blade57's picture
First Push
bb0e12b verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7622503042221069,
"min": 0.7529322504997253,
"max": 2.8351101875305176,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7244.4267578125,
"min": 7244.4267578125,
"max": 28940.8046875,
"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": 13.004538536071777,
"min": 0.33604422211647034,
"max": 13.004538536071777,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2535.885009765625,
"min": 65.19258117675781,
"max": 2638.78369140625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07030608561691741,
"min": 0.06167956081980283,
"max": 0.07950192082196236,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28122434246766964,
"min": 0.24671824327921132,
"max": 0.36022966347880747,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19650773320566206,
"min": 0.12650720130962628,
"max": 0.278907922699171,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7860309328226482,
"min": 0.5060288052385051,
"max": 1.297334189800655,
"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": 25.863636363636363,
"min": 3.340909090909091,
"max": 25.863636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1138.0,
"min": 147.0,
"max": 1416.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.863636363636363,
"min": 3.340909090909091,
"max": 25.863636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1138.0,
"min": 147.0,
"max": 1416.0,
"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": "1740151825",
"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": "1740152250"
},
"total": 425.3969879499998,
"count": 1,
"self": 0.389208157999974,
"children": {
"run_training.setup": {
"total": 0.022900277999951868,
"count": 1,
"self": 0.022900277999951868
},
"TrainerController.start_learning": {
"total": 424.9848795139999,
"count": 1,
"self": 0.33607330603308583,
"children": {
"TrainerController._reset_env": {
"total": 2.885446004999949,
"count": 1,
"self": 2.885446004999949
},
"TrainerController.advance": {
"total": 421.6767558389665,
"count": 18192,
"self": 0.3444409799508321,
"children": {
"env_step": {
"total": 299.0843346900085,
"count": 18192,
"self": 227.00790253400191,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.87946655100836,
"count": 18192,
"self": 1.256303902005584,
"children": {
"TorchPolicy.evaluate": {
"total": 70.62316264900278,
"count": 18192,
"self": 70.62316264900278
}
}
},
"workers": {
"total": 0.19696560499824045,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 423.4511161290093,
"count": 18192,
"is_parallel": true,
"self": 224.47475982000674,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0054741930000545835,
"count": 1,
"is_parallel": true,
"self": 0.0038200000005872425,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001654192999467341,
"count": 10,
"is_parallel": true,
"self": 0.001654192999467341
}
}
},
"UnityEnvironment.step": {
"total": 0.034747275000199807,
"count": 1,
"is_parallel": true,
"self": 0.000593227000308616,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004350110000359564,
"count": 1,
"is_parallel": true,
"self": 0.0004350110000359564
},
"communicator.exchange": {
"total": 0.031828524000047764,
"count": 1,
"is_parallel": true,
"self": 0.031828524000047764
},
"steps_from_proto": {
"total": 0.00189051299980747,
"count": 1,
"is_parallel": true,
"self": 0.0004194089999600692,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014711039998474007,
"count": 10,
"is_parallel": true,
"self": 0.0014711039998474007
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 198.97635630900254,
"count": 18191,
"is_parallel": true,
"self": 9.702646117026461,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.387372035993849,
"count": 18191,
"is_parallel": true,
"self": 5.387372035993849
},
"communicator.exchange": {
"total": 152.23869936796814,
"count": 18191,
"is_parallel": true,
"self": 152.23869936796814
},
"steps_from_proto": {
"total": 31.647638788014092,
"count": 18191,
"is_parallel": true,
"self": 5.67382084403971,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.97381794397438,
"count": 181910,
"is_parallel": true,
"self": 25.97381794397438
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 122.24798016900718,
"count": 18192,
"self": 0.415574711986892,
"children": {
"process_trajectory": {
"total": 27.002288433019885,
"count": 18192,
"self": 26.407376980019535,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5949114530003499,
"count": 4,
"self": 0.5949114530003499
}
}
},
"_update_policy": {
"total": 94.8301170240004,
"count": 90,
"self": 37.80808929900559,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.022027724994814,
"count": 4587,
"self": 57.022027724994814
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0650001058820635e-06,
"count": 1,
"self": 1.0650001058820635e-06
},
"TrainerController._save_models": {
"total": 0.0866032990002168,
"count": 1,
"self": 0.0009311240000897669,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08567217500012703,
"count": 1,
"self": 0.08567217500012703
}
}
}
}
}
}
}