maximrud's picture
First Push
c10bb24 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9748097658157349,
"min": 0.9748097658157349,
"max": 2.843841791152954,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9264.591796875,
"min": 9264.591796875,
"max": 29029.9375,
"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": 13.088208198547363,
"min": 0.3928322494029999,
"max": 13.088208198547363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2552.20068359375,
"min": 76.20945739746094,
"max": 2661.939697265625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06731382647107613,
"min": 0.06359437142599228,
"max": 0.07173301855215744,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2692553058843045,
"min": 0.25464808427746977,
"max": 0.3540555308538708,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19781124175471418,
"min": 0.129258230821613,
"max": 0.2906154131188112,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7912449670188567,
"min": 0.517032923286452,
"max": 1.3698292386298085,
"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": 25.568181818181817,
"min": 3.659090909090909,
"max": 25.886363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1125.0,
"min": 161.0,
"max": 1399.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.568181818181817,
"min": 3.659090909090909,
"max": 25.886363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1125.0,
"min": 161.0,
"max": 1399.0,
"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": "1752661088",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1752661498"
},
"total": 410.07142823600043,
"count": 1,
"self": 0.4892525970008137,
"children": {
"run_training.setup": {
"total": 0.023197507000077167,
"count": 1,
"self": 0.023197507000077167
},
"TrainerController.start_learning": {
"total": 409.55897813199954,
"count": 1,
"self": 0.33359266396746534,
"children": {
"TrainerController._reset_env": {
"total": 4.282125151999935,
"count": 1,
"self": 4.282125151999935
},
"TrainerController.advance": {
"total": 404.86489908003205,
"count": 18192,
"self": 0.35772542104950844,
"children": {
"env_step": {
"total": 288.82285689398486,
"count": 18192,
"self": 222.22622437597784,
"children": {
"SubprocessEnvManager._take_step": {
"total": 66.39808477599945,
"count": 18192,
"self": 1.1972739590655692,
"children": {
"TorchPolicy.evaluate": {
"total": 65.20081081693388,
"count": 18192,
"self": 65.20081081693388
}
}
},
"workers": {
"total": 0.19854774200757674,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 408.2242408940738,
"count": 18192,
"is_parallel": true,
"self": 213.05182108207282,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005957960999694478,
"count": 1,
"is_parallel": true,
"self": 0.0044080049974581925,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015499560022362857,
"count": 10,
"is_parallel": true,
"self": 0.0015499560022362857
}
}
},
"UnityEnvironment.step": {
"total": 0.058016597000460024,
"count": 1,
"is_parallel": true,
"self": 0.0005958790006843628,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004112469996471191,
"count": 1,
"is_parallel": true,
"self": 0.0004112469996471191
},
"communicator.exchange": {
"total": 0.05515182300041488,
"count": 1,
"is_parallel": true,
"self": 0.05515182300041488
},
"steps_from_proto": {
"total": 0.001857647999713663,
"count": 1,
"is_parallel": true,
"self": 0.00036538899803417735,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014922590016794857,
"count": 10,
"is_parallel": true,
"self": 0.0014922590016794857
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 195.17241981200095,
"count": 18191,
"is_parallel": true,
"self": 9.637847679974584,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.074224676967788,
"count": 18191,
"is_parallel": true,
"self": 5.074224676967788
},
"communicator.exchange": {
"total": 150.28072428002724,
"count": 18191,
"is_parallel": true,
"self": 150.28072428002724
},
"steps_from_proto": {
"total": 30.179623175031338,
"count": 18191,
"is_parallel": true,
"self": 5.339262093049001,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.840361081982337,
"count": 181910,
"is_parallel": true,
"self": 24.840361081982337
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 115.68431676499767,
"count": 18192,
"self": 0.42797582491130015,
"children": {
"process_trajectory": {
"total": 25.183478331087827,
"count": 18192,
"self": 24.70958791808971,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4738904129981165,
"count": 4,
"self": 0.4738904129981165
}
}
},
"_update_policy": {
"total": 90.07286260899855,
"count": 90,
"self": 37.11901204398873,
"children": {
"TorchPPOOptimizer.update": {
"total": 52.953850565009816,
"count": 4587,
"self": 52.953850565009816
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.680000635446049e-07,
"count": 1,
"self": 7.680000635446049e-07
},
"TrainerController._save_models": {
"total": 0.07836046800002805,
"count": 1,
"self": 0.000831622000077914,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07752884599995014,
"count": 1,
"self": 0.07752884599995014
}
}
}
}
}
}
}