{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 0.790346086025238, "min": 0.7343851327896118, "max": 1.096280813217163, "count": 200 }, "Agent.Policy.Entropy.sum": { "value": 31613.84375, "min": 29387.15625, "max": 43931.8515625, "count": 200 }, "Agent.Environment.LessonNumber.pattern.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "Agent.Environment.LessonNumber.pattern.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "Agent.Environment.LessonNumber.task.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "Agent.Environment.LessonNumber.task.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "Agent.Step.mean": { "value": 7999096.0, "min": 39096.0, "max": 7999096.0, "count": 200 }, "Agent.Step.sum": { "value": 7999096.0, "min": 39096.0, "max": 7999096.0, "count": 200 }, "Agent.Policy.ExtrinsicValueEstimate.mean": { "value": 9.780200004577637, "min": 2.4280426502227783, "max": 9.820754051208496, "count": 200 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 234.72479248046875, "min": 55.84497833251953, "max": 235.69810485839844, "count": 200 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.04866604715246625, "min": 0.04545393447545986, "max": 0.05493653173690536, "count": 200 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.14599814145739876, "min": 0.10218151656833166, "max": 0.1648095952107161, "count": 200 }, "Agent.Losses.ValueLoss.mean": { "value": 0.003906352770591473, "min": 0.002974676047400978, "max": 3.8673377021526294, "count": 200 }, "Agent.Losses.ValueLoss.sum": { "value": 0.011719058311774418, "min": 0.008924028142202934, "max": 10.25289195190583, "count": 200 }, "Agent.Policy.LearningRate.mean": { "value": 8.856997047999973e-07, "min": 8.856997047999973e-07, "max": 0.00029907840030719997, "count": 200 }, "Agent.Policy.LearningRate.sum": { "value": 2.657099114399992e-06, "min": 2.657099114399992e-06, "max": 0.0008936568021144, "count": 200 }, "Agent.Policy.Epsilon.mean": { "value": 0.10029520000000001, "min": 0.10029520000000001, "max": 0.1996928, "count": 200 }, "Agent.Policy.Epsilon.sum": { "value": 0.30088560000000003, "min": 0.30088560000000003, "max": 0.5978856, "count": 200 }, "Agent.Policy.Beta.mean": { "value": 2.4730479999999958e-05, "min": 2.4730479999999958e-05, "max": 0.004984670720000001, "count": 200 }, "Agent.Policy.Beta.sum": { "value": 7.419143999999988e-05, "min": 7.419143999999988e-05, "max": 0.014894491440000001, "count": 200 }, "Agent.Environment.EpisodeLength.mean": { "value": 4999.0, "min": 4999.0, "max": 4999.0, "count": 200 }, "Agent.Environment.EpisodeLength.sum": { "value": 39992.0, "min": 39992.0, "max": 39992.0, "count": 200 }, "Agent.WindFarmControl.IndividualPerformance.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "Agent.WindFarmControl.IndividualPerformance.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "Agent.WindFarmControl.AvoidDamageReward.mean": { "value": 4875.396667480469, "min": 1677.5268249511719, "max": 4897.457214355469, "count": 200 }, "Agent.WindFarmControl.AvoidDamageReward.sum": { "value": 39003.17333984375, "min": 13420.214599609375, "max": 39179.65771484375, "count": 200 }, "Agent.Environment.CumulativeReward.mean": { "value": 4857.6708984375, "min": 1789.2040557861328, "max": 4891.219200134277, "count": 200 }, "Agent.Environment.CumulativeReward.sum": { "value": 38861.3671875, "min": 14313.632446289062, "max": 39129.75360107422, "count": 200 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 4857.6708984375, "min": 1789.2040557861328, "max": 4891.219200134277, "count": 200 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 38861.3671875, "min": 14313.632446289062, "max": 39129.75360107422, "count": 200 }, "Agent.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "Agent.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1715269261", "python_version": "3.9.18 (main, Sep 11 2023, 14:09:26) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\pdsie\\anaconda3\\envs\\mlagents20\\Scripts\\mlagents-learn c:/users/pdsie/documents/hivex/src/hivex/training/baseline/ml_agents/configs/mlagents/tmp/train/WindFarmControl_pattern_6_task_1_run_id_1_train.yaml --run-id=WindFarmControl/train/WindFarmControl_pattern_6_task_1_run_id_1_train", "mlagents_version": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.7.1+cu110", "numpy_version": "1.21.2", "end_time_seconds": "1715273193" }, "total": 3932.1076965, "count": 1, "self": 0.2694571000001815, "children": { "run_training.setup": { "total": 0.057912399999999975, "count": 1, "self": 0.057912399999999975 }, "TrainerController.start_learning": { "total": 3931.780327, "count": 1, "self": 11.143726699908257, "children": { "TrainerController._reset_env": { "total": 1.6015077999999998, "count": 1, "self": 1.6015077999999998 }, "TrainerController.advance": { "total": 3919.008560400092, "count": 1002053, "self": 10.426466300008997, "children": { "env_step": { "total": 3908.582094100083, "count": 1002053, "self": 1664.7135692999927, "children": { "SubprocessEnvManager._take_step": { "total": 2237.3401259001093, "count": 1002053, "self": 28.281610000073215, "children": { "TorchPolicy.evaluate": { "total": 2209.058515900036, "count": 1002053, "self": 2209.058515900036 } } }, "workers": { "total": 6.528398899980708, "count": 1002053, "self": 0.0, "children": { "worker_root": { "total": 3916.478589399937, "count": 1002053, "is_parallel": true, "self": 2935.2456467999436, "children": { "steps_from_proto": { "total": 0.00024140000000005823, "count": 1, "is_parallel": true, "self": 0.00011190000000005362, "children": { "_process_rank_one_or_two_observation": { "total": 0.0001295000000000046, "count": 2, "is_parallel": true, "self": 0.0001295000000000046 } } }, "UnityEnvironment.step": { "total": 981.2327011999935, "count": 1002053, "is_parallel": true, "self": 52.88822529990375, "children": { "UnityEnvironment._generate_step_input": { "total": 86.6870290998966, "count": 1002053, "is_parallel": true, "self": 86.6870290998966 }, "communicator.exchange": { "total": 696.799883800111, "count": 1002053, "is_parallel": true, "self": 696.799883800111 }, "steps_from_proto": { "total": 144.85756300008217, "count": 1002053, "is_parallel": true, "self": 81.40976620002975, "children": { "_process_rank_one_or_two_observation": { "total": 63.447796800052416, "count": 2004106, "is_parallel": true, "self": 63.447796800052416 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.189999986512703e-05, "count": 1, "self": 2.189999986512703e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 3929.2400280000875, "count": 110669, "is_parallel": true, "self": 4.825245700135383, "children": { "process_trajectory": { "total": 1952.6322472999582, "count": 110669, "is_parallel": true, "self": 1952.1611276999586, "children": { "RLTrainer._checkpoint": { "total": 0.471119599999696, "count": 16, "is_parallel": true, "self": 0.471119599999696 } } }, "_update_policy": { "total": 1971.7825349999937, "count": 600, "is_parallel": true, "self": 580.4958276999798, "children": { "TorchPPOOptimizer.update": { "total": 1391.2867073000139, "count": 93600, "is_parallel": true, "self": 1391.2867073000139 } } } } } } } } }, "TrainerController._save_models": { "total": 0.026510199999847828, "count": 1, "self": 0.005493799999840121, "children": { "RLTrainer._checkpoint": { "total": 0.021016400000007707, "count": 1, "self": 0.021016400000007707 } } } } } } }