lanqi777's picture
First Push
4d08d50 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7129464149475098,
"min": 0.7067804932594299,
"max": 2.8673388957977295,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6775.8427734375,
"min": 6775.8427734375,
"max": 29269.794921875,
"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": 4.351609706878662,
"min": 0.32194754481315613,
"max": 4.35893440246582,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 848.5639038085938,
"min": 62.45782470703125,
"max": 886.0444946289062,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0672566745387146,
"min": 0.06176831669176418,
"max": 0.0747156599997634,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2690266981548584,
"min": 0.2470732667670567,
"max": 0.37357829999881703,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1641857727047275,
"min": 0.09829291677463106,
"max": 0.21317293293335857,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.65674309081891,
"min": 0.39317166709852425,
"max": 1.0658646646667929,
"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": 25.545454545454547,
"min": 3.6136363636363638,
"max": 25.818181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1124.0,
"min": 159.0,
"max": 1408.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.545454545454547,
"min": 3.6136363636363638,
"max": 25.818181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1124.0,
"min": 159.0,
"max": 1408.0,
"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": "1746595508",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1746595958"
},
"total": 450.319619309,
"count": 1,
"self": 0.4361010400000396,
"children": {
"run_training.setup": {
"total": 0.029429827999933877,
"count": 1,
"self": 0.029429827999933877
},
"TrainerController.start_learning": {
"total": 449.85408844100004,
"count": 1,
"self": 0.4096216660036589,
"children": {
"TrainerController._reset_env": {
"total": 3.882701785999984,
"count": 1,
"self": 3.882701785999984
},
"TrainerController.advance": {
"total": 445.4768555009964,
"count": 18192,
"self": 0.4177925980023929,
"children": {
"env_step": {
"total": 316.16148591399417,
"count": 18192,
"self": 241.7167117939615,
"children": {
"SubprocessEnvManager._take_step": {
"total": 74.21546093701659,
"count": 18192,
"self": 1.3520174020209197,
"children": {
"TorchPolicy.evaluate": {
"total": 72.86344353499567,
"count": 18192,
"self": 72.86344353499567
}
}
},
"workers": {
"total": 0.22931318301607462,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 448.4078741300011,
"count": 18192,
"is_parallel": true,
"self": 236.47793553199563,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006505340999979126,
"count": 1,
"is_parallel": true,
"self": 0.004356954000172664,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002148386999806462,
"count": 10,
"is_parallel": true,
"self": 0.002148386999806462
}
}
},
"UnityEnvironment.step": {
"total": 0.03943821199993636,
"count": 1,
"is_parallel": true,
"self": 0.0006595849998802805,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004388090000020384,
"count": 1,
"is_parallel": true,
"self": 0.0004388090000020384
},
"communicator.exchange": {
"total": 0.03619881200006603,
"count": 1,
"is_parallel": true,
"self": 0.03619881200006603
},
"steps_from_proto": {
"total": 0.0021410059999880104,
"count": 1,
"is_parallel": true,
"self": 0.00042272999996839644,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001718276000019614,
"count": 10,
"is_parallel": true,
"self": 0.001718276000019614
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 211.9299385980055,
"count": 18191,
"is_parallel": true,
"self": 10.264989602002743,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.5631539879916545,
"count": 18191,
"is_parallel": true,
"self": 5.5631539879916545
},
"communicator.exchange": {
"total": 163.6525062170125,
"count": 18191,
"is_parallel": true,
"self": 163.6525062170125
},
"steps_from_proto": {
"total": 32.449288790998594,
"count": 18191,
"is_parallel": true,
"self": 5.931310376977763,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.51797841402083,
"count": 181910,
"is_parallel": true,
"self": 26.51797841402083
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 128.89757698899984,
"count": 18192,
"self": 0.5246932829996922,
"children": {
"process_trajectory": {
"total": 27.99065764900024,
"count": 18192,
"self": 27.51529878600013,
"children": {
"RLTrainer._checkpoint": {
"total": 0.47535886300011043,
"count": 4,
"self": 0.47535886300011043
}
}
},
"_update_policy": {
"total": 100.38222605699991,
"count": 90,
"self": 40.601188837000564,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.78103721999935,
"count": 4587,
"self": 59.78103721999935
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.810000847210176e-07,
"count": 1,
"self": 9.810000847210176e-07
},
"TrainerController._save_models": {
"total": 0.08490850699990915,
"count": 1,
"self": 0.0008157309998750861,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08409277600003406,
"count": 1,
"self": 0.08409277600003406
}
}
}
}
}
}
}