SnowballTarget1 / run_logs /timers.json
Honza's picture
train1
9562f8d
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9938265085220337,
"min": 0.9835718870162964,
"max": 2.8637094497680664,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9489.0556640625,
"min": 9489.0556640625,
"max": 29327.248046875,
"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": 11.869491577148438,
"min": 0.384447306394577,
"max": 11.869491577148438,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2314.55078125,
"min": 74.58277893066406,
"max": 2428.880859375,
"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": 0.06807874128628778,
"min": 0.061815504843766314,
"max": 0.07409520894996639,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27231496514515113,
"min": 0.25304502038988197,
"max": 0.3681162680538061,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21224709432206904,
"min": 0.10572833595021316,
"max": 0.2927317808071772,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8489883772882761,
"min": 0.42291334380085266,
"max": 1.463658904035886,
"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": 23.40909090909091,
"min": 3.090909090909091,
"max": 23.545454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1030.0,
"min": 136.0,
"max": 1295.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.40909090909091,
"min": 3.090909090909091,
"max": 23.545454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1030.0,
"min": 136.0,
"max": 1295.0,
"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": "1674159124",
"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": "1674159562"
},
"total": 438.509697568,
"count": 1,
"self": 0.39351560899990545,
"children": {
"run_training.setup": {
"total": 0.11144312099997933,
"count": 1,
"self": 0.11144312099997933
},
"TrainerController.start_learning": {
"total": 438.0047388380001,
"count": 1,
"self": 0.5336352709919083,
"children": {
"TrainerController._reset_env": {
"total": 10.282959554000058,
"count": 1,
"self": 10.282959554000058
},
"TrainerController.advance": {
"total": 427.06162012600805,
"count": 18201,
"self": 0.2727154360009081,
"children": {
"env_step": {
"total": 426.78890469000714,
"count": 18201,
"self": 281.3358688359988,
"children": {
"SubprocessEnvManager._take_step": {
"total": 145.18079025600287,
"count": 18201,
"self": 1.4022653490022776,
"children": {
"TorchPolicy.evaluate": {
"total": 143.7785249070006,
"count": 18201,
"self": 31.90762309900356,
"children": {
"TorchPolicy.sample_actions": {
"total": 111.87090180799703,
"count": 18201,
"self": 111.87090180799703
}
}
}
}
},
"workers": {
"total": 0.2722455980054974,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 436.67787146399496,
"count": 18201,
"is_parallel": true,
"self": 209.69760817700876,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.009486310999932357,
"count": 1,
"is_parallel": true,
"self": 0.003973030999873117,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00551328000005924,
"count": 10,
"is_parallel": true,
"self": 0.00551328000005924
}
}
},
"UnityEnvironment.step": {
"total": 0.04594635400007974,
"count": 1,
"is_parallel": true,
"self": 0.0004924290001326881,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00032232000000931293,
"count": 1,
"is_parallel": true,
"self": 0.00032232000000931293
},
"communicator.exchange": {
"total": 0.04103823100001591,
"count": 1,
"is_parallel": true,
"self": 0.04103823100001591
},
"steps_from_proto": {
"total": 0.004093373999921823,
"count": 1,
"is_parallel": true,
"self": 0.00045516799991673906,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003638206000005084,
"count": 10,
"is_parallel": true,
"self": 0.003638206000005084
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 226.9802632869862,
"count": 18200,
"is_parallel": true,
"self": 8.286616370001411,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.955180009997093,
"count": 18200,
"is_parallel": true,
"self": 4.955180009997093
},
"communicator.exchange": {
"total": 179.9053956719963,
"count": 18200,
"is_parallel": true,
"self": 179.9053956719963
},
"steps_from_proto": {
"total": 33.833071234991394,
"count": 18200,
"is_parallel": true,
"self": 6.7731297779703254,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.05994145702107,
"count": 182000,
"is_parallel": true,
"self": 27.05994145702107
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.842299995289068e-05,
"count": 1,
"self": 4.842299995289068e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 424.0739142499681,
"count": 353035,
"is_parallel": true,
"self": 9.351768177991858,
"children": {
"process_trajectory": {
"total": 244.31284960697633,
"count": 353035,
"is_parallel": true,
"self": 243.5884348449763,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7244147620000376,
"count": 4,
"is_parallel": true,
"self": 0.7244147620000376
}
}
},
"_update_policy": {
"total": 170.4092964649999,
"count": 90,
"is_parallel": true,
"self": 43.83872361600322,
"children": {
"TorchPPOOptimizer.update": {
"total": 126.57057284899668,
"count": 4587,
"is_parallel": true,
"self": 126.57057284899668
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12647546400012288,
"count": 1,
"self": 0.0009279320001951419,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12554753199992774,
"count": 1,
"self": 0.12554753199992774
}
}
}
}
}
}
}