grinvolod's picture
First Push
554e6fd verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7340123653411865,
"min": 0.7340123653411865,
"max": 2.8529164791107178,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6976.0537109375,
"min": 6976.0537109375,
"max": 29122.5703125,
"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": 8.787528991699219,
"min": 0.3383921682834625,
"max": 8.787528991699219,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1713.568115234375,
"min": 65.64807891845703,
"max": 1772.771728515625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07630767296402208,
"min": 0.06246729202811206,
"max": 0.07630767296402208,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3052306918560883,
"min": 0.24986916811244825,
"max": 0.3666489105586045,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17865009653363742,
"min": 0.12211144023675326,
"max": 0.27154687011943146,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7146003861345497,
"min": 0.48844576094701303,
"max": 1.3577343505971573,
"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": 25.931818181818183,
"min": 3.4318181818181817,
"max": 25.931818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1141.0,
"min": 151.0,
"max": 1413.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.931818181818183,
"min": 3.4318181818181817,
"max": 25.931818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1141.0,
"min": 151.0,
"max": 1413.0,
"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": "1769787288",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1769787729"
},
"total": 440.69831419699995,
"count": 1,
"self": 0.43362222400014616,
"children": {
"run_training.setup": {
"total": 0.026732684999842604,
"count": 1,
"self": 0.026732684999842604
},
"TrainerController.start_learning": {
"total": 440.23795928799996,
"count": 1,
"self": 0.34175963701727596,
"children": {
"TrainerController._reset_env": {
"total": 2.6405982050000603,
"count": 1,
"self": 2.6405982050000603
},
"TrainerController.advance": {
"total": 437.18002924198277,
"count": 18192,
"self": 0.37325293597177733,
"children": {
"env_step": {
"total": 318.561789312007,
"count": 18192,
"self": 248.96375439597568,
"children": {
"SubprocessEnvManager._take_step": {
"total": 69.38791946401193,
"count": 18192,
"self": 1.2519188930034488,
"children": {
"TorchPolicy.evaluate": {
"total": 68.13600057100848,
"count": 18192,
"self": 68.13600057100848
}
}
},
"workers": {
"total": 0.21011545201940862,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 438.4133599120112,
"count": 18192,
"is_parallel": true,
"self": 219.566137761994,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005053970000062691,
"count": 1,
"is_parallel": true,
"self": 0.0035981900000479072,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014557800000147836,
"count": 10,
"is_parallel": true,
"self": 0.0014557800000147836
}
}
},
"UnityEnvironment.step": {
"total": 0.037561684000138484,
"count": 1,
"is_parallel": true,
"self": 0.0006492030001936655,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044879699999000877,
"count": 1,
"is_parallel": true,
"self": 0.00044879699999000877
},
"communicator.exchange": {
"total": 0.034518073000072036,
"count": 1,
"is_parallel": true,
"self": 0.034518073000072036
},
"steps_from_proto": {
"total": 0.0019456109998827742,
"count": 1,
"is_parallel": true,
"self": 0.00038797699971837574,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015576340001643985,
"count": 10,
"is_parallel": true,
"self": 0.0015576340001643985
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 218.84722215001716,
"count": 18191,
"is_parallel": true,
"self": 10.526576822026755,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.559773483005529,
"count": 18191,
"is_parallel": true,
"self": 5.559773483005529
},
"communicator.exchange": {
"total": 166.27839728899403,
"count": 18191,
"is_parallel": true,
"self": 166.27839728899403
},
"steps_from_proto": {
"total": 36.48247455599085,
"count": 18191,
"is_parallel": true,
"self": 6.418917633973706,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.063556922017142,
"count": 181910,
"is_parallel": true,
"self": 30.063556922017142
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 118.24498699400397,
"count": 18192,
"self": 0.4372526039949207,
"children": {
"process_trajectory": {
"total": 26.17868360400712,
"count": 18192,
"self": 25.699875124006894,
"children": {
"RLTrainer._checkpoint": {
"total": 0.47880848000022525,
"count": 4,
"self": 0.47880848000022525
}
}
},
"_update_policy": {
"total": 91.62905078600193,
"count": 90,
"self": 37.63552699401134,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.99352379199058,
"count": 4587,
"self": 53.99352379199058
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2149998838140164e-06,
"count": 1,
"self": 1.2149998838140164e-06
},
"TrainerController._save_models": {
"total": 0.07557098899997072,
"count": 1,
"self": 0.0007482260000415408,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07482276299992918,
"count": 1,
"self": 0.07482276299992918
}
}
}
}
}
}
}