RafaelJaime's picture
First Push
8e59e02 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8544067144393921,
"min": 0.8544067144393921,
"max": 2.8341782093048096,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8120.28125,
"min": 8120.28125,
"max": 28931.291015625,
"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": 12.660491943359375,
"min": 0.4726080298423767,
"max": 12.68015193939209,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2468.7958984375,
"min": 91.68595886230469,
"max": 2586.7509765625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07038566119017024,
"min": 0.062251518307854053,
"max": 0.07520494147052068,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28154264476068097,
"min": 0.24900607323141621,
"max": 0.37602470735260335,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20030086651882703,
"min": 0.13055955768818509,
"max": 0.31034838416997124,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8012034660753081,
"min": 0.5222382307527403,
"max": 1.5517419208498562,
"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": 24.772727272727273,
"min": 3.772727272727273,
"max": 25.072727272727274,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1090.0,
"min": 166.0,
"max": 1379.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.772727272727273,
"min": 3.772727272727273,
"max": 25.072727272727274,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1090.0,
"min": 166.0,
"max": 1379.0,
"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": "1736627795",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1736628218"
},
"total": 422.194596017,
"count": 1,
"self": 0.4253949609999381,
"children": {
"run_training.setup": {
"total": 0.056814912000049844,
"count": 1,
"self": 0.056814912000049844
},
"TrainerController.start_learning": {
"total": 421.712386144,
"count": 1,
"self": 0.33947168799466,
"children": {
"TrainerController._reset_env": {
"total": 2.5774261690000912,
"count": 1,
"self": 2.5774261690000912
},
"TrainerController.advance": {
"total": 418.69728897200514,
"count": 18192,
"self": 0.35489100700988274,
"children": {
"env_step": {
"total": 296.8145674930032,
"count": 18192,
"self": 226.2268381430157,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.37528411399023,
"count": 18192,
"self": 1.2323715439968055,
"children": {
"TorchPolicy.evaluate": {
"total": 69.14291256999343,
"count": 18192,
"self": 69.14291256999343
}
}
},
"workers": {
"total": 0.21244523599727927,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 420.2987904030015,
"count": 18192,
"is_parallel": true,
"self": 222.556795344002,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002176669000050424,
"count": 1,
"is_parallel": true,
"self": 0.0006563370000094437,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015203320000409803,
"count": 10,
"is_parallel": true,
"self": 0.0015203320000409803
}
}
},
"UnityEnvironment.step": {
"total": 0.07743890799997644,
"count": 1,
"is_parallel": true,
"self": 0.0006620329999122987,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000396614999999656,
"count": 1,
"is_parallel": true,
"self": 0.000396614999999656
},
"communicator.exchange": {
"total": 0.07447806900006526,
"count": 1,
"is_parallel": true,
"self": 0.07447806900006526
},
"steps_from_proto": {
"total": 0.0019021909999992204,
"count": 1,
"is_parallel": true,
"self": 0.0003695789999937915,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015326120000054289,
"count": 10,
"is_parallel": true,
"self": 0.0015326120000054289
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 197.74199505899946,
"count": 18191,
"is_parallel": true,
"self": 9.776409268005864,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.368848217998334,
"count": 18191,
"is_parallel": true,
"self": 5.368848217998334
},
"communicator.exchange": {
"total": 151.56575696399887,
"count": 18191,
"is_parallel": true,
"self": 151.56575696399887
},
"steps_from_proto": {
"total": 31.0309806089964,
"count": 18191,
"is_parallel": true,
"self": 5.416412699986154,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.614567909010248,
"count": 181910,
"is_parallel": true,
"self": 25.614567909010248
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 121.52783047199205,
"count": 18192,
"self": 0.4205196979929724,
"children": {
"process_trajectory": {
"total": 28.90031265099924,
"count": 18192,
"self": 28.46521574599933,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4350969049999094,
"count": 4,
"self": 0.4350969049999094
}
}
},
"_update_policy": {
"total": 92.20699812299983,
"count": 90,
"self": 37.312410054998054,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.89458806800178,
"count": 4587,
"self": 54.89458806800178
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1300001006020466e-06,
"count": 1,
"self": 1.1300001006020466e-06
},
"TrainerController._save_models": {
"total": 0.0981981850000011,
"count": 1,
"self": 0.0009381969999822104,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0972599880000189,
"count": 1,
"self": 0.0972599880000189
}
}
}
}
}
}
}