oscarb92's picture
First training of SnowballTarget
8af42dd
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7938248515129089,
"min": 0.781169593334198,
"max": 2.871081829071045,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7579.439453125,
"min": 7579.439453125,
"max": 29402.75,
"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": 12.836530685424805,
"min": 0.379591703414917,
"max": 12.846275329589844,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2503.12353515625,
"min": 73.64079284667969,
"max": 2620.64013671875,
"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": 0.07625383586074509,
"min": 0.062131151186465505,
"max": 0.07790825333983831,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.30501534344298037,
"min": 0.24852460474586202,
"max": 0.38954126669919154,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20364511107989386,
"min": 0.11605182550413826,
"max": 0.2660039826204964,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8145804443195754,
"min": 0.464207302016553,
"max": 1.2867693700371128,
"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": 25.363636363636363,
"min": 3.159090909090909,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1116.0,
"min": 139.0,
"max": 1394.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.363636363636363,
"min": 3.159090909090909,
"max": 25.363636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1116.0,
"min": 139.0,
"max": 1394.0,
"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": "1676018565",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1676019020"
},
"total": 455.64837789200004,
"count": 1,
"self": 0.5580110619999914,
"children": {
"run_training.setup": {
"total": 0.10521816300001774,
"count": 1,
"self": 0.10521816300001774
},
"TrainerController.start_learning": {
"total": 454.98514866700003,
"count": 1,
"self": 0.5182054310135982,
"children": {
"TrainerController._reset_env": {
"total": 10.484931988000028,
"count": 1,
"self": 10.484931988000028
},
"TrainerController.advance": {
"total": 443.8558167709865,
"count": 18201,
"self": 0.2913714479942655,
"children": {
"env_step": {
"total": 443.56444532299224,
"count": 18201,
"self": 306.4671137059879,
"children": {
"SubprocessEnvManager._take_step": {
"total": 136.83773546500151,
"count": 18201,
"self": 1.4415070969976114,
"children": {
"TorchPolicy.evaluate": {
"total": 135.3962283680039,
"count": 18201,
"self": 30.08753970800319,
"children": {
"TorchPolicy.sample_actions": {
"total": 105.30868866000071,
"count": 18201,
"self": 105.30868866000071
}
}
}
}
},
"workers": {
"total": 0.25959615200281405,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 453.44136130800035,
"count": 18201,
"is_parallel": true,
"self": 222.23892839900617,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005460691999985556,
"count": 1,
"is_parallel": true,
"self": 0.0031604349999838632,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002300257000001693,
"count": 10,
"is_parallel": true,
"self": 0.002300257000001693
}
}
},
"UnityEnvironment.step": {
"total": 0.08082084799991662,
"count": 1,
"is_parallel": true,
"self": 0.0005782739999631303,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004102289999536879,
"count": 1,
"is_parallel": true,
"self": 0.0004102289999536879
},
"communicator.exchange": {
"total": 0.07788345099993421,
"count": 1,
"is_parallel": true,
"self": 0.07788345099993421
},
"steps_from_proto": {
"total": 0.001948894000065593,
"count": 1,
"is_parallel": true,
"self": 0.0004325090001202625,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015163849999453305,
"count": 10,
"is_parallel": true,
"self": 0.0015163849999453305
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 231.20243290899418,
"count": 18200,
"is_parallel": true,
"self": 9.370066087003465,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.053570101000787,
"count": 18200,
"is_parallel": true,
"self": 5.053570101000787
},
"communicator.exchange": {
"total": 186.55139825699086,
"count": 18200,
"is_parallel": true,
"self": 186.55139825699086
},
"steps_from_proto": {
"total": 30.227398463999066,
"count": 18200,
"is_parallel": true,
"self": 6.408566447006024,
"children": {
"_process_rank_one_or_two_observation": {
"total": 23.818832016993042,
"count": 182000,
"is_parallel": true,
"self": 23.818832016993042
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011461199994755589,
"count": 1,
"self": 0.00011461199994755589,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 440.5019272390134,
"count": 410840,
"is_parallel": true,
"self": 10.139650926008699,
"children": {
"process_trajectory": {
"total": 251.71211741800448,
"count": 410840,
"is_parallel": true,
"self": 250.17083403400454,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5412833839999394,
"count": 4,
"is_parallel": true,
"self": 1.5412833839999394
}
}
},
"_update_policy": {
"total": 178.65015889500023,
"count": 90,
"is_parallel": true,
"self": 65.37278196499881,
"children": {
"TorchPPOOptimizer.update": {
"total": 113.27737693000142,
"count": 4584,
"is_parallel": true,
"self": 113.27737693000142
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1260798649999515,
"count": 1,
"self": 0.0008610619998989932,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1252188030000525,
"count": 1,
"self": 0.1252188030000525
}
}
}
}
}
}
}