Pyro-X2's picture
Push trained model
c254071 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0865230560302734,
"min": 1.0865230560302734,
"max": 2.834765911102295,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10326.3154296875,
"min": 10326.3154296875,
"max": 28937.291015625,
"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": 13.521689414978027,
"min": 0.31581056118011475,
"max": 13.521689414978027,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2636.7294921875,
"min": 61.267250061035156,
"max": 2735.306640625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07142925126747429,
"min": 0.06319557402286377,
"max": 0.07409184812108743,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28571700506989717,
"min": 0.2527822960914551,
"max": 0.3542521183815053,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18566032323767157,
"min": 0.16499350835482463,
"max": 0.2596227661067364,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7426412929506863,
"min": 0.6599740334192985,
"max": 1.2272740161302043,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082009730600007e-05,
"min": 8.082009730600007e-05,
"max": 0.0029188200027059994,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.00032328038922400026,
"min": 0.00032328038922400026,
"max": 0.013851600038280001,
"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": 26.522727272727273,
"min": 4.159090909090909,
"max": 26.527272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1167.0,
"min": 183.0,
"max": 1459.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.522727272727273,
"min": 4.159090909090909,
"max": 26.527272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1167.0,
"min": 183.0,
"max": 1459.0,
"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": "1735494438",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
"command_line_arguments": "/home/jakub/.local/bin/mlagents-learn config/ppo/SnowballTarget.yaml --env=../hugging_face_rl_course/training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --run-id=SnownballTarget1 --force",
"mlagents_version": "1.1.0",
"mlagents_envs_version": "1.1.0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1735494616"
},
"total": 178.46247538099988,
"count": 1,
"self": 0.21778031699977873,
"children": {
"run_training.setup": {
"total": 0.013789022000082696,
"count": 1,
"self": 0.013789022000082696
},
"TrainerController.start_learning": {
"total": 178.23090604200002,
"count": 1,
"self": 0.2179639299961309,
"children": {
"TrainerController._reset_env": {
"total": 3.310624281999935,
"count": 1,
"self": 3.310624281999935
},
"TrainerController.advance": {
"total": 174.66699410400406,
"count": 18192,
"self": 0.21197300500807614,
"children": {
"env_step": {
"total": 128.30234109998491,
"count": 18192,
"self": 98.53425444696336,
"children": {
"SubprocessEnvManager._take_step": {
"total": 29.6297942860092,
"count": 18192,
"self": 0.6681960030130085,
"children": {
"TorchPolicy.evaluate": {
"total": 28.961598282996192,
"count": 18192,
"self": 28.961598282996192
}
}
},
"workers": {
"total": 0.1382923670123546,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 177.83709484299652,
"count": 18192,
"is_parallel": true,
"self": 92.94755295702385,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009683749999567226,
"count": 1,
"is_parallel": true,
"self": 0.0002434739999443991,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007249010000123235,
"count": 10,
"is_parallel": true,
"self": 0.0007249010000123235
}
}
},
"UnityEnvironment.step": {
"total": 0.01730880500008425,
"count": 1,
"is_parallel": true,
"self": 0.000189036000165288,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00012750899986713193,
"count": 1,
"is_parallel": true,
"self": 0.00012750899986713193
},
"communicator.exchange": {
"total": 0.01646294400006809,
"count": 1,
"is_parallel": true,
"self": 0.01646294400006809
},
"steps_from_proto": {
"total": 0.0005293159999837371,
"count": 1,
"is_parallel": true,
"self": 0.00011393600038900331,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004153799995947338,
"count": 10,
"is_parallel": true,
"self": 0.0004153799995947338
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 84.88954188597268,
"count": 18191,
"is_parallel": true,
"self": 3.4794113509549334,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 1.6858899910109812,
"count": 18191,
"is_parallel": true,
"self": 1.6858899910109812
},
"communicator.exchange": {
"total": 69.70420888501258,
"count": 18191,
"is_parallel": true,
"self": 69.70420888501258
},
"steps_from_proto": {
"total": 10.020031658994185,
"count": 18191,
"is_parallel": true,
"self": 2.0616233589491912,
"children": {
"_process_rank_one_or_two_observation": {
"total": 7.958408300044994,
"count": 181910,
"is_parallel": true,
"self": 7.958408300044994
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 46.15267999901107,
"count": 18192,
"self": 0.2510481010153853,
"children": {
"process_trajectory": {
"total": 10.650585176996174,
"count": 18192,
"self": 10.4785585909965,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17202658599967435,
"count": 4,
"self": 0.17202658599967435
}
}
},
"_update_policy": {
"total": 35.25104672099951,
"count": 90,
"self": 15.91775787599795,
"children": {
"TorchPPOOptimizer.update": {
"total": 19.33328884500156,
"count": 4587,
"self": 19.33328884500156
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.619998890120769e-07,
"count": 1,
"self": 4.619998890120769e-07
},
"TrainerController._save_models": {
"total": 0.035323263999998744,
"count": 1,
"self": 0.0004693680000400491,
"children": {
"RLTrainer._checkpoint": {
"total": 0.034853895999958695,
"count": 1,
"self": 0.034853895999958695
}
}
}
}
}
}
}