DeepNuc's picture
initial
4a68640 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8000791668891907,
"min": 0.8000791668891907,
"max": 2.827587366104126,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7603.9521484375,
"min": 7603.9521484375,
"max": 28864.01171875,
"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": 12.81591510772705,
"min": 0.45649686455726624,
"max": 12.81591510772705,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2499.103515625,
"min": 88.56039428710938,
"max": 2608.8681640625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06552691837800119,
"min": 0.06552691837800119,
"max": 0.07390902149742104,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26210767351200476,
"min": 0.26210767351200476,
"max": 0.3646972959786402,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19553150528786228,
"min": 0.15062941040492198,
"max": 0.29914741765926867,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7821260211514491,
"min": 0.6025176416196879,
"max": 1.389694567112362,
"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": 24.727272727272727,
"min": 4.136363636363637,
"max": 25.386363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1088.0,
"min": 182.0,
"max": 1386.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.727272727272727,
"min": 4.136363636363637,
"max": 25.386363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1088.0,
"min": 182.0,
"max": 1386.0,
"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": "1753102127",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1753102537"
},
"total": 410.63436702700005,
"count": 1,
"self": 0.3867308710000543,
"children": {
"run_training.setup": {
"total": 0.02832920299988473,
"count": 1,
"self": 0.02832920299988473
},
"TrainerController.start_learning": {
"total": 410.2193069530001,
"count": 1,
"self": 0.3295558649740542,
"children": {
"TrainerController._reset_env": {
"total": 3.3678142189999107,
"count": 1,
"self": 3.3678142189999107
},
"TrainerController.advance": {
"total": 406.4423945580263,
"count": 18192,
"self": 0.3712666920396259,
"children": {
"env_step": {
"total": 291.99846468798523,
"count": 18192,
"self": 223.82985881096215,
"children": {
"SubprocessEnvManager._take_step": {
"total": 67.9717048750133,
"count": 18192,
"self": 1.1956251410017558,
"children": {
"TorchPolicy.evaluate": {
"total": 66.77607973401155,
"count": 18192,
"self": 66.77607973401155
}
}
},
"workers": {
"total": 0.19690100200978122,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 408.99407021800175,
"count": 18192,
"is_parallel": true,
"self": 211.7187144449938,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0061728040000161855,
"count": 1,
"is_parallel": true,
"self": 0.004027966999956334,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021448370000598516,
"count": 10,
"is_parallel": true,
"self": 0.0021448370000598516
}
}
},
"UnityEnvironment.step": {
"total": 0.034142139999858045,
"count": 1,
"is_parallel": true,
"self": 0.0005493300002399337,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00037635899980159593,
"count": 1,
"is_parallel": true,
"self": 0.00037635899980159593
},
"communicator.exchange": {
"total": 0.03146191799987719,
"count": 1,
"is_parallel": true,
"self": 0.03146191799987719
},
"steps_from_proto": {
"total": 0.0017545329999393289,
"count": 1,
"is_parallel": true,
"self": 0.00033688900020933943,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014176439997299894,
"count": 10,
"is_parallel": true,
"self": 0.0014176439997299894
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 197.27535577300796,
"count": 18191,
"is_parallel": true,
"self": 9.714519340012657,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.35285547999365,
"count": 18191,
"is_parallel": true,
"self": 5.35285547999365
},
"communicator.exchange": {
"total": 151.05641219497693,
"count": 18191,
"is_parallel": true,
"self": 151.05641219497693
},
"steps_from_proto": {
"total": 31.151568758024723,
"count": 18191,
"is_parallel": true,
"self": 5.466508001920374,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.68506075610435,
"count": 181910,
"is_parallel": true,
"self": 25.68506075610435
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 114.07266317800145,
"count": 18192,
"self": 0.381435851999413,
"children": {
"process_trajectory": {
"total": 25.16646871800208,
"count": 18192,
"self": 24.778297106002128,
"children": {
"RLTrainer._checkpoint": {
"total": 0.388171611999951,
"count": 4,
"self": 0.388171611999951
}
}
},
"_update_policy": {
"total": 88.52475860799996,
"count": 90,
"self": 36.13230206198796,
"children": {
"TorchPPOOptimizer.update": {
"total": 52.392456546012,
"count": 4587,
"self": 52.392456546012
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.189998309011571e-07,
"count": 1,
"self": 9.189998309011571e-07
},
"TrainerController._save_models": {
"total": 0.07954139200001009,
"count": 1,
"self": 0.0007900049999989278,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07875138700001116,
"count": 1,
"self": 0.07875138700001116
}
}
}
}
}
}
}