Adripro01's picture
First Push
2b5e329 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9249752759933472,
"min": 0.9249752759933472,
"max": 2.859248638153076,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8831.6640625,
"min": 8831.6640625,
"max": 29313.017578125,
"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": 12.61305046081543,
"min": 0.42989370226860046,
"max": 12.61305046081543,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2459.544921875,
"min": 83.39937591552734,
"max": 2531.85107421875,
"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": 0.06966369500279304,
"min": 0.06478574341157332,
"max": 0.0736334759687238,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27865478001117217,
"min": 0.2591429736462933,
"max": 0.3662801925646479,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19826797111069455,
"min": 0.1305514712996014,
"max": 0.26709802178483383,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7930718844427782,
"min": 0.5222058851984056,
"max": 1.2907493795249976,
"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": 24.727272727272727,
"min": 3.8636363636363638,
"max": 24.90909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1088.0,
"min": 170.0,
"max": 1370.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.727272727272727,
"min": 3.8636363636363638,
"max": 24.90909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1088.0,
"min": 170.0,
"max": 1370.0,
"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": "1724050127",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1724050650"
},
"total": 522.37029942,
"count": 1,
"self": 0.4389546140000675,
"children": {
"run_training.setup": {
"total": 0.06394905199999812,
"count": 1,
"self": 0.06394905199999812
},
"TrainerController.start_learning": {
"total": 521.867395754,
"count": 1,
"self": 0.733076457005609,
"children": {
"TrainerController._reset_env": {
"total": 3.2231589640000493,
"count": 1,
"self": 3.2231589640000493
},
"TrainerController.advance": {
"total": 517.8105523129943,
"count": 18202,
"self": 0.36356519297601153,
"children": {
"env_step": {
"total": 517.4469871200183,
"count": 18202,
"self": 339.5951896960087,
"children": {
"SubprocessEnvManager._take_step": {
"total": 177.4810293139958,
"count": 18202,
"self": 1.8671360059986455,
"children": {
"TorchPolicy.evaluate": {
"total": 175.61389330799716,
"count": 18202,
"self": 175.61389330799716
}
}
},
"workers": {
"total": 0.3707681100138416,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 520.2793915860066,
"count": 18202,
"is_parallel": true,
"self": 257.31693140599054,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0054860770001141645,
"count": 1,
"is_parallel": true,
"self": 0.0036400400001639355,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001846036999950229,
"count": 10,
"is_parallel": true,
"self": 0.001846036999950229
}
}
},
"UnityEnvironment.step": {
"total": 0.09726316799992674,
"count": 1,
"is_parallel": true,
"self": 0.000721306999821536,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00043492899999364454,
"count": 1,
"is_parallel": true,
"self": 0.00043492899999364454
},
"communicator.exchange": {
"total": 0.09393531099999564,
"count": 1,
"is_parallel": true,
"self": 0.09393531099999564
},
"steps_from_proto": {
"total": 0.0021716210001159197,
"count": 1,
"is_parallel": true,
"self": 0.00040991100013343384,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001761709999982486,
"count": 10,
"is_parallel": true,
"self": 0.001761709999982486
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 262.962460180016,
"count": 18201,
"is_parallel": true,
"self": 11.981309945989324,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.339636003997157,
"count": 18201,
"is_parallel": true,
"self": 6.339636003997157
},
"communicator.exchange": {
"total": 205.31794527901184,
"count": 18201,
"is_parallel": true,
"self": 205.31794527901184
},
"steps_from_proto": {
"total": 39.323568951017705,
"count": 18201,
"is_parallel": true,
"self": 7.646373931976768,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.677195019040937,
"count": 182010,
"is_parallel": true,
"self": 31.677195019040937
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001729420000629034,
"count": 1,
"self": 0.0001729420000629034,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 511.36845889012693,
"count": 786541,
"is_parallel": true,
"self": 16.571291379260174,
"children": {
"process_trajectory": {
"total": 286.9539405238668,
"count": 786541,
"is_parallel": true,
"self": 286.05446090986675,
"children": {
"RLTrainer._checkpoint": {
"total": 0.899479614000029,
"count": 4,
"is_parallel": true,
"self": 0.899479614000029
}
}
},
"_update_policy": {
"total": 207.84322698699998,
"count": 90,
"is_parallel": true,
"self": 63.98864059099492,
"children": {
"TorchPPOOptimizer.update": {
"total": 143.85458639600506,
"count": 4587,
"is_parallel": true,
"self": 143.85458639600506
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10043507799991858,
"count": 1,
"self": 0.0009797529999104881,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09945532500000809,
"count": 1,
"self": 0.09945532500000809
}
}
}
}
}
}
}