rami8k's picture
First Push
4150597
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8822513222694397,
"min": 0.8822513222694397,
"max": 2.8673577308654785,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8423.7353515625,
"min": 8423.7353515625,
"max": 29459.232421875,
"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": 12.972538948059082,
"min": 0.33992162346839905,
"max": 13.075366020202637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2529.64501953125,
"min": 65.94479370117188,
"max": 2655.51708984375,
"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": 0.0676133937827395,
"min": 0.063997771549575,
"max": 0.07399944048451931,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.270453575130958,
"min": 0.2559910861983,
"max": 0.3652148265140497,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21317189281769827,
"min": 0.10753731207018169,
"max": 0.28471409135005055,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8526875712707931,
"min": 0.43014924828072676,
"max": 1.422063633799553,
"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": 25.40909090909091,
"min": 2.9545454545454546,
"max": 25.672727272727272,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1118.0,
"min": 130.0,
"max": 1412.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.40909090909091,
"min": 2.9545454545454546,
"max": 25.672727272727272,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1118.0,
"min": 130.0,
"max": 1412.0,
"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": "1687304811",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1687305259"
},
"total": 447.973048099,
"count": 1,
"self": 0.39912976000005074,
"children": {
"run_training.setup": {
"total": 0.05221814499998345,
"count": 1,
"self": 0.05221814499998345
},
"TrainerController.start_learning": {
"total": 447.52170019399995,
"count": 1,
"self": 0.5179753149981821,
"children": {
"TrainerController._reset_env": {
"total": 4.064245071000016,
"count": 1,
"self": 4.064245071000016
},
"TrainerController.advance": {
"total": 442.7874171590017,
"count": 18203,
"self": 0.2600992730062899,
"children": {
"env_step": {
"total": 442.5273178859954,
"count": 18203,
"self": 324.07664235099224,
"children": {
"SubprocessEnvManager._take_step": {
"total": 118.2027118610028,
"count": 18203,
"self": 1.6811556700056371,
"children": {
"TorchPolicy.evaluate": {
"total": 116.52155619099716,
"count": 18203,
"self": 116.52155619099716
}
}
},
"workers": {
"total": 0.2479636740003457,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 445.88595502999993,
"count": 18203,
"is_parallel": true,
"self": 210.28708072300964,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00581918500000711,
"count": 1,
"is_parallel": true,
"self": 0.004377653000176451,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014415319998306586,
"count": 10,
"is_parallel": true,
"self": 0.0014415319998306586
}
}
},
"UnityEnvironment.step": {
"total": 0.035508556999957364,
"count": 1,
"is_parallel": true,
"self": 0.0004217540000013287,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003194920000169077,
"count": 1,
"is_parallel": true,
"self": 0.0003194920000169077
},
"communicator.exchange": {
"total": 0.03287728399999423,
"count": 1,
"is_parallel": true,
"self": 0.03287728399999423
},
"steps_from_proto": {
"total": 0.0018900269999448938,
"count": 1,
"is_parallel": true,
"self": 0.00034912799992525834,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015408990000196354,
"count": 10,
"is_parallel": true,
"self": 0.0015408990000196354
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 235.5988743069903,
"count": 18202,
"is_parallel": true,
"self": 9.769133128998135,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.137113422006223,
"count": 18202,
"is_parallel": true,
"self": 5.137113422006223
},
"communicator.exchange": {
"total": 187.8549625359932,
"count": 18202,
"is_parallel": true,
"self": 187.8549625359932
},
"steps_from_proto": {
"total": 32.83766521999274,
"count": 18202,
"is_parallel": true,
"self": 5.795331662009573,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.04233355798317,
"count": 182020,
"is_parallel": true,
"self": 27.04233355798317
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014825300002030417,
"count": 1,
"self": 0.00014825300002030417,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 439.4208361850275,
"count": 423754,
"is_parallel": true,
"self": 9.194253717008621,
"children": {
"process_trajectory": {
"total": 241.07002710401878,
"count": 423754,
"is_parallel": true,
"self": 239.8830603310189,
"children": {
"RLTrainer._checkpoint": {
"total": 1.186966772999881,
"count": 4,
"is_parallel": true,
"self": 1.186966772999881
}
}
},
"_update_policy": {
"total": 189.1565553640001,
"count": 90,
"is_parallel": true,
"self": 73.22111340199945,
"children": {
"TorchPPOOptimizer.update": {
"total": 115.93544196200065,
"count": 4587,
"is_parallel": true,
"self": 115.93544196200065
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15191439600005197,
"count": 1,
"self": 0.0008702790000825189,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15104411699996945,
"count": 1,
"self": 0.15104411699996945
}
}
}
}
}
}
}