84645532898782,
"count": 18192,
"self": 72.84645532898782
}
}
},
"workers": {
"total": 0.22320518099439823,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 437.05409206300766,
"count": 18192,
"is_parallel": true,
"self": 230.273719349009,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005215645999953722,
"count": 1,
"is_parallel": true,
"self": 0.003812113999970279,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014035319999834428,
"count": 10,
"is_parallel": true,
"self": 0.0014035319999834428
}
}
},
"UnityEnvironment.step": {
"total": 0.03790477600000486,
"count": 1,
"is_parallel": true,
"self": 0.0005915309999409146,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004020050000121955,
"count": 1,
"is_parallel": true,
"self": 0.0004020050000121955
},
"communicator.exchange": {
"total": 0.03482946400004039,
"count": 1,
"is_parallel": true,
"self": 0.03482946400004039
},
"steps_from_proto": {
"total": 0.0020817760000113594,
"count": 1,
"is_parallel": true,
"self": 0.0003973289999521512,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016844470000592082,
"count": 10,
"is_parallel": true,
"self": 0.0016844470000592082
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 206.78037271399864,
"count": 18191,
"is_parallel": true,
"self": 9.838514740997141,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.545555967007658,
"count": 18191,
"is_parallel": true,
"self": 5.545555967007658
},
"communicator.exchange": {
"total": 158.8250271219914,
"count": 18191,
"is_parallel": true,
"self": 158.8250271219914
},
"steps_from_proto": {
"total": 32.571274884002435,
"count": 18191,
"is_parallel": true,
"self": 5.902059333019736,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.6692155509827,
"count": 181910,
"is_parallel": true,
"self": 26.6692155509827
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 123.39200749100047,
"count": 18192,
"self": 0.45519270799803735,
"children": {
"process_trajectory": {
"total": 27.310394389002,
"count": 18192,
"self": 26.888413331001857,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4219810580001422,
"count": 4,
"self": 0.4219810580001422
}
}
},
"_update_policy": {
"total": 95.62642039400043,
"count": 90,
"self": 38.86501315500266,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.761407238997776,
"count": 4587,
"self": 56.761407238997776
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.310000450568623e-07,
"count": 1,
"self": 9.310000450568623e-07
},
"TrainerController._save_models": {
"total": 0.08945676700000149,
"count": 1,
"self": 0.000854298999911407,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08860246800009008,
"count": 1,
"self": 0.08860246800009008
}
}
}
}
}
}
}