maskjp's picture
First Push
11b1983 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8937026262283325,
"min": 0.8937026262283325,
"max": 2.8281283378601074,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8493.75,
"min": 8493.75,
"max": 28869.53515625,
"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": 12.371899604797363,
"min": 0.24371452629566193,
"max": 12.371899604797363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2412.5205078125,
"min": 47.280616760253906,
"max": 2503.011962890625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07029773062993841,
"min": 0.060938233103918125,
"max": 0.07632618613276339,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28119092251975364,
"min": 0.25478989210986425,
"max": 0.3816309306638169,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2090743560270936,
"min": 0.10840906705775791,
"max": 0.2697950044683382,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8362974241083744,
"min": 0.43363626823103163,
"max": 1.348975022341691,
"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": 24.386363636363637,
"min": 3.0681818181818183,
"max": 24.490909090909092,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1073.0,
"min": 135.0,
"max": 1347.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.386363636363637,
"min": 3.0681818181818183,
"max": 24.490909090909092,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1073.0,
"min": 135.0,
"max": 1347.0,
"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": "1741643452",
"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": "1741643903"
},
"total": 450.96872427300013,
"count": 1,
"self": 0.43649305400015237,
"children": {
"run_training.setup": {
"total": 0.023262524000074336,
"count": 1,
"self": 0.023262524000074336
},
"TrainerController.start_learning": {
"total": 450.5089686949999,
"count": 1,
"self": 0.36839166500988085,
"children": {
"TrainerController._reset_env": {
"total": 2.9242768380000825,
"count": 1,
"self": 2.9242768380000825
},
"TrainerController.advance": {
"total": 447.1231771849899,
"count": 18192,
"self": 0.3889099190076877,
"children": {
"env_step": {
"total": 319.0436296059969,
"count": 18192,
"self": 242.63016100300388,
"children": {
"SubprocessEnvManager._take_step": {
"total": 76.19176350400505,
"count": 18192,
"self": 1.3346514300176295,
"children": {
"TorchPolicy.evaluate": {
"total": 74.85711207398742,
"count": 18192,
"self": 74.85711207398742
}
}
},
"workers": {
"total": 0.22170509898796809,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 448.95433298900457,
"count": 18192,
"is_parallel": true,
"self": 236.17988465602173,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005232317000036346,
"count": 1,
"is_parallel": true,
"self": 0.0037157200001729507,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015165969998633955,
"count": 10,
"is_parallel": true,
"self": 0.0015165969998633955
}
}
},
"UnityEnvironment.step": {
"total": 0.03896241600000394,
"count": 1,
"is_parallel": true,
"self": 0.0006846410001344339,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042069799997079826,
"count": 1,
"is_parallel": true,
"self": 0.00042069799997079826
},
"communicator.exchange": {
"total": 0.03554490299995905,
"count": 1,
"is_parallel": true,
"self": 0.03554490299995905
},
"steps_from_proto": {
"total": 0.0023121739999396596,
"count": 1,
"is_parallel": true,
"self": 0.0004190799998013972,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018930940001382623,
"count": 10,
"is_parallel": true,
"self": 0.0018930940001382623
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 212.77444833298284,
"count": 18191,
"is_parallel": true,
"self": 9.989127685963922,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.668770317006761,
"count": 18191,
"is_parallel": true,
"self": 5.668770317006761
},
"communicator.exchange": {
"total": 163.69038208999893,
"count": 18191,
"is_parallel": true,
"self": 163.69038208999893
},
"steps_from_proto": {
"total": 33.426168240013226,
"count": 18191,
"is_parallel": true,
"self": 6.034555305027766,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.39161293498546,
"count": 181910,
"is_parallel": true,
"self": 27.39161293498546
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 127.69063765998533,
"count": 18192,
"self": 0.448172917990064,
"children": {
"process_trajectory": {
"total": 28.540504757994427,
"count": 18192,
"self": 27.99748802399438,
"children": {
"RLTrainer._checkpoint": {
"total": 0.543016734000048,
"count": 4,
"self": 0.543016734000048
}
}
},
"_update_policy": {
"total": 98.70195998400084,
"count": 90,
"self": 39.89955864799788,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.80240133600296,
"count": 4587,
"self": 58.80240133600296
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.089999366551638e-07,
"count": 1,
"self": 9.089999366551638e-07
},
"TrainerController._save_models": {
"total": 0.09312209800009441,
"count": 1,
"self": 0.0009480660000917851,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09217403200000263,
"count": 1,
"self": 0.09217403200000263
}
}
}
}
}
}
}