root-jlee's picture
First Push
7fed884 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7990298271179199,
"min": 0.798519492149353,
"max": 2.866894483566284,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7593.9794921875,
"min": 7593.9794921875,
"max": 29265.259765625,
"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": 12.866772651672363,
"min": 0.3333686888217926,
"max": 12.866772651672363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2509.020751953125,
"min": 64.67352294921875,
"max": 2594.26318359375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06553559234963163,
"min": 0.06102750507267832,
"max": 0.07842446209628287,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26214236939852653,
"min": 0.24411002029071327,
"max": 0.36069650384859986,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17617842219039506,
"min": 0.1379792516863923,
"max": 0.28110383816209494,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7047136887615802,
"min": 0.5519170067455692,
"max": 1.396230594492426,
"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": 25.295454545454547,
"min": 3.25,
"max": 25.545454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1113.0,
"min": 143.0,
"max": 1387.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.295454545454547,
"min": 3.25,
"max": 25.545454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1113.0,
"min": 143.0,
"max": 1387.0,
"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": "1749432839",
"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": "1749433283"
},
"total": 443.94015148799997,
"count": 1,
"self": 0.441260813000099,
"children": {
"run_training.setup": {
"total": 0.02489345300000423,
"count": 1,
"self": 0.02489345300000423
},
"TrainerController.start_learning": {
"total": 443.47399722199987,
"count": 1,
"self": 0.38239267301048585,
"children": {
"TrainerController._reset_env": {
"total": 3.436091458999954,
"count": 1,
"self": 3.436091458999954
},
"TrainerController.advance": {
"total": 439.57027032498945,
"count": 18192,
"self": 0.40870281899810834,
"children": {
"env_step": {
"total": 311.9516338540029,
"count": 18192,
"self": 239.01104201000692,
"children": {
"SubprocessEnvManager._take_step": {
"total": 72.72502460399642,
"count": 18192,
"self": 1.2873323070035667,
"children": {
"TorchPolicy.evaluate": {
"total": 71.43769229699285,
"count": 18192,
"self": 71.43769229699285
}
}
},
"workers": {
"total": 0.2155672399995865,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 441.9909375590029,
"count": 18192,
"is_parallel": true,
"self": 232.17320547099928,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00563166300003104,
"count": 1,
"is_parallel": true,
"self": 0.004125958000145147,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001505704999885893,
"count": 10,
"is_parallel": true,
"self": 0.001505704999885893
}
}
},
"UnityEnvironment.step": {
"total": 0.03543892400000459,
"count": 1,
"is_parallel": true,
"self": 0.0005648359999668173,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041597400002046925,
"count": 1,
"is_parallel": true,
"self": 0.00041597400002046925
},
"communicator.exchange": {
"total": 0.03267456100002164,
"count": 1,
"is_parallel": true,
"self": 0.03267456100002164
},
"steps_from_proto": {
"total": 0.0017835529999956634,
"count": 1,
"is_parallel": true,
"self": 0.00034717799974259833,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001436375000253065,
"count": 10,
"is_parallel": true,
"self": 0.001436375000253065
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 209.8177320880036,
"count": 18191,
"is_parallel": true,
"self": 10.121655033992397,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.518537681009661,
"count": 18191,
"is_parallel": true,
"self": 5.518537681009661
},
"communicator.exchange": {
"total": 161.88073865499769,
"count": 18191,
"is_parallel": true,
"self": 161.88073865499769
},
"steps_from_proto": {
"total": 32.29680071800385,
"count": 18191,
"is_parallel": true,
"self": 5.839995446009652,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.4568052719942,
"count": 181910,
"is_parallel": true,
"self": 26.4568052719942
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 127.20993365198842,
"count": 18192,
"self": 0.4431216759888912,
"children": {
"process_trajectory": {
"total": 27.407884506000187,
"count": 18192,
"self": 26.924429238000243,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4834552679999433,
"count": 4,
"self": 0.4834552679999433
}
}
},
"_update_policy": {
"total": 99.35892746999934,
"count": 90,
"self": 40.63897779500246,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.71994967499688,
"count": 4587,
"self": 58.71994967499688
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.43000031838892e-07,
"count": 1,
"self": 9.43000031838892e-07
},
"TrainerController._save_models": {
"total": 0.08524182199994357,
"count": 1,
"self": 0.0008855469998252374,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08435627500011833,
"count": 1,
"self": 0.08435627500011833
}
}
}
}
}
}
}