arshiaze's picture
First Push
ae1d638 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9221019744873047,
"min": 0.9221019744873047,
"max": 2.8668272495269775,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8824.515625,
"min": 8824.515625,
"max": 29390.712890625,
"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": 12.358871459960938,
"min": 0.30807948112487793,
"max": 12.358871459960938,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2409.97998046875,
"min": 59.767417907714844,
"max": 2471.30224609375,
"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": 0.05880927580922919,
"min": 0.05880927580922919,
"max": 0.07332077560074737,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.23523710323691677,
"min": 0.23523710323691677,
"max": 0.3666038780037369,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20361584870546473,
"min": 0.1148528595769997,
"max": 0.2642480784361626,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8144633948218589,
"min": 0.4594114383079988,
"max": 1.321240392180813,
"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": 24.568181818181817,
"min": 3.3863636363636362,
"max": 24.78181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1081.0,
"min": 149.0,
"max": 1363.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.568181818181817,
"min": 3.3863636363636362,
"max": 24.78181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1081.0,
"min": 149.0,
"max": 1363.0,
"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": "1735438655",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1735439177"
},
"total": 521.914899545,
"count": 1,
"self": 0.4835558150000452,
"children": {
"run_training.setup": {
"total": 0.06857626400000072,
"count": 1,
"self": 0.06857626400000072
},
"TrainerController.start_learning": {
"total": 521.3627674659999,
"count": 1,
"self": 0.7858828199997561,
"children": {
"TrainerController._reset_env": {
"total": 6.276986813999997,
"count": 1,
"self": 6.276986813999997
},
"TrainerController.advance": {
"total": 514.2211869760001,
"count": 18205,
"self": 0.37706938199278284,
"children": {
"env_step": {
"total": 513.8441175940073,
"count": 18205,
"self": 396.5919912529989,
"children": {
"SubprocessEnvManager._take_step": {
"total": 116.8754268350047,
"count": 18205,
"self": 1.874561806998429,
"children": {
"TorchPolicy.evaluate": {
"total": 115.00086502800627,
"count": 18205,
"self": 115.00086502800627
}
}
},
"workers": {
"total": 0.3766995060037175,
"count": 18205,
"self": 0.0,
"children": {
"worker_root": {
"total": 519.6584534569986,
"count": 18205,
"is_parallel": true,
"self": 244.84776383399992,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0029404420000105347,
"count": 1,
"is_parallel": true,
"self": 0.0006939950000628414,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022464469999476933,
"count": 10,
"is_parallel": true,
"self": 0.0022464469999476933
}
}
},
"UnityEnvironment.step": {
"total": 0.07772320999998783,
"count": 1,
"is_parallel": true,
"self": 0.0008147519999397446,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004156420000072103,
"count": 1,
"is_parallel": true,
"self": 0.0004156420000072103
},
"communicator.exchange": {
"total": 0.07372491199998876,
"count": 1,
"is_parallel": true,
"self": 0.07372491199998876
},
"steps_from_proto": {
"total": 0.0027679040000521127,
"count": 1,
"is_parallel": true,
"self": 0.0004144780000956416,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002353425999956471,
"count": 10,
"is_parallel": true,
"self": 0.002353425999956471
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 274.81068962299867,
"count": 18204,
"is_parallel": true,
"self": 13.113597860998539,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.59156322200073,
"count": 18204,
"is_parallel": true,
"self": 6.59156322200073
},
"communicator.exchange": {
"total": 214.8643485869963,
"count": 18204,
"is_parallel": true,
"self": 214.8643485869963
},
"steps_from_proto": {
"total": 40.2411799530031,
"count": 18204,
"is_parallel": true,
"self": 7.754064427974072,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.487115525029026,
"count": 182040,
"is_parallel": true,
"self": 32.487115525029026
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00010852600007638102,
"count": 1,
"self": 0.00010852600007638102,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 508.4599382709725,
"count": 716873,
"is_parallel": true,
"self": 14.784050781981477,
"children": {
"process_trajectory": {
"total": 275.0031327589911,
"count": 716873,
"is_parallel": true,
"self": 274.3380112489913,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6651215099998353,
"count": 4,
"is_parallel": true,
"self": 0.6651215099998353
}
}
},
"_update_policy": {
"total": 218.6727547299999,
"count": 90,
"is_parallel": true,
"self": 62.719358891002514,
"children": {
"TorchPPOOptimizer.update": {
"total": 155.95339583899738,
"count": 4587,
"is_parallel": true,
"self": 155.95339583899738
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.07860232999996697,
"count": 1,
"self": 0.001108326999997189,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07749400299996978,
"count": 1,
"self": 0.07749400299996978
}
}
}
}
}
}
}