Dioptry's picture
First Push
944636a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8459895849227905,
"min": 0.8459895849227905,
"max": 2.8516364097595215,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8040.28515625,
"min": 8040.28515625,
"max": 29109.50390625,
"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": 13.135013580322266,
"min": 0.35762181878089905,
"max": 13.17622184753418,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2561.32763671875,
"min": 69.37863159179688,
"max": 2687.94921875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06723032886757033,
"min": 0.061632294165011606,
"max": 0.07285667428856388,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2689213154702813,
"min": 0.24652917666004642,
"max": 0.3642833714428194,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22506395756613973,
"min": 0.0992130404144215,
"max": 0.30616841289926977,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9002558302645589,
"min": 0.396852161657686,
"max": 1.4536737454872506,
"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": 25.727272727272727,
"min": 2.8863636363636362,
"max": 26.25,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1132.0,
"min": 127.0,
"max": 1415.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.727272727272727,
"min": 2.8863636363636362,
"max": 26.25,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1132.0,
"min": 127.0,
"max": 1415.0,
"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": "1743505202",
"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": "1743505624"
},
"total": 421.54957773,
"count": 1,
"self": 0.4416890950000152,
"children": {
"run_training.setup": {
"total": 0.023296590999962064,
"count": 1,
"self": 0.023296590999962064
},
"TrainerController.start_learning": {
"total": 421.08459204400003,
"count": 1,
"self": 0.3254347069948835,
"children": {
"TrainerController._reset_env": {
"total": 3.2753787609999563,
"count": 1,
"self": 3.2753787609999563
},
"TrainerController.advance": {
"total": 417.39523795900516,
"count": 18192,
"self": 0.35043577999340414,
"children": {
"env_step": {
"total": 294.0135222239952,
"count": 18192,
"self": 224.35596590701766,
"children": {
"SubprocessEnvManager._take_step": {
"total": 69.45864417498024,
"count": 18192,
"self": 1.2239929369781066,
"children": {
"TorchPolicy.evaluate": {
"total": 68.23465123800213,
"count": 18192,
"self": 68.23465123800213
}
}
},
"workers": {
"total": 0.19891214199731166,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 419.6462930189915,
"count": 18192,
"is_parallel": true,
"self": 222.28455804199461,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0056184229999871604,
"count": 1,
"is_parallel": true,
"self": 0.003995752000150787,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001622670999836373,
"count": 10,
"is_parallel": true,
"self": 0.001622670999836373
}
}
},
"UnityEnvironment.step": {
"total": 0.03538156299998718,
"count": 1,
"is_parallel": true,
"self": 0.0005828229999451651,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004175420000365193,
"count": 1,
"is_parallel": true,
"self": 0.0004175420000365193
},
"communicator.exchange": {
"total": 0.0325335320000022,
"count": 1,
"is_parallel": true,
"self": 0.0325335320000022
},
"steps_from_proto": {
"total": 0.0018476660000033007,
"count": 1,
"is_parallel": true,
"self": 0.0003414340001199889,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015062319998833118,
"count": 10,
"is_parallel": true,
"self": 0.0015062319998833118
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 197.3617349769969,
"count": 18191,
"is_parallel": true,
"self": 9.655453234995889,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.334177416006128,
"count": 18191,
"is_parallel": true,
"self": 5.334177416006128
},
"communicator.exchange": {
"total": 151.61926085199013,
"count": 18191,
"is_parallel": true,
"self": 151.61926085199013
},
"steps_from_proto": {
"total": 30.75284347400475,
"count": 18191,
"is_parallel": true,
"self": 5.409702040039406,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.343141433965343,
"count": 181910,
"is_parallel": true,
"self": 25.343141433965343
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 123.03127995501654,
"count": 18192,
"self": 0.41008162700632056,
"children": {
"process_trajectory": {
"total": 26.684227813009784,
"count": 18192,
"self": 26.233350381009927,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4508774319998565,
"count": 4,
"self": 0.4508774319998565
}
}
},
"_update_policy": {
"total": 95.93697051500044,
"count": 90,
"self": 38.55719609999517,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.37977441500527,
"count": 4587,
"self": 57.37977441500527
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.499999578110874e-07,
"count": 1,
"self": 9.499999578110874e-07
},
"TrainerController._save_models": {
"total": 0.08853966700007732,
"count": 1,
"self": 0.0009386199999426026,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08760104700013471,
"count": 1,
"self": 0.08760104700013471
}
}
}
}
}
}
}