RealityAdmin's picture
First Push
6f78772 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8284511566162109,
"min": 0.8284511566162109,
"max": 2.8572466373443604,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7873.599609375,
"min": 7873.599609375,
"max": 29166.7734375,
"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": 12.825886726379395,
"min": 0.2962426245212555,
"max": 12.825886726379395,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2501.0478515625,
"min": 57.4710693359375,
"max": 2593.666015625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06580261395263769,
"min": 0.06421094451380116,
"max": 0.07369330852182912,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26321045581055075,
"min": 0.26321045581055075,
"max": 0.3684665426091456,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1962249983905577,
"min": 0.13736597790300628,
"max": 0.2905188779036204,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7848999935622308,
"min": 0.5494639116120251,
"max": 1.4525943895181022,
"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": 3.8636363636363638,
"max": 25.59090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1117.0,
"min": 170.0,
"max": 1387.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.386363636363637,
"min": 3.8636363636363638,
"max": 25.59090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1117.0,
"min": 170.0,
"max": 1387.0,
"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": "1738448960",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1738449418"
},
"total": 457.4656992680001,
"count": 1,
"self": 0.4351867340000126,
"children": {
"run_training.setup": {
"total": 0.023670184000025074,
"count": 1,
"self": 0.023670184000025074
},
"TrainerController.start_learning": {
"total": 457.00684235000006,
"count": 1,
"self": 0.3636945509971383,
"children": {
"TrainerController._reset_env": {
"total": 2.904812664000019,
"count": 1,
"self": 2.904812664000019
},
"TrainerController.advance": {
"total": 453.64604861900284,
"count": 18192,
"self": 0.3819855770242384,
"children": {
"env_step": {
"total": 324.38183807299185,
"count": 18192,
"self": 245.9329103049829,
"children": {
"SubprocessEnvManager._take_step": {
"total": 78.23346978999643,
"count": 18192,
"self": 1.3463809360015375,
"children": {
"TorchPolicy.evaluate": {
"total": 76.8870888539949,
"count": 18192,
"self": 76.8870888539949
}
}
},
"workers": {
"total": 0.2154579780125232,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 455.4013828150089,
"count": 18192,
"is_parallel": true,
"self": 239.98382705601568,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005377133000024514,
"count": 1,
"is_parallel": true,
"self": 0.003586727999845607,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017904050001789074,
"count": 10,
"is_parallel": true,
"self": 0.0017904050001789074
}
}
},
"UnityEnvironment.step": {
"total": 0.04112083900008656,
"count": 1,
"is_parallel": true,
"self": 0.0006975240000883787,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004251179999528176,
"count": 1,
"is_parallel": true,
"self": 0.0004251179999528176
},
"communicator.exchange": {
"total": 0.03777105200003916,
"count": 1,
"is_parallel": true,
"self": 0.03777105200003916
},
"steps_from_proto": {
"total": 0.002227145000006203,
"count": 1,
"is_parallel": true,
"self": 0.0004132390004087938,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018139059995974094,
"count": 10,
"is_parallel": true,
"self": 0.0018139059995974094
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 215.41755575899322,
"count": 18191,
"is_parallel": true,
"self": 10.21083800598717,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.6996681030037735,
"count": 18191,
"is_parallel": true,
"self": 5.6996681030037735
},
"communicator.exchange": {
"total": 165.83909247700024,
"count": 18191,
"is_parallel": true,
"self": 165.83909247700024
},
"steps_from_proto": {
"total": 33.66795717300204,
"count": 18191,
"is_parallel": true,
"self": 5.933861772984642,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.734095400017395,
"count": 181910,
"is_parallel": true,
"self": 27.734095400017395
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 128.88222496898675,
"count": 18192,
"self": 0.43246996298762497,
"children": {
"process_trajectory": {
"total": 28.858886782998297,
"count": 18192,
"self": 28.319914438998467,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5389723439998306,
"count": 4,
"self": 0.5389723439998306
}
}
},
"_update_policy": {
"total": 99.59086822300083,
"count": 90,
"self": 39.636611585006904,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.95425663799392,
"count": 4587,
"self": 59.95425663799392
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.450000106880907e-07,
"count": 1,
"self": 9.450000106880907e-07
},
"TrainerController._save_models": {
"total": 0.09228557100004764,
"count": 1,
"self": 0.0009308169999258098,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09135475400012183,
"count": 1,
"self": 0.09135475400012183
}
}
}
}
}
}
}