GalacticWalker's picture
First Push
d52e537 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7679681777954102,
"min": 0.7510733604431152,
"max": 2.8666915893554688,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7298.76953125,
"min": 7298.76953125,
"max": 29263.1875,
"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": 12.806489944458008,
"min": 0.30880168080329895,
"max": 12.848431587219238,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2497.265625,
"min": 59.907527923583984,
"max": 2621.080078125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06375365077443369,
"min": 0.06323591977892576,
"max": 0.0743215119261246,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25501460309773477,
"min": 0.25294367911570304,
"max": 0.3647429032237543,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21574248212809655,
"min": 0.11939822764857216,
"max": 0.27588263878635333,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8629699285123862,
"min": 0.47759291059428866,
"max": 1.3794131939317666,
"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": 24.772727272727273,
"min": 3.409090909090909,
"max": 25.295454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1090.0,
"min": 150.0,
"max": 1387.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.772727272727273,
"min": 3.409090909090909,
"max": 25.295454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1090.0,
"min": 150.0,
"max": 1387.0,
"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": "1767310985",
"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=SnowballTarget2 --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": "1767311412"
},
"total": 427.2262991179998,
"count": 1,
"self": 0.42559989399978804,
"children": {
"run_training.setup": {
"total": 0.023909748000050968,
"count": 1,
"self": 0.023909748000050968
},
"TrainerController.start_learning": {
"total": 426.776789476,
"count": 1,
"self": 0.33054240101546384,
"children": {
"TrainerController._reset_env": {
"total": 1.850878241999908,
"count": 1,
"self": 1.850878241999908
},
"TrainerController.advance": {
"total": 424.51995973098474,
"count": 18192,
"self": 0.3463757739664288,
"children": {
"env_step": {
"total": 308.31137106400433,
"count": 18192,
"self": 241.7088796460166,
"children": {
"SubprocessEnvManager._take_step": {
"total": 66.39502564099917,
"count": 18192,
"self": 1.2261419180013036,
"children": {
"TorchPolicy.evaluate": {
"total": 65.16888372299786,
"count": 18192,
"self": 65.16888372299786
}
}
},
"workers": {
"total": 0.20746577698855617,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 424.9818393420155,
"count": 18192,
"is_parallel": true,
"self": 212.24099655802206,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002144684999848323,
"count": 1,
"is_parallel": true,
"self": 0.0006495119998817245,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014951729999665986,
"count": 10,
"is_parallel": true,
"self": 0.0014951729999665986
}
}
},
"UnityEnvironment.step": {
"total": 0.03484075500000472,
"count": 1,
"is_parallel": true,
"self": 0.0005449370000860654,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003942809998989105,
"count": 1,
"is_parallel": true,
"self": 0.0003942809998989105
},
"communicator.exchange": {
"total": 0.032130348999999114,
"count": 1,
"is_parallel": true,
"self": 0.032130348999999114
},
"steps_from_proto": {
"total": 0.0017711880000206293,
"count": 1,
"is_parallel": true,
"self": 0.000345826000057059,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014253619999635703,
"count": 10,
"is_parallel": true,
"self": 0.0014253619999635703
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 212.74084278399346,
"count": 18191,
"is_parallel": true,
"self": 10.106737000013482,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.425340015979145,
"count": 18191,
"is_parallel": true,
"self": 5.425340015979145
},
"communicator.exchange": {
"total": 161.39926884701686,
"count": 18191,
"is_parallel": true,
"self": 161.39926884701686
},
"steps_from_proto": {
"total": 35.809496920983975,
"count": 18191,
"is_parallel": true,
"self": 6.430676449940165,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.37882047104381,
"count": 181910,
"is_parallel": true,
"self": 29.37882047104381
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 115.86221289301398,
"count": 18192,
"self": 0.4161938450129128,
"children": {
"process_trajectory": {
"total": 25.149397276000855,
"count": 18192,
"self": 24.74881624000068,
"children": {
"RLTrainer._checkpoint": {
"total": 0.400581036000176,
"count": 4,
"self": 0.400581036000176
}
}
},
"_update_policy": {
"total": 90.29662177200021,
"count": 90,
"self": 37.497259482997606,
"children": {
"TorchPPOOptimizer.update": {
"total": 52.7993622890026,
"count": 4587,
"self": 52.7993622890026
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.539999155094847e-07,
"count": 1,
"self": 9.539999155094847e-07
},
"TrainerController._save_models": {
"total": 0.07540814799995132,
"count": 1,
"self": 0.0006656410000687174,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07474250699988261,
"count": 1,
"self": 0.07474250699988261
}
}
}
}
}
}
}