mviano's picture
First Push
354888d verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7447940111160278,
"min": 0.7447940111160278,
"max": 2.853853225708008,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7078.5224609375,
"min": 7078.5224609375,
"max": 29132.1328125,
"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": 13.154930114746094,
"min": 0.47936737537384033,
"max": 13.154930114746094,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2565.21142578125,
"min": 92.99726867675781,
"max": 2677.698486328125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06834532016414324,
"min": 0.05788411666335556,
"max": 0.07537716527973923,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27338128065657297,
"min": 0.23153646665342223,
"max": 0.3768858263986961,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20301031869123964,
"min": 0.14681559762296575,
"max": 0.2935887314379215,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8120412747649586,
"min": 0.587262390491863,
"max": 1.4184847646484187,
"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": 25.84090909090909,
"min": 3.8181818181818183,
"max": 25.98181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1137.0,
"min": 168.0,
"max": 1429.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.84090909090909,
"min": 3.8181818181818183,
"max": 25.98181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1137.0,
"min": 168.0,
"max": 1429.0,
"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": "1729809846",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1729810235"
},
"total": 389.3309288720002,
"count": 1,
"self": 0.3214099430006172,
"children": {
"run_training.setup": {
"total": 0.057352120999894396,
"count": 1,
"self": 0.057352120999894396
},
"TrainerController.start_learning": {
"total": 388.9521668079997,
"count": 1,
"self": 0.39719352197516855,
"children": {
"TrainerController._reset_env": {
"total": 1.9701251060005234,
"count": 1,
"self": 1.9701251060005234
},
"TrainerController.advance": {
"total": 386.49360715602324,
"count": 18192,
"self": 0.37854645186325797,
"children": {
"env_step": {
"total": 269.42414049510444,
"count": 18192,
"self": 201.7814263380833,
"children": {
"SubprocessEnvManager._take_step": {
"total": 67.41327777394963,
"count": 18192,
"self": 1.2028575039630596,
"children": {
"TorchPolicy.evaluate": {
"total": 66.21042026998657,
"count": 18192,
"self": 66.21042026998657
}
}
},
"workers": {
"total": 0.2294363830715156,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 387.9336656759924,
"count": 18192,
"is_parallel": true,
"self": 210.94507790197986,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0022526689999722294,
"count": 1,
"is_parallel": true,
"self": 0.0006668679998256266,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015858010001466027,
"count": 10,
"is_parallel": true,
"self": 0.0015858010001466027
}
}
},
"UnityEnvironment.step": {
"total": 0.026818923000064387,
"count": 1,
"is_parallel": true,
"self": 0.0004289520002203062,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00030205000075511634,
"count": 1,
"is_parallel": true,
"self": 0.00030205000075511634
},
"communicator.exchange": {
"total": 0.024800567999591294,
"count": 1,
"is_parallel": true,
"self": 0.024800567999591294
},
"steps_from_proto": {
"total": 0.0012873529994976707,
"count": 1,
"is_parallel": true,
"self": 0.00026646300102584064,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00102088999847183,
"count": 10,
"is_parallel": true,
"self": 0.00102088999847183
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 176.98858777401256,
"count": 18191,
"is_parallel": true,
"self": 6.332703600020068,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.3511107880158306,
"count": 18191,
"is_parallel": true,
"self": 3.3511107880158306
},
"communicator.exchange": {
"total": 146.7488894689659,
"count": 18191,
"is_parallel": true,
"self": 146.7488894689659
},
"steps_from_proto": {
"total": 20.55588391701076,
"count": 18191,
"is_parallel": true,
"self": 4.06688357612893,
"children": {
"_process_rank_one_or_two_observation": {
"total": 16.48900034088183,
"count": 181910,
"is_parallel": true,
"self": 16.48900034088183
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 116.69092020905555,
"count": 18192,
"self": 0.46974823399341403,
"children": {
"process_trajectory": {
"total": 25.419528210067256,
"count": 18192,
"self": 25.041954825068387,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3775733849988683,
"count": 4,
"self": 0.3775733849988683
}
}
},
"_update_policy": {
"total": 90.80164376499488,
"count": 90,
"self": 36.292938737010445,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.50870502798443,
"count": 4587,
"self": 54.50870502798443
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1620004443102516e-06,
"count": 1,
"self": 1.1620004443102516e-06
},
"TrainerController._save_models": {
"total": 0.09123986200029321,
"count": 1,
"self": 0.0011230420004721964,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09011681999982102,
"count": 1,
"self": 0.09011681999982102
}
}
}
}
}
}
}