lnros's picture
First training of SnowballTarget
f7cfe1f
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8868127465248108,
"min": 0.8795204758644104,
"max": 2.863415479660034,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8467.2880859375,
"min": 8467.2880859375,
"max": 29324.23828125,
"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": 12.88078784942627,
"min": 0.464897483587265,
"max": 12.896929740905762,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2511.753662109375,
"min": 90.19010925292969,
"max": 2630.9736328125,
"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": 0.06888187039779345,
"min": 0.0615997187258686,
"max": 0.07557328536723598,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2755274815911738,
"min": 0.2463988749034744,
"max": 0.35824011479071133,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1998397180554914,
"min": 0.11945887023523705,
"max": 0.28765374649973474,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7993588722219656,
"min": 0.4778354809409482,
"max": 1.4382687324986738,
"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": 25.15909090909091,
"min": 3.3863636363636362,
"max": 25.681818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1107.0,
"min": 149.0,
"max": 1400.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.15909090909091,
"min": 3.3863636363636362,
"max": 25.681818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1107.0,
"min": 149.0,
"max": 1400.0,
"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": "1674484900",
"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": "1674485349"
},
"total": 449.866916671,
"count": 1,
"self": 0.39293873899998744,
"children": {
"run_training.setup": {
"total": 0.10572918299999401,
"count": 1,
"self": 0.10572918299999401
},
"TrainerController.start_learning": {
"total": 449.36824874900003,
"count": 1,
"self": 0.5725618690008787,
"children": {
"TrainerController._reset_env": {
"total": 10.583582312999994,
"count": 1,
"self": 10.583582312999994
},
"TrainerController.advance": {
"total": 438.08314388499906,
"count": 18201,
"self": 0.3032615539984249,
"children": {
"env_step": {
"total": 437.77988233100064,
"count": 18201,
"self": 290.08373955600257,
"children": {
"SubprocessEnvManager._take_step": {
"total": 147.4003966559968,
"count": 18201,
"self": 1.5864445020037863,
"children": {
"TorchPolicy.evaluate": {
"total": 145.813952153993,
"count": 18201,
"self": 34.40234883099822,
"children": {
"TorchPolicy.sample_actions": {
"total": 111.41160332299478,
"count": 18201,
"self": 111.41160332299478
}
}
}
}
},
"workers": {
"total": 0.2957461190012509,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 448.09683703199653,
"count": 18201,
"is_parallel": true,
"self": 212.54138244399633,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007407008999990694,
"count": 1,
"is_parallel": true,
"self": 0.0043215379999992365,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0030854709999914576,
"count": 10,
"is_parallel": true,
"self": 0.0030854709999914576
}
}
},
"UnityEnvironment.step": {
"total": 0.04438020400002074,
"count": 1,
"is_parallel": true,
"self": 0.0005872549999992316,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00026124199999344455,
"count": 1,
"is_parallel": true,
"self": 0.00026124199999344455
},
"communicator.exchange": {
"total": 0.04133687800000985,
"count": 1,
"is_parallel": true,
"self": 0.04133687800000985
},
"steps_from_proto": {
"total": 0.002194829000018217,
"count": 1,
"is_parallel": true,
"self": 0.0006929180000554425,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015019109999627744,
"count": 10,
"is_parallel": true,
"self": 0.0015019109999627744
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 235.5554545880002,
"count": 18200,
"is_parallel": true,
"self": 8.71241744400055,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.077949274000446,
"count": 18200,
"is_parallel": true,
"self": 5.077949274000446
},
"communicator.exchange": {
"total": 188.54358398199835,
"count": 18200,
"is_parallel": true,
"self": 188.54358398199835
},
"steps_from_proto": {
"total": 33.22150388800085,
"count": 18200,
"is_parallel": true,
"self": 6.86103363803511,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.360470249965744,
"count": 182000,
"is_parallel": true,
"self": 26.360470249965744
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.885300006662874e-05,
"count": 1,
"self": 4.885300006662874e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 435.1618563489461,
"count": 349040,
"is_parallel": true,
"self": 9.27412656594845,
"children": {
"process_trajectory": {
"total": 250.91830657099746,
"count": 349040,
"is_parallel": true,
"self": 250.24019837699734,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6781081940001172,
"count": 4,
"is_parallel": true,
"self": 0.6781081940001172
}
}
},
"_update_policy": {
"total": 174.9694232120002,
"count": 90,
"is_parallel": true,
"self": 42.71423174599755,
"children": {
"TorchPPOOptimizer.update": {
"total": 132.25519146600266,
"count": 4587,
"is_parallel": true,
"self": 132.25519146600266
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1289118290000033,
"count": 1,
"self": 0.000940656000011586,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12797117299999172,
"count": 1,
"self": 0.12797117299999172
}
}
}
}
}
}
}