css919's picture
First Push
97e67a9
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9161278605461121,
"min": 0.9161278605461121,
"max": 2.8532607555389404,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8737.111328125,
"min": 8737.111328125,
"max": 29220.2421875,
"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": 12.792947769165039,
"min": 0.34236836433410645,
"max": 12.792947769165039,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2494.624755859375,
"min": 66.41946411132812,
"max": 2585.27099609375,
"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.Losses.PolicyLoss.mean": {
"value": 0.06493873101392049,
"min": 0.06346165729691183,
"max": 0.07671150070211083,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25975492405568196,
"min": 0.25975492405568196,
"max": 0.3835575035105541,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21025418541302868,
"min": 0.12672507601753608,
"max": 0.3030462482980653,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8410167416521147,
"min": 0.5069003040701443,
"max": 1.5152312414903266,
"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.CumulativeReward.mean": {
"value": 24.954545454545453,
"min": 3.840909090909091,
"max": 25.181818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1098.0,
"min": 169.0,
"max": 1385.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.954545454545453,
"min": 3.840909090909091,
"max": 25.181818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1098.0,
"min": 169.0,
"max": 1385.0,
"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": "1674725916",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1674726332"
},
"total": 415.430992393,
"count": 1,
"self": 0.3925213560000884,
"children": {
"run_training.setup": {
"total": 0.10521980199996506,
"count": 1,
"self": 0.10521980199996506
},
"TrainerController.start_learning": {
"total": 414.93325123499994,
"count": 1,
"self": 0.5553333460001113,
"children": {
"TrainerController._reset_env": {
"total": 9.228487502000007,
"count": 1,
"self": 9.228487502000007
},
"TrainerController.advance": {
"total": 405.0301738779998,
"count": 18202,
"self": 0.2725815429954537,
"children": {
"env_step": {
"total": 404.75759233500435,
"count": 18202,
"self": 264.3967090680163,
"children": {
"SubprocessEnvManager._take_step": {
"total": 140.10128729499974,
"count": 18202,
"self": 1.3767446059999315,
"children": {
"TorchPolicy.evaluate": {
"total": 138.7245426889998,
"count": 18202,
"self": 31.53530204800427,
"children": {
"TorchPolicy.sample_actions": {
"total": 107.18924064099554,
"count": 18202,
"self": 107.18924064099554
}
}
}
}
},
"workers": {
"total": 0.2595959719882899,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 413.7167646920082,
"count": 18202,
"is_parallel": true,
"self": 199.30242841499904,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005957577999993191,
"count": 1,
"is_parallel": true,
"self": 0.002956752000045526,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003000825999947665,
"count": 10,
"is_parallel": true,
"self": 0.003000825999947665
}
}
},
"UnityEnvironment.step": {
"total": 0.030716295999980048,
"count": 1,
"is_parallel": true,
"self": 0.0005080490000182181,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00027791099995511104,
"count": 1,
"is_parallel": true,
"self": 0.00027791099995511104
},
"communicator.exchange": {
"total": 0.02809186900003624,
"count": 1,
"is_parallel": true,
"self": 0.02809186900003624
},
"steps_from_proto": {
"total": 0.0018384669999704784,
"count": 1,
"is_parallel": true,
"self": 0.00043131699993637085,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014071500000341075,
"count": 10,
"is_parallel": true,
"self": 0.0014071500000341075
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 214.41433627700917,
"count": 18201,
"is_parallel": true,
"self": 8.092461214004118,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.668195442001149,
"count": 18201,
"is_parallel": true,
"self": 4.668195442001149
},
"communicator.exchange": {
"total": 173.05000683600332,
"count": 18201,
"is_parallel": true,
"self": 173.05000683600332
},
"steps_from_proto": {
"total": 28.603672785000583,
"count": 18201,
"is_parallel": true,
"self": 6.205202605018144,
"children": {
"_process_rank_one_or_two_observation": {
"total": 22.39847017998244,
"count": 182010,
"is_parallel": true,
"self": 22.39847017998244
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.4414999933906074e-05,
"count": 1,
"self": 4.4414999933906074e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 402.24884930699363,
"count": 337903,
"is_parallel": true,
"self": 8.704228050026984,
"children": {
"process_trajectory": {
"total": 231.91618136596696,
"count": 337903,
"is_parallel": true,
"self": 231.221228975967,
"children": {
"RLTrainer._checkpoint": {
"total": 0.694952389999969,
"count": 4,
"is_parallel": true,
"self": 0.694952389999969
}
}
},
"_update_policy": {
"total": 161.6284398909997,
"count": 90,
"is_parallel": true,
"self": 40.90873552099998,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.7197043699997,
"count": 4587,
"is_parallel": true,
"self": 120.7197043699997
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.11921209400009047,
"count": 1,
"self": 0.0008759330000884802,
"children": {
"RLTrainer._checkpoint": {
"total": 0.118336161000002,
"count": 1,
"self": 0.118336161000002
}
}
}
}
}
}
}