Pro152's picture
First Push
b05f8b9 verified
Raw
History Blame Contribute Delete
17.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9398170709609985,
"min": 0.9261173009872437,
"max": 2.798288583755493,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8932.021484375,
"min": 8932.021484375,
"max": 28564.9296875,
"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": 11.850730895996094,
"min": 0.47341516613960266,
"max": 11.850730895996094,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2310.892578125,
"min": 91.84254455566406,
"max": 2362.18212890625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06634950083132614,
"min": 0.058621352375007076,
"max": 0.0769829727645379,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26539800332530455,
"min": 0.2344854095000283,
"max": 0.37799811085873375,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.204661994880321,
"min": 0.1548574051760393,
"max": 0.33013906154562445,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.818647979521284,
"min": 0.6194296207041572,
"max": 1.3932845253570407,
"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": 23.613636363636363,
"min": 4.454545454545454,
"max": 23.613636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1039.0,
"min": 196.0,
"max": 1275.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.613636363636363,
"min": 4.454545454545454,
"max": 23.613636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1039.0,
"min": 196.0,
"max": 1275.0,
"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": "1788180742",
"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": "1788181353"
},
"total": 610.7185357000001,
"count": 1,
"self": 0.587546341000234,
"children": {
"run_training.setup": {
"total": 0.037620483999944554,
"count": 1,
"self": 0.037620483999944554
},
"TrainerController.start_learning": {
"total": 610.0933688749999,
"count": 1,
"self": 0.6477207620134777,
"children": {
"TrainerController._reset_env": {
"total": 3.717915637000033,
"count": 1,
"self": 3.717915637000033
},
"TrainerController.advance": {
"total": 605.6570244759866,
"count": 18192,
"self": 0.7038472450044537,
"children": {
"env_step": {
"total": 440.50598976299057,
"count": 18192,
"self": 382.4508170639808,
"children": {
"SubprocessEnvManager._take_step": {
"total": 57.659623716001306,
"count": 18192,
"self": 2.067511044013827,
"children": {
"TorchPolicy.evaluate": {
"total": 55.59211267198748,
"count": 18192,
"self": 55.59211267198748
}
}
},
"workers": {
"total": 0.3955489830084389,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 606.7687318510054,
"count": 18192,
"is_parallel": true,
"self": 275.63147316302,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006633870000086972,
"count": 1,
"is_parallel": true,
"self": 0.004668933000402831,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019649369996841415,
"count": 10,
"is_parallel": true,
"self": 0.0019649369996841415
}
}
},
"UnityEnvironment.step": {
"total": 0.09254376599983516,
"count": 1,
"is_parallel": true,
"self": 0.00070384900004683,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0012296219999825553,
"count": 1,
"is_parallel": true,
"self": 0.0012296219999825553
},
"communicator.exchange": {
"total": 0.08633458799999971,
"count": 1,
"is_parallel": true,
"self": 0.08633458799999971
},
"steps_from_proto": {
"total": 0.0042757069998060615,
"count": 1,
"is_parallel": true,
"self": 0.0004836489999888727,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003792057999817189,
"count": 10,
"is_parallel": true,
"self": 0.003792057999817189
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 331.1372586879854,
"count": 18191,
"is_parallel": true,
"self": 14.281303802966931,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.5707605470011,
"count": 18191,
"is_parallel": true,
"self": 7.5707605470011
},
"communicator.exchange": {
"total": 258.63732557799153,
"count": 18191,
"is_parallel": true,
"self": 258.63732557799153
},
"steps_from_proto": {
"total": 50.64786876002586,
"count": 18191,
"is_parallel": true,
"self": 8.865402514070865,
"children": {
"_process_rank_one_or_two_observation": {
"total": 41.78246624595499,
"count": 181910,
"is_parallel": true,
"self": 41.78246624595499
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 164.44718746799163,
"count": 18192,
"self": 0.809630265002852,
"children": {
"process_trajectory": {
"total": 30.123857518989553,
"count": 18192,
"self": 29.73572368898931,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3881338300002426,
"count": 4,
"self": 0.3881338300002426
}
}
},
"_update_policy": {
"total": 133.51369968399922,
"count": 90,
"self": 47.66110107500754,
"children": {
"TorchPPOOptimizer.update": {
"total": 85.85259860899168,
"count": 4587,
"self": 85.85259860899168
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.719998731976375e-07,
"count": 1,
"self": 8.719998731976375e-07
},
"TrainerController._save_models": {
"total": 0.07070712799986723,
"count": 1,
"self": 0.001095314999929542,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06961181299993768,
"count": 1,
"self": 0.06961181299993768
}
}
}
}
}
}
}