KevStrider's picture
First Push
f2fe74d verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8646242022514343,
"min": 0.8646242022514343,
"max": 2.8621115684509277,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8245.9208984375,
"min": 8245.9208984375,
"max": 29373.8515625,
"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": 12.700410842895508,
"min": 0.4039401113986969,
"max": 12.700410842895508,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2476.580078125,
"min": 78.3643798828125,
"max": 2582.45361328125,
"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": 0.07179567353530586,
"min": 0.060099042048771964,
"max": 0.07387151652858615,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28718269414122344,
"min": 0.24039616819508786,
"max": 0.3684901765846721,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22497232543194995,
"min": 0.1525427774827489,
"max": 0.2683471726436241,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8998893017277998,
"min": 0.6101711099309955,
"max": 1.3417358632181207,
"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": 24.84090909090909,
"min": 3.840909090909091,
"max": 25.30909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1093.0,
"min": 169.0,
"max": 1392.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.84090909090909,
"min": 3.840909090909091,
"max": 25.30909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1093.0,
"min": 169.0,
"max": 1392.0,
"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": "1709055004",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1709055440"
},
"total": 436.1221060480001,
"count": 1,
"self": 0.4633836280000878,
"children": {
"run_training.setup": {
"total": 0.07225082100001146,
"count": 1,
"self": 0.07225082100001146
},
"TrainerController.start_learning": {
"total": 435.586471599,
"count": 1,
"self": 0.5601225890056867,
"children": {
"TrainerController._reset_env": {
"total": 3.482086435000042,
"count": 1,
"self": 3.482086435000042
},
"TrainerController.advance": {
"total": 431.4538028569941,
"count": 18200,
"self": 0.26766932700252255,
"children": {
"env_step": {
"total": 431.1861335299916,
"count": 18200,
"self": 280.7090791769774,
"children": {
"SubprocessEnvManager._take_step": {
"total": 150.0793094960095,
"count": 18200,
"self": 1.4595830680081008,
"children": {
"TorchPolicy.evaluate": {
"total": 148.6197264280014,
"count": 18200,
"self": 148.6197264280014
}
}
},
"workers": {
"total": 0.39774485700468176,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 434.5391918219981,
"count": 18200,
"is_parallel": true,
"self": 215.88166995298025,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006461408999939522,
"count": 1,
"is_parallel": true,
"self": 0.004172541999992063,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022888669999474587,
"count": 10,
"is_parallel": true,
"self": 0.0022888669999474587
}
}
},
"UnityEnvironment.step": {
"total": 0.03676276099997722,
"count": 1,
"is_parallel": true,
"self": 0.0006130210001629166,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042354199990768393,
"count": 1,
"is_parallel": true,
"self": 0.00042354199990768393
},
"communicator.exchange": {
"total": 0.03384211599995979,
"count": 1,
"is_parallel": true,
"self": 0.03384211599995979
},
"steps_from_proto": {
"total": 0.0018840819999468295,
"count": 1,
"is_parallel": true,
"self": 0.00037685600000259,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015072259999442394,
"count": 10,
"is_parallel": true,
"self": 0.0015072259999442394
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 218.65752186901784,
"count": 18199,
"is_parallel": true,
"self": 10.38340376300414,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.235386124006595,
"count": 18199,
"is_parallel": true,
"self": 5.235386124006595
},
"communicator.exchange": {
"total": 170.03811714899302,
"count": 18199,
"is_parallel": true,
"self": 170.03811714899302
},
"steps_from_proto": {
"total": 33.00061483301408,
"count": 18199,
"is_parallel": true,
"self": 6.148992250022161,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.851622582991922,
"count": 181990,
"is_parallel": true,
"self": 26.851622582991922
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.8495000126204104e-05,
"count": 1,
"self": 3.8495000126204104e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 426.10370658692887,
"count": 653220,
"is_parallel": true,
"self": 13.540061685933551,
"children": {
"process_trajectory": {
"total": 235.5002490329964,
"count": 653220,
"is_parallel": true,
"self": 234.9730157719962,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5272332610002195,
"count": 4,
"is_parallel": true,
"self": 0.5272332610002195
}
}
},
"_update_policy": {
"total": 177.0633958679989,
"count": 90,
"is_parallel": true,
"self": 50.50436497899511,
"children": {
"TorchPPOOptimizer.update": {
"total": 126.5590308890038,
"count": 4587,
"is_parallel": true,
"self": 126.5590308890038
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.0904212230000212,
"count": 1,
"self": 0.000979871000026833,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08944135199999437,
"count": 1,
"self": 0.08944135199999437
}
}
}
}
}
}
}