{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 0.7218747735023499, "min": 0.6940035223960876, "max": 1.0971450805664062, "count": 200 }, "Agent.Policy.Entropy.sum": { "value": 28869.21484375, "min": 27782.349609375, "max": 43947.2421875, "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": 9.735854148864746, "min": 2.147902011871338, "max": 9.793658256530762, "count": 200 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 233.66049194335938, "min": 49.4017448425293, "max": 235.04779052734375, "count": 200 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.04933432716412455, "min": 0.04447418065995277, "max": 0.055316796393035765, "count": 200 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.14800298149237365, "min": 0.10811876258473299, "max": 0.1659503891791073, "count": 200 }, "Agent.Losses.ValueLoss.mean": { "value": 0.005592584401234664, "min": 0.0039296456493574956, "max": 3.5018418881421285, "count": 200 }, "Agent.Losses.ValueLoss.sum": { "value": 0.01677775320370399, "min": 0.011788936948072487, "max": 9.655951581451864, "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": 4849.96142578125, "min": 1752.84521484375, "max": 4872.472961425781, "count": 200 }, "Agent.WindFarmControl.AvoidDamageReward.sum": { "value": 38799.69140625, "min": 14022.76171875, "max": 38979.78369140625, "count": 200 }, "Agent.Environment.CumulativeReward.mean": { "value": 4832.607498168945, "min": 1931.336552143097, "max": 4872.811553955078, "count": 200 }, "Agent.Environment.CumulativeReward.sum": { "value": 38660.85998535156, "min": 15450.692417144775, "max": 38982.492431640625, "count": 200 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 4832.607498168945, "min": 1931.336552143097, "max": 4872.811553955078, "count": 200 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 38660.85998535156, "min": 15450.692417144775, "max": 38982.492431640625, "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": "1715245748", "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_3_task_1_run_id_1_train.yaml --run-id=WindFarmControl/train/WindFarmControl_pattern_3_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": "1715249586" }, "total": 3837.3614258000002, "count": 1, "self": 0.16283079999993788, "children": { "run_training.setup": { "total": 0.045013199999999975, "count": 1, "self": 0.045013199999999975 }, "TrainerController.start_learning": { "total": 3837.1535818, "count": 1, "self": 10.813646200022049, "children": { "TrainerController._reset_env": { "total": 1.5855089000000002, "count": 1, "self": 1.5855089000000002 }, "TrainerController.advance": { "total": 3824.728977499978, "count": 1002054, "self": 10.196508799975163, "children": { "env_step": { "total": 3814.532468700003, "count": 1002054, "self": 1622.7114112999097, "children": { "SubprocessEnvManager._take_step": { "total": 2185.8818435000403, "count": 1002054, "self": 27.394037200139337, "children": { "TorchPolicy.evaluate": { "total": 2158.487806299901, "count": 1002054, "self": 2158.487806299901 } } }, "workers": { "total": 5.939213900052835, "count": 1002054, "self": 0.0, "children": { "worker_root": { "total": 3822.4237732000774, "count": 1002054, "is_parallel": true, "self": 2865.7397840001263, "children": { "steps_from_proto": { "total": 0.0002431000000000516, "count": 1, "is_parallel": true, "self": 0.00011039999999995498, "children": { "_process_rank_one_or_two_observation": { "total": 0.00013270000000009663, "count": 2, "is_parallel": true, "self": 0.00013270000000009663 } } }, "UnityEnvironment.step": { "total": 956.6837460999511, "count": 1002054, "is_parallel": true, "self": 51.44988209972678, "children": { "UnityEnvironment._generate_step_input": { "total": 85.67555180013024, "count": 1002054, "is_parallel": true, "self": 85.67555180013024 }, "communicator.exchange": { "total": 676.3446058000975, "count": 1002054, "is_parallel": true, "self": 676.3446058000975 }, "steps_from_proto": { "total": 143.2137063999966, "count": 1002054, "is_parallel": true, "self": 81.08753609989604, "children": { "_process_rank_one_or_two_observation": { "total": 62.126170300100554, "count": 2004108, "is_parallel": true, "self": 62.126170300100554 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.009999980145949e-05, "count": 1, "self": 2.009999980145949e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 3834.6650312999523, "count": 109417, "is_parallel": true, "self": 4.533581299905109, "children": { "process_trajectory": { "total": 1926.8658423000447, "count": 109417, "is_parallel": true, "self": 1926.4221271000447, "children": { "RLTrainer._checkpoint": { "total": 0.4437152000001561, "count": 16, "is_parallel": true, "self": 0.4437152000001561 } } }, "_update_policy": { "total": 1903.2656077000022, "count": 600, "is_parallel": true, "self": 572.3421929000413, "children": { "TorchPPOOptimizer.update": { "total": 1330.923414799961, "count": 93600, "is_parallel": true, "self": 1330.923414799961 } } } } } } } } }, "TrainerController._save_models": { "total": 0.02542910000011034, "count": 1, "self": 0.004638500000055501, "children": { "RLTrainer._checkpoint": { "total": 0.020790600000054837, "count": 1, "self": 0.020790600000054837 } } } } } } }