katk31's picture
First Push
57afeed verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.199587345123291,
"min": 1.199587345123291,
"max": 2.8687901496887207,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 11453.66015625,
"min": 11453.66015625,
"max": 29347.72265625,
"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": 0.6144239902496338,
"min": 0.0761551484465599,
"max": 0.6261214017868042,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 119.81268310546875,
"min": 14.77409839630127,
"max": 123.67221069335938,
"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": 0.07092289203508556,
"min": 0.06361877883440077,
"max": 0.07484731197694725,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28369156814034224,
"min": 0.2544751153376031,
"max": 0.35827426196249457,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.07689571859059381,
"min": 0.023019724835809458,
"max": 0.08296194175879161,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.30758287436237525,
"min": 0.09207889934323783,
"max": 0.41480970879395807,
"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": 24.318181818181817,
"min": 2.75,
"max": 24.522727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1070.0,
"min": 121.0,
"max": 1322.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.318181818181817,
"min": 2.75,
"max": 24.522727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1070.0,
"min": 121.0,
"max": 1322.0,
"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": "1716760945",
"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": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1716761457"
},
"total": 511.4561931269999,
"count": 1,
"self": 0.49995701499994993,
"children": {
"run_training.setup": {
"total": 0.06981632099996204,
"count": 1,
"self": 0.06981632099996204
},
"TrainerController.start_learning": {
"total": 510.886419791,
"count": 1,
"self": 0.7215163310017942,
"children": {
"TrainerController._reset_env": {
"total": 3.201512913999977,
"count": 1,
"self": 3.201512913999977
},
"TrainerController.advance": {
"total": 506.8636954079982,
"count": 18201,
"self": 0.3575853810049239,
"children": {
"env_step": {
"total": 506.50611002699327,
"count": 18201,
"self": 334.6433986469872,
"children": {
"SubprocessEnvManager._take_step": {
"total": 171.5007406150031,
"count": 18201,
"self": 1.721658650012614,
"children": {
"TorchPolicy.evaluate": {
"total": 169.7790819649905,
"count": 18201,
"self": 169.7790819649905
}
}
},
"workers": {
"total": 0.36197076500297953,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 509.43145046000734,
"count": 18201,
"is_parallel": true,
"self": 251.39649702300562,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0055036310000105,
"count": 1,
"is_parallel": true,
"self": 0.003791181000224242,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017124499997862586,
"count": 10,
"is_parallel": true,
"self": 0.0017124499997862586
}
}
},
"UnityEnvironment.step": {
"total": 0.03982992099997773,
"count": 1,
"is_parallel": true,
"self": 0.0007568199997649572,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046291500007100694,
"count": 1,
"is_parallel": true,
"self": 0.00046291500007100694
},
"communicator.exchange": {
"total": 0.036516652000045724,
"count": 1,
"is_parallel": true,
"self": 0.036516652000045724
},
"steps_from_proto": {
"total": 0.0020935340000960423,
"count": 1,
"is_parallel": true,
"self": 0.00040921399988747,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016843200002085723,
"count": 10,
"is_parallel": true,
"self": 0.0016843200002085723
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 258.0349534370017,
"count": 18200,
"is_parallel": true,
"self": 11.874143016006883,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.993874463996917,
"count": 18200,
"is_parallel": true,
"self": 5.993874463996917
},
"communicator.exchange": {
"total": 203.01555042899724,
"count": 18200,
"is_parallel": true,
"self": 203.01555042899724
},
"steps_from_proto": {
"total": 37.151385528000674,
"count": 18200,
"is_parallel": true,
"self": 7.4086066730079665,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.742778854992707,
"count": 182000,
"is_parallel": true,
"self": 29.742778854992707
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001356459999897197,
"count": 1,
"self": 0.0001356459999897197,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 500.70659291396817,
"count": 761807,
"is_parallel": true,
"self": 16.04504790698786,
"children": {
"process_trajectory": {
"total": 278.29372654198085,
"count": 761807,
"is_parallel": true,
"self": 277.22074223798074,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0729843040001015,
"count": 4,
"is_parallel": true,
"self": 1.0729843040001015
}
}
},
"_update_policy": {
"total": 206.36781846499946,
"count": 90,
"is_parallel": true,
"self": 65.47561661100406,
"children": {
"TorchPPOOptimizer.update": {
"total": 140.8922018539954,
"count": 4587,
"is_parallel": true,
"self": 140.8922018539954
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09955949200002578,
"count": 1,
"self": 0.0010278530000960018,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09853163899992978,
"count": 1,
"self": 0.09853163899992978
}
}
}
}
}
}
}