JKuniszewski's picture
First Push
0a30c3d verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8089519739151001,
"min": 0.8017097115516663,
"max": 2.854810953140259,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7688.27978515625,
"min": 7688.27978515625,
"max": 29141.91015625,
"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": 12.671256065368652,
"min": 0.31455960869789124,
"max": 12.671256065368652,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2470.89501953125,
"min": 61.02456283569336,
"max": 2534.778076171875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06562241521311865,
"min": 0.06363019592148096,
"max": 0.0787656152066726,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2624896608524746,
"min": 0.26244437737349313,
"max": 0.3893648592946941,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19673877903351594,
"min": 0.11999329114127356,
"max": 0.2995941036326044,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7869551161340638,
"min": 0.47997316456509426,
"max": 1.3321629520140443,
"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": 25.386363636363637,
"min": 3.159090909090909,
"max": 25.386363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1117.0,
"min": 139.0,
"max": 1376.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.386363636363637,
"min": 3.159090909090909,
"max": 25.386363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1117.0,
"min": 139.0,
"max": 1376.0,
"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": "1756670087",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1756670526"
},
"total": 438.773808151,
"count": 1,
"self": 0.4322393900001771,
"children": {
"run_training.setup": {
"total": 0.03408536099993853,
"count": 1,
"self": 0.03408536099993853
},
"TrainerController.start_learning": {
"total": 438.3074833999999,
"count": 1,
"self": 0.41795832900129426,
"children": {
"TrainerController._reset_env": {
"total": 3.0109552359999725,
"count": 1,
"self": 3.0109552359999725
},
"TrainerController.advance": {
"total": 434.80035650299874,
"count": 18192,
"self": 0.4467257719944655,
"children": {
"env_step": {
"total": 313.0551228329996,
"count": 18192,
"self": 241.4981343819975,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.3042865310083,
"count": 18192,
"self": 1.340641063004341,
"children": {
"TorchPolicy.evaluate": {
"total": 69.96364546800396,
"count": 18192,
"self": 69.96364546800396
}
}
},
"workers": {
"total": 0.25270191999379676,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 436.86864464999746,
"count": 18192,
"is_parallel": true,
"self": 225.51885381700697,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004910494000000654,
"count": 1,
"is_parallel": true,
"self": 0.003531070999883923,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013794230001167307,
"count": 10,
"is_parallel": true,
"self": 0.0013794230001167307
}
}
},
"UnityEnvironment.step": {
"total": 0.03500661399993987,
"count": 1,
"is_parallel": true,
"self": 0.0005850630000168167,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003995289999920715,
"count": 1,
"is_parallel": true,
"self": 0.0003995289999920715
},
"communicator.exchange": {
"total": 0.03224215000000186,
"count": 1,
"is_parallel": true,
"self": 0.03224215000000186
},
"steps_from_proto": {
"total": 0.001779871999929128,
"count": 1,
"is_parallel": true,
"self": 0.0003361039999845161,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014437679999446118,
"count": 10,
"is_parallel": true,
"self": 0.0014437679999446118
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 211.3497908329905,
"count": 18191,
"is_parallel": true,
"self": 10.0543052660081,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.398378918992762,
"count": 18191,
"is_parallel": true,
"self": 5.398378918992762
},
"communicator.exchange": {
"total": 163.8248650029966,
"count": 18191,
"is_parallel": true,
"self": 163.8248650029966
},
"steps_from_proto": {
"total": 32.07224164499303,
"count": 18191,
"is_parallel": true,
"self": 5.882029569999986,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.190212074993042,
"count": 181910,
"is_parallel": true,
"self": 26.190212074993042
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 121.29850789800469,
"count": 18192,
"self": 0.5222813790174996,
"children": {
"process_trajectory": {
"total": 27.284932023987608,
"count": 18192,
"self": 26.893416079987787,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3915159439998206,
"count": 4,
"self": 0.3915159439998206
}
}
},
"_update_policy": {
"total": 93.49129449499958,
"count": 90,
"self": 38.23101096800076,
"children": {
"TorchPPOOptimizer.update": {
"total": 55.26028352699882,
"count": 4587,
"self": 55.26028352699882
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0339999789721332e-06,
"count": 1,
"self": 1.0339999789721332e-06
},
"TrainerController._save_models": {
"total": 0.0782122979999258,
"count": 1,
"self": 0.0007930009999199683,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07741929700000583,
"count": 1,
"self": 0.07741929700000583
}
}
}
}
}
}
}