chauvanphuoc's picture
First Push
24740a6 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.273343801498413,
"min": 1.273343801498413,
"max": 2.8852550983428955,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 12101.859375,
"min": 12101.859375,
"max": 29452.68359375,
"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": 8.812703132629395,
"min": 0.39983895421028137,
"max": 8.812703132629395,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1718.47705078125,
"min": 77.56875610351562,
"max": 1770.146240234375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06355173374579275,
"min": 0.06168149118728288,
"max": 0.0742512608847784,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.254206934983171,
"min": 0.24672596474913153,
"max": 0.34704259307192625,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22046966178744448,
"min": 0.11089645267701616,
"max": 0.2954477152988023,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8818786471497779,
"min": 0.44358581070806463,
"max": 1.4772385764940115,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.6940973060000025e-06,
"min": 2.6940973060000025e-06,
"max": 9.729400270599998e-05,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.077638922400001e-05,
"min": 1.077638922400001e-05,
"max": 0.0004617200382800001,
"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": 17.40909090909091,
"min": 3.272727272727273,
"max": 17.863636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 766.0,
"min": 144.0,
"max": 972.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 17.40909090909091,
"min": 3.272727272727273,
"max": 17.863636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 766.0,
"min": 144.0,
"max": 972.0,
"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": "1764758195",
"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": "1764758671"
},
"total": 475.9474950580002,
"count": 1,
"self": 0.7506595949998882,
"children": {
"run_training.setup": {
"total": 0.029509838000194577,
"count": 1,
"self": 0.029509838000194577
},
"TrainerController.start_learning": {
"total": 475.1673256250001,
"count": 1,
"self": 0.3626281770170863,
"children": {
"TrainerController._reset_env": {
"total": 3.0648573389999,
"count": 1,
"self": 3.0648573389999
},
"TrainerController.advance": {
"total": 471.6176876189834,
"count": 18192,
"self": 0.3912986608920619,
"children": {
"env_step": {
"total": 346.04274757704434,
"count": 18192,
"self": 271.534739774037,
"children": {
"SubprocessEnvManager._take_step": {
"total": 74.28049094898552,
"count": 18192,
"self": 1.3143401289580652,
"children": {
"TorchPolicy.evaluate": {
"total": 72.96615082002745,
"count": 18192,
"self": 72.96615082002745
}
}
},
"workers": {
"total": 0.22751685402181465,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 473.2932358799999,
"count": 18192,
"is_parallel": true,
"self": 234.21857645800492,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0056900900003711286,
"count": 1,
"is_parallel": true,
"self": 0.003976740001235157,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017133499991359713,
"count": 10,
"is_parallel": true,
"self": 0.0017133499991359713
}
}
},
"UnityEnvironment.step": {
"total": 0.04053672199961511,
"count": 1,
"is_parallel": true,
"self": 0.0006694299995615438,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044735200026480015,
"count": 1,
"is_parallel": true,
"self": 0.00044735200026480015
},
"communicator.exchange": {
"total": 0.03715154399969833,
"count": 1,
"is_parallel": true,
"self": 0.03715154399969833
},
"steps_from_proto": {
"total": 0.0022683960000904335,
"count": 1,
"is_parallel": true,
"self": 0.0004273879999345809,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018410080001558526,
"count": 10,
"is_parallel": true,
"self": 0.0018410080001558526
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 239.07465942199497,
"count": 18191,
"is_parallel": true,
"self": 11.254823781986488,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.036177227030294,
"count": 18191,
"is_parallel": true,
"self": 6.036177227030294
},
"communicator.exchange": {
"total": 180.5723107680169,
"count": 18191,
"is_parallel": true,
"self": 180.5723107680169
},
"steps_from_proto": {
"total": 41.21134764496128,
"count": 18191,
"is_parallel": true,
"self": 7.26818962790685,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.94315801705443,
"count": 181910,
"is_parallel": true,
"self": 33.94315801705443
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 125.18364138104698,
"count": 18192,
"self": 0.4504627930564311,
"children": {
"process_trajectory": {
"total": 28.196123955989606,
"count": 18192,
"self": 27.61457370898961,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5815502469999956,
"count": 4,
"self": 0.5815502469999956
}
}
},
"_update_policy": {
"total": 96.53705463200095,
"count": 90,
"self": 39.846037421983965,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.69101721001698,
"count": 4587,
"self": 56.69101721001698
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5189998521236703e-06,
"count": 1,
"self": 1.5189998521236703e-06
},
"TrainerController._save_models": {
"total": 0.1221509709998827,
"count": 1,
"self": 0.0008143389995893813,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12133663200029332,
"count": 1,
"self": 0.12133663200029332
}
}
}
}
}
}
}