Bandika's picture
First training of SnowballTarget
907f246
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.006365180015564,
"min": 1.006365180015564,
"max": 2.872704267501831,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9653.0546875,
"min": 9653.0546875,
"max": 29419.36328125,
"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": 13.13095474243164,
"min": 0.526780903339386,
"max": 13.13095474243164,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2560.5361328125,
"min": 102.19549560546875,
"max": 2669.718994140625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06708954017484953,
"min": 0.06392838219839106,
"max": 0.07533981426269178,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2683581606993981,
"min": 0.25571352879356424,
"max": 0.35766298130471896,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1780547786723165,
"min": 0.11398467398020348,
"max": 0.2921774748931913,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.712219114689266,
"min": 0.45593869592081393,
"max": 1.4234850541049358,
"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": 26.09090909090909,
"min": 3.25,
"max": 26.09090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1148.0,
"min": 143.0,
"max": 1419.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.09090909090909,
"min": 3.25,
"max": 26.09090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1148.0,
"min": 143.0,
"max": 1419.0,
"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": "1681573500",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1681573980"
},
"total": 479.63811416799996,
"count": 1,
"self": 0.7369745749999197,
"children": {
"run_training.setup": {
"total": 0.17519610900001226,
"count": 1,
"self": 0.17519610900001226
},
"TrainerController.start_learning": {
"total": 478.725943484,
"count": 1,
"self": 0.5929077050048477,
"children": {
"TrainerController._reset_env": {
"total": 4.3115992340000275,
"count": 1,
"self": 4.3115992340000275
},
"TrainerController.advance": {
"total": 473.59963900299516,
"count": 18220,
"self": 0.28015557999685825,
"children": {
"env_step": {
"total": 473.3194834229983,
"count": 18220,
"self": 347.3763102679921,
"children": {
"SubprocessEnvManager._take_step": {
"total": 125.65101800700029,
"count": 18220,
"self": 1.804678105999301,
"children": {
"TorchPolicy.evaluate": {
"total": 123.84633990100099,
"count": 18220,
"self": 123.84633990100099
}
}
},
"workers": {
"total": 0.2921551480059179,
"count": 18220,
"self": 0.0,
"children": {
"worker_root": {
"total": 477.10108883999663,
"count": 18220,
"is_parallel": true,
"self": 221.51572816499686,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006763516999967578,
"count": 1,
"is_parallel": true,
"self": 0.004452610000100776,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002310906999866802,
"count": 10,
"is_parallel": true,
"self": 0.002310906999866802
}
}
},
"UnityEnvironment.step": {
"total": 0.03756809600002953,
"count": 1,
"is_parallel": true,
"self": 0.0006711720000680543,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00036773399995126965,
"count": 1,
"is_parallel": true,
"self": 0.00036773399995126965
},
"communicator.exchange": {
"total": 0.03445953300001747,
"count": 1,
"is_parallel": true,
"self": 0.03445953300001747
},
"steps_from_proto": {
"total": 0.0020696569999927306,
"count": 1,
"is_parallel": true,
"self": 0.0004451839999433105,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00162447300004942,
"count": 10,
"is_parallel": true,
"self": 0.00162447300004942
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 255.58536067499978,
"count": 18219,
"is_parallel": true,
"self": 10.15535469700393,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.72915644399194,
"count": 18219,
"is_parallel": true,
"self": 5.72915644399194
},
"communicator.exchange": {
"total": 205.99931345500204,
"count": 18219,
"is_parallel": true,
"self": 205.99931345500204
},
"steps_from_proto": {
"total": 33.70153607900187,
"count": 18219,
"is_parallel": true,
"self": 6.700973714012832,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.000562364989037,
"count": 182190,
"is_parallel": true,
"self": 27.000562364989037
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001300189999255963,
"count": 1,
"self": 0.0001300189999255963,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 469.90766735795506,
"count": 430486,
"is_parallel": true,
"self": 10.730997629903015,
"children": {
"process_trajectory": {
"total": 261.7986015810519,
"count": 430486,
"is_parallel": true,
"self": 260.0925770960518,
"children": {
"RLTrainer._checkpoint": {
"total": 1.706024485000114,
"count": 4,
"is_parallel": true,
"self": 1.706024485000114
}
}
},
"_update_policy": {
"total": 197.37806814700014,
"count": 90,
"is_parallel": true,
"self": 76.85910764800406,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.51896049899608,
"count": 4587,
"is_parallel": true,
"self": 120.51896049899608
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.22166752300006465,
"count": 1,
"self": 0.0011182060000010097,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22054931700006364,
"count": 1,
"self": 0.22054931700006364
}
}
}
}
}
}
}