PedroPlusPlus's picture
First Push
19ee0c8 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8220521211624146,
"min": 0.7970927953720093,
"max": 2.853597402572632,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7812.783203125,
"min": 7812.783203125,
"max": 29129.5234375,
"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": 12.917903900146484,
"min": 0.49479585886001587,
"max": 12.917903900146484,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2518.9912109375,
"min": 95.99039459228516,
"max": 2610.12109375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07031974680830899,
"min": 0.06341941983166678,
"max": 0.07413633079176733,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28127898723323597,
"min": 0.2536776793266671,
"max": 0.3600516619313994,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21480223485359962,
"min": 0.12795756329033597,
"max": 0.2900525208781747,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8592089394143985,
"min": 0.5118302531613439,
"max": 1.4502626043908735,
"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.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.Environment.CumulativeReward.mean": {
"value": 24.931818181818183,
"min": 3.8863636363636362,
"max": 25.927272727272726,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1097.0,
"min": 171.0,
"max": 1426.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.931818181818183,
"min": 3.8863636363636362,
"max": 25.927272727272726,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1097.0,
"min": 171.0,
"max": 1426.0,
"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": "1740641594",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1740642000"
},
"total": 406.264866362,
"count": 1,
"self": 0.43649259899996196,
"children": {
"run_training.setup": {
"total": 0.022684010000034505,
"count": 1,
"self": 0.022684010000034505
},
"TrainerController.start_learning": {
"total": 405.805689753,
"count": 1,
"self": 0.3005104360087216,
"children": {
"TrainerController._reset_env": {
"total": 3.6199045179999985,
"count": 1,
"self": 3.6199045179999985
},
"TrainerController.advance": {
"total": 401.79896090999137,
"count": 18192,
"self": 0.32465292798906376,
"children": {
"env_step": {
"total": 282.85908822799706,
"count": 18192,
"self": 214.90703695100694,
"children": {
"SubprocessEnvManager._take_step": {
"total": 67.76526089399363,
"count": 18192,
"self": 1.1716395260028776,
"children": {
"TorchPolicy.evaluate": {
"total": 66.59362136799075,
"count": 18192,
"self": 66.59362136799075
}
}
},
"workers": {
"total": 0.18679038299649164,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 404.3134724620011,
"count": 18192,
"is_parallel": true,
"self": 215.64104805100294,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006132966999985001,
"count": 1,
"is_parallel": true,
"self": 0.004106825000121717,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020261419998632846,
"count": 10,
"is_parallel": true,
"self": 0.0020261419998632846
}
}
},
"UnityEnvironment.step": {
"total": 0.04009798100003081,
"count": 1,
"is_parallel": true,
"self": 0.0006494780000139144,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00045851800007312704,
"count": 1,
"is_parallel": true,
"self": 0.00045851800007312704
},
"communicator.exchange": {
"total": 0.0369971349999787,
"count": 1,
"is_parallel": true,
"self": 0.0369971349999787
},
"steps_from_proto": {
"total": 0.001992849999965074,
"count": 1,
"is_parallel": true,
"self": 0.00038543099992693897,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001607419000038135,
"count": 10,
"is_parallel": true,
"self": 0.001607419000038135
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 188.67242441099813,
"count": 18191,
"is_parallel": true,
"self": 9.459250800999826,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.386174459996823,
"count": 18191,
"is_parallel": true,
"self": 5.386174459996823
},
"communicator.exchange": {
"total": 143.7997897229908,
"count": 18191,
"is_parallel": true,
"self": 143.7997897229908
},
"steps_from_proto": {
"total": 30.02720942701069,
"count": 18191,
"is_parallel": true,
"self": 5.179808093038673,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.847401333972016,
"count": 181910,
"is_parallel": true,
"self": 24.847401333972016
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 118.61521975400524,
"count": 18192,
"self": 0.35875096001871043,
"children": {
"process_trajectory": {
"total": 25.405987282986985,
"count": 18192,
"self": 24.884214840986942,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5217724420000422,
"count": 4,
"self": 0.5217724420000422
}
}
},
"_update_policy": {
"total": 92.85048151099954,
"count": 90,
"self": 36.83303418599564,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.0174473250039,
"count": 4587,
"self": 56.0174473250039
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.099999260797631e-07,
"count": 1,
"self": 9.099999260797631e-07
},
"TrainerController._save_models": {
"total": 0.086312979000013,
"count": 1,
"self": 0.0008553769998798089,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08545760200013319,
"count": 1,
"self": 0.08545760200013319
}
}
}
}
}
}
}