arnemaass's picture
First Push
7f2b3b5 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8229658603668213,
"min": 0.8125287294387817,
"max": 2.8289248943328857,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7821.4677734375,
"min": 7821.4677734375,
"max": 28877.666015625,
"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": 12.963811874389648,
"min": 0.3247487246990204,
"max": 12.963811874389648,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2527.943359375,
"min": 63.00125503540039,
"max": 2632.775390625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06365488337356581,
"min": 0.06329694055271902,
"max": 0.07915761614038934,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25461953349426325,
"min": 0.25461953349426325,
"max": 0.3650939324688094,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1856027474152107,
"min": 0.14588767103166045,
"max": 0.2779079112498199,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7424109896608428,
"min": 0.5835506841266418,
"max": 1.2989120103564917,
"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": 25.34090909090909,
"min": 3.8181818181818183,
"max": 25.34090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1115.0,
"min": 168.0,
"max": 1391.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.34090909090909,
"min": 3.8181818181818183,
"max": 25.34090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1115.0,
"min": 168.0,
"max": 1391.0,
"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": "1745101050",
"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": "1745101482"
},
"total": 432.335896409,
"count": 1,
"self": 0.438114477000056,
"children": {
"run_training.setup": {
"total": 0.022307733999980428,
"count": 1,
"self": 0.022307733999980428
},
"TrainerController.start_learning": {
"total": 431.87547419799995,
"count": 1,
"self": 0.355415476006101,
"children": {
"TrainerController._reset_env": {
"total": 2.8311775680000437,
"count": 1,
"self": 2.8311775680000437
},
"TrainerController.advance": {
"total": 428.59921694599376,
"count": 18192,
"self": 0.3723214469899858,
"children": {
"env_step": {
"total": 304.3714575910046,
"count": 18192,
"self": 230.64128419000997,
"children": {
"SubprocessEnvManager._take_step": {
"total": 73.5198211649984,
"count": 18192,
"self": 1.2802635460083707,
"children": {
"TorchPolicy.evaluate": {
"total": 72.23955761899003,
"count": 18192,
"self": 72.23955761899003
}
}
},
"workers": {
"total": 0.21035223599625397,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 430.49140643200013,
"count": 18192,
"is_parallel": true,
"self": 228.04172949400817,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005763929000011103,
"count": 1,
"is_parallel": true,
"self": 0.004215578999946956,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001548350000064147,
"count": 10,
"is_parallel": true,
"self": 0.001548350000064147
}
}
},
"UnityEnvironment.step": {
"total": 0.03859940400002415,
"count": 1,
"is_parallel": true,
"self": 0.0006400679999956083,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004238370000280156,
"count": 1,
"is_parallel": true,
"self": 0.0004238370000280156
},
"communicator.exchange": {
"total": 0.03560914799999182,
"count": 1,
"is_parallel": true,
"self": 0.03560914799999182
},
"steps_from_proto": {
"total": 0.001926351000008708,
"count": 1,
"is_parallel": true,
"self": 0.0003950920001329905,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015312589998757176,
"count": 10,
"is_parallel": true,
"self": 0.0015312589998757176
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 202.44967693799197,
"count": 18191,
"is_parallel": true,
"self": 9.85653015699154,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.3945923850016015,
"count": 18191,
"is_parallel": true,
"self": 5.3945923850016015
},
"communicator.exchange": {
"total": 154.88451671800374,
"count": 18191,
"is_parallel": true,
"self": 154.88451671800374
},
"steps_from_proto": {
"total": 32.31403767799509,
"count": 18191,
"is_parallel": true,
"self": 5.840282932993489,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.4737547450016,
"count": 181910,
"is_parallel": true,
"self": 26.4737547450016
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 123.85543790799915,
"count": 18192,
"self": 0.42227999899677116,
"children": {
"process_trajectory": {
"total": 27.676465102002055,
"count": 18192,
"self": 27.250725981002006,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4257391210000492,
"count": 4,
"self": 0.4257391210000492
}
}
},
"_update_policy": {
"total": 95.75669280700032,
"count": 90,
"self": 38.158937061005986,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.597755745994334,
"count": 4587,
"self": 57.597755745994334
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.060000820682035e-07,
"count": 1,
"self": 9.060000820682035e-07
},
"TrainerController._save_models": {
"total": 0.08966330199996264,
"count": 1,
"self": 0.0009301759998834314,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08873312600007921,
"count": 1,
"self": 0.08873312600007921
}
}
}
}
}
}
}