sohm's picture
first push
26ac9ef
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8182554841041565,
"min": 0.8182554841041565,
"max": 2.8691320419311523,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7812.703125,
"min": 7812.703125,
"max": 29382.78125,
"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": 13.009750366210938,
"min": 0.2090936303138733,
"max": 13.009750366210938,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2536.9013671875,
"min": 40.56416320800781,
"max": 2635.810791015625,
"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": 0.06819942807808677,
"min": 0.059702132465591765,
"max": 0.07269231770952304,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27279771231234706,
"min": 0.23880852986236706,
"max": 0.3519053282140222,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1893199402473721,
"min": 0.10141685861162841,
"max": 0.26911959015563425,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7572797609894883,
"min": 0.40566743444651365,
"max": 1.3116201889398862,
"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": 25.295454545454547,
"min": 2.7045454545454546,
"max": 25.70909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1113.0,
"min": 119.0,
"max": 1414.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.295454545454547,
"min": 2.7045454545454546,
"max": 25.70909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1113.0,
"min": 119.0,
"max": 1414.0,
"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": "1675121212",
"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": "1675121666"
},
"total": 454.83551468999997,
"count": 1,
"self": 0.4381132109998589,
"children": {
"run_training.setup": {
"total": 0.10650711400001,
"count": 1,
"self": 0.10650711400001
},
"TrainerController.start_learning": {
"total": 454.2908943650001,
"count": 1,
"self": 0.5637389920068472,
"children": {
"TrainerController._reset_env": {
"total": 9.489439655999945,
"count": 1,
"self": 9.489439655999945
},
"TrainerController.advance": {
"total": 444.10179872099343,
"count": 18201,
"self": 0.2939374629766007,
"children": {
"env_step": {
"total": 443.8078612580168,
"count": 18201,
"self": 289.75380684702964,
"children": {
"SubprocessEnvManager._take_step": {
"total": 153.77094859900785,
"count": 18201,
"self": 1.4949097790164387,
"children": {
"TorchPolicy.evaluate": {
"total": 152.2760388199914,
"count": 18201,
"self": 35.36231097200516,
"children": {
"TorchPolicy.sample_actions": {
"total": 116.91372784798625,
"count": 18201,
"self": 116.91372784798625
}
}
}
}
},
"workers": {
"total": 0.2831058119793397,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 452.92924306601924,
"count": 18201,
"is_parallel": true,
"self": 218.5659858840246,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007118940999930601,
"count": 1,
"is_parallel": true,
"self": 0.0032794820002663982,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0038394589996642026,
"count": 10,
"is_parallel": true,
"self": 0.0038394589996642026
}
}
},
"UnityEnvironment.step": {
"total": 0.039873085999943214,
"count": 1,
"is_parallel": true,
"self": 0.0007158159999107738,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000315666999995301,
"count": 1,
"is_parallel": true,
"self": 0.000315666999995301
},
"communicator.exchange": {
"total": 0.03647638799998276,
"count": 1,
"is_parallel": true,
"self": 0.03647638799998276
},
"steps_from_proto": {
"total": 0.002365215000054377,
"count": 1,
"is_parallel": true,
"self": 0.0004989450000039142,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018662700000504628,
"count": 10,
"is_parallel": true,
"self": 0.0018662700000504628
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 234.36325718199464,
"count": 18200,
"is_parallel": true,
"self": 8.699573988987936,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.289850913004557,
"count": 18200,
"is_parallel": true,
"self": 5.289850913004557
},
"communicator.exchange": {
"total": 187.93615718099932,
"count": 18200,
"is_parallel": true,
"self": 187.93615718099932
},
"steps_from_proto": {
"total": 32.43767509900283,
"count": 18200,
"is_parallel": true,
"self": 7.0327513719649914,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.40492372703784,
"count": 182000,
"is_parallel": true,
"self": 25.40492372703784
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.1607999921543524e-05,
"count": 1,
"self": 5.1607999921543524e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 440.8300603759552,
"count": 365987,
"is_parallel": true,
"self": 10.038167203969692,
"children": {
"process_trajectory": {
"total": 253.06669085198484,
"count": 365987,
"is_parallel": true,
"self": 252.35430625598497,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7123845959998789,
"count": 4,
"is_parallel": true,
"self": 0.7123845959998789
}
}
},
"_update_policy": {
"total": 177.72520232000068,
"count": 90,
"is_parallel": true,
"self": 44.466694781005685,
"children": {
"TorchPPOOptimizer.update": {
"total": 133.258507538995,
"count": 4587,
"is_parallel": true,
"self": 133.258507538995
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1358653879999565,
"count": 1,
"self": 0.0009390489999532292,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13492633900000328,
"count": 1,
"self": 0.13492633900000328
}
}
}
}
}
}
}