BenLearningRL's picture
First Push
537f253
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8176538348197937,
"min": 0.8176538348197937,
"max": 2.8702261447906494,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7797.96484375,
"min": 7797.96484375,
"max": 29425.55859375,
"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": 12.873565673828125,
"min": 0.3821314871311188,
"max": 12.873565673828125,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2510.34521484375,
"min": 74.13350677490234,
"max": 2611.912109375,
"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.Losses.PolicyLoss.mean": {
"value": 0.0590908744060132,
"min": 0.0590908744060132,
"max": 0.07622120198656751,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2363634976240528,
"min": 0.2363634976240528,
"max": 0.3663526559682271,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18616837599113878,
"min": 0.1417535147926423,
"max": 0.28406715400370897,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7446735039645551,
"min": 0.5670140591705692,
"max": 1.3502159857318974,
"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": 25.613636363636363,
"min": 3.6363636363636362,
"max": 25.613636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1127.0,
"min": 160.0,
"max": 1377.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.613636363636363,
"min": 3.6363636363636362,
"max": 25.613636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1127.0,
"min": 160.0,
"max": 1377.0,
"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": "1701160680",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1701161157"
},
"total": 477.02484930599985,
"count": 1,
"self": 0.48873573299988493,
"children": {
"run_training.setup": {
"total": 0.06182615399995939,
"count": 1,
"self": 0.06182615399995939
},
"TrainerController.start_learning": {
"total": 476.474287419,
"count": 1,
"self": 0.5837759609827344,
"children": {
"TrainerController._reset_env": {
"total": 3.4847331309999845,
"count": 1,
"self": 3.4847331309999845
},
"TrainerController.advance": {
"total": 472.31393926001715,
"count": 18197,
"self": 0.2801120340127454,
"children": {
"env_step": {
"total": 472.0338272260044,
"count": 18197,
"self": 321.63977194200766,
"children": {
"SubprocessEnvManager._take_step": {
"total": 150.09941698599982,
"count": 18197,
"self": 1.4692059299862876,
"children": {
"TorchPolicy.evaluate": {
"total": 148.63021105601354,
"count": 18197,
"self": 148.63021105601354
}
}
},
"workers": {
"total": 0.29463829799692576,
"count": 18197,
"self": 0.0,
"children": {
"worker_root": {
"total": 475.08542987199735,
"count": 18197,
"is_parallel": true,
"self": 230.87442101299825,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005503165000050103,
"count": 1,
"is_parallel": true,
"self": 0.004035973999975795,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014671910000743082,
"count": 10,
"is_parallel": true,
"self": 0.0014671910000743082
}
}
},
"UnityEnvironment.step": {
"total": 0.03433527400000003,
"count": 1,
"is_parallel": true,
"self": 0.0006610219998037792,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041786800011323066,
"count": 1,
"is_parallel": true,
"self": 0.00041786800011323066
},
"communicator.exchange": {
"total": 0.03138189600008445,
"count": 1,
"is_parallel": true,
"self": 0.03138189600008445
},
"steps_from_proto": {
"total": 0.0018744879999985642,
"count": 1,
"is_parallel": true,
"self": 0.0003633989998661491,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001511089000132415,
"count": 10,
"is_parallel": true,
"self": 0.001511089000132415
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 244.2110088589991,
"count": 18196,
"is_parallel": true,
"self": 10.88747075700519,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.415162259005115,
"count": 18196,
"is_parallel": true,
"self": 5.415162259005115
},
"communicator.exchange": {
"total": 194.05290421899883,
"count": 18196,
"is_parallel": true,
"self": 194.05290421899883
},
"steps_from_proto": {
"total": 33.855471623989956,
"count": 18196,
"is_parallel": true,
"self": 6.426956117986379,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.428515506003578,
"count": 181960,
"is_parallel": true,
"self": 27.428515506003578
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001266300000679621,
"count": 1,
"self": 0.0001266300000679621,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 468.36068932897206,
"count": 497766,
"is_parallel": true,
"self": 10.505519653937768,
"children": {
"process_trajectory": {
"total": 264.0220395690352,
"count": 497766,
"is_parallel": true,
"self": 263.10803000903513,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9140095600000677,
"count": 4,
"is_parallel": true,
"self": 0.9140095600000677
}
}
},
"_update_policy": {
"total": 193.8331301059991,
"count": 90,
"is_parallel": true,
"self": 61.265332455993644,
"children": {
"TorchPPOOptimizer.update": {
"total": 132.56779765000545,
"count": 4584,
"is_parallel": true,
"self": 132.56779765000545
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09171243700006926,
"count": 1,
"self": 0.0009324870000000374,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09077995000006922,
"count": 1,
"self": 0.09077995000006922
}
}
}
}
}
}
}