EchineF's picture
First Push
28664a3 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9076352715492249,
"min": 0.9076352715492249,
"max": 2.869284152984619,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8666.1015625,
"min": 8666.1015625,
"max": 29384.33984375,
"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": 12.676724433898926,
"min": 0.1994783729314804,
"max": 12.676724433898926,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2471.961181640625,
"min": 38.69880294799805,
"max": 2529.2509765625,
"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": 0.06886222051038846,
"min": 0.06172427906872768,
"max": 0.07435356206197849,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2754488820415538,
"min": 0.24689711627491073,
"max": 0.3717678103098925,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21278111695074567,
"min": 0.10853065509125406,
"max": 0.27326480348904925,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8511244678029827,
"min": 0.43412262036501625,
"max": 1.3663240174452462,
"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": 25.272727272727273,
"min": 3.1818181818181817,
"max": 25.272727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1112.0,
"min": 140.0,
"max": 1369.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.272727272727273,
"min": 3.1818181818181817,
"max": 25.272727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1112.0,
"min": 140.0,
"max": 1369.0,
"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": "1709559039",
"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": "1709559487"
},
"total": 448.21417763,
"count": 1,
"self": 0.5538125539999328,
"children": {
"run_training.setup": {
"total": 0.05233624200002396,
"count": 1,
"self": 0.05233624200002396
},
"TrainerController.start_learning": {
"total": 447.60802883400004,
"count": 1,
"self": 0.5497676530071658,
"children": {
"TrainerController._reset_env": {
"total": 3.8165094319999753,
"count": 1,
"self": 3.8165094319999753
},
"TrainerController.advance": {
"total": 443.1504590879928,
"count": 18198,
"self": 0.2610141709870959,
"children": {
"env_step": {
"total": 442.8894449170057,
"count": 18198,
"self": 285.91091931599294,
"children": {
"SubprocessEnvManager._take_step": {
"total": 156.69489927200243,
"count": 18198,
"self": 1.4569556800101964,
"children": {
"TorchPolicy.evaluate": {
"total": 155.23794359199223,
"count": 18198,
"self": 155.23794359199223
}
}
},
"workers": {
"total": 0.2836263290103034,
"count": 18198,
"self": 0.0,
"children": {
"worker_root": {
"total": 446.51676928499023,
"count": 18198,
"is_parallel": true,
"self": 222.92395564698847,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006768308999994588,
"count": 1,
"is_parallel": true,
"self": 0.004573357000253964,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002194951999740624,
"count": 10,
"is_parallel": true,
"self": 0.002194951999740624
}
}
},
"UnityEnvironment.step": {
"total": 0.040464265999958116,
"count": 1,
"is_parallel": true,
"self": 0.0006405169999652571,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004172520000338409,
"count": 1,
"is_parallel": true,
"self": 0.0004172520000338409
},
"communicator.exchange": {
"total": 0.0375599169999532,
"count": 1,
"is_parallel": true,
"self": 0.0375599169999532
},
"steps_from_proto": {
"total": 0.0018465800000058152,
"count": 1,
"is_parallel": true,
"self": 0.00036667300003045966,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014799069999753556,
"count": 10,
"is_parallel": true,
"self": 0.0014799069999753556
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 223.59281363800176,
"count": 18197,
"is_parallel": true,
"self": 10.792380361014125,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.328435432983497,
"count": 18197,
"is_parallel": true,
"self": 5.328435432983497
},
"communicator.exchange": {
"total": 173.560144063008,
"count": 18197,
"is_parallel": true,
"self": 173.560144063008
},
"steps_from_proto": {
"total": 33.911853780996125,
"count": 18197,
"is_parallel": true,
"self": 6.275303355949404,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.63655042504672,
"count": 181970,
"is_parallel": true,
"self": 27.63655042504672
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00019549800003915152,
"count": 1,
"self": 0.00019549800003915152,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 437.6035233280264,
"count": 677010,
"is_parallel": true,
"self": 14.224946312026646,
"children": {
"process_trajectory": {
"total": 240.5535183029998,
"count": 677010,
"is_parallel": true,
"self": 240.05682676899994,
"children": {
"RLTrainer._checkpoint": {
"total": 0.496691533999865,
"count": 4,
"is_parallel": true,
"self": 0.496691533999865
}
}
},
"_update_policy": {
"total": 182.82505871299998,
"count": 90,
"is_parallel": true,
"self": 52.69911914699048,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.1259395660095,
"count": 4587,
"is_parallel": true,
"self": 130.1259395660095
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09109716300008586,
"count": 1,
"self": 0.0009375960000852501,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0901595670000006,
"count": 1,
"self": 0.0901595670000006
}
}
}
}
}
}
}