Michellemingxuan's picture
First Push
059a9cb verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8078758120536804,
"min": 0.8078758120536804,
"max": 2.857377767562866,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7678.0517578125,
"min": 7678.0517578125,
"max": 29168.111328125,
"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": 13.155110359191895,
"min": 0.3281885087490082,
"max": 13.16188907623291,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2565.24658203125,
"min": 63.66857147216797,
"max": 2685.025390625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0661864971564629,
"min": 0.06325936975213244,
"max": 0.07414080074230178,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2647459886258516,
"min": 0.26139030443136657,
"max": 0.3601238619223438,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20071336670833476,
"min": 0.0986871820276457,
"max": 0.2877718146671267,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.802853466833339,
"min": 0.3947487281105828,
"max": 1.4235292044924754,
"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": 25.75,
"min": 2.6136363636363638,
"max": 25.977272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1133.0,
"min": 115.0,
"max": 1424.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.75,
"min": 2.6136363636363638,
"max": 25.977272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1133.0,
"min": 115.0,
"max": 1424.0,
"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": "1766252864",
"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 --resume",
"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": "1766253322"
},
"total": 458.19847311800004,
"count": 1,
"self": 0.5454022469998563,
"children": {
"run_training.setup": {
"total": 0.031100756000114416,
"count": 1,
"self": 0.031100756000114416
},
"TrainerController.start_learning": {
"total": 457.62197011500007,
"count": 1,
"self": 0.3557778460206009,
"children": {
"TrainerController._reset_env": {
"total": 4.112378704000093,
"count": 1,
"self": 4.112378704000093
},
"TrainerController.advance": {
"total": 453.0113779839794,
"count": 18192,
"self": 0.38525449596636463,
"children": {
"env_step": {
"total": 330.0214418650198,
"count": 18192,
"self": 259.57918316103155,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.22219992998976,
"count": 18192,
"self": 1.2880489160158959,
"children": {
"TorchPolicy.evaluate": {
"total": 68.93415101397386,
"count": 18192,
"self": 68.93415101397386
}
}
},
"workers": {
"total": 0.2200587739985167,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 455.2631777409904,
"count": 18192,
"is_parallel": true,
"self": 227.46203505796825,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018691109999053879,
"count": 1,
"is_parallel": true,
"self": 0.0005815000001803128,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001287610999725075,
"count": 10,
"is_parallel": true,
"self": 0.001287610999725075
}
}
},
"UnityEnvironment.step": {
"total": 0.03724913400014884,
"count": 1,
"is_parallel": true,
"self": 0.0006132880002951424,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042602400003488583,
"count": 1,
"is_parallel": true,
"self": 0.00042602400003488583
},
"communicator.exchange": {
"total": 0.03423026099994786,
"count": 1,
"is_parallel": true,
"self": 0.03423026099994786
},
"steps_from_proto": {
"total": 0.001979560999870955,
"count": 1,
"is_parallel": true,
"self": 0.0003861049999613897,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015934559999095654,
"count": 10,
"is_parallel": true,
"self": 0.0015934559999095654
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 227.80114268302214,
"count": 18191,
"is_parallel": true,
"self": 10.406085543015479,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.534557874001166,
"count": 18191,
"is_parallel": true,
"self": 5.534557874001166
},
"communicator.exchange": {
"total": 173.6603828130137,
"count": 18191,
"is_parallel": true,
"self": 173.6603828130137
},
"steps_from_proto": {
"total": 38.20011645299178,
"count": 18191,
"is_parallel": true,
"self": 6.888552990953485,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.311563462038293,
"count": 181910,
"is_parallel": true,
"self": 31.311563462038293
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 122.60468162299321,
"count": 18192,
"self": 0.46007459999759703,
"children": {
"process_trajectory": {
"total": 27.762815923997096,
"count": 18192,
"self": 27.11772174499697,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6450941790001252,
"count": 4,
"self": 0.6450941790001252
}
}
},
"_update_policy": {
"total": 94.38179109899852,
"count": 90,
"self": 39.95777290799879,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.42401819099973,
"count": 4587,
"self": 54.42401819099973
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1759998415072914e-06,
"count": 1,
"self": 1.1759998415072914e-06
},
"TrainerController._save_models": {
"total": 0.14243440500013094,
"count": 1,
"self": 0.029826694000348652,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11260771099978228,
"count": 1,
"self": 0.11260771099978228
}
}
}
}
}
}
}