{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 0.8999090790748596, "min": 0.2972509264945984, "max": 1.0968706607818604, "count": 200 }, "Agent.Policy.Entropy.sum": { "value": 35996.36328125, "min": 11894.79296875, "max": 43936.25, "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": 9.783114433288574, "min": 2.3174941539764404, "max": 9.821760177612305, "count": 200 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 234.79473876953125, "min": 53.302364349365234, "max": 235.7222442626953, "count": 200 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.0490415236332439, "min": 0.04379769929708721, "max": 0.053755234173242204, "count": 200 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.1471245708997317, "min": 0.1060606107081791, "max": 0.1612657025197266, "count": 200 }, "Agent.Losses.ValueLoss.mean": { "value": 0.0037911957570320245, "min": 0.0033585095964857223, "max": 4.002783409630259, "count": 200 }, "Agent.Losses.ValueLoss.sum": { "value": 0.011373587271096074, "min": 0.010075528789457167, "max": 8.32337309242714, "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": 4877.3953857421875, "min": 1900.360107421875, "max": 4887.926940917969, "count": 200 }, "Agent.WindFarmControl.AvoidDamageReward.sum": { "value": 39019.1630859375, "min": 15202.880859375, "max": 39103.41552734375, "count": 200 }, "Agent.Environment.CumulativeReward.mean": { "value": 4858.763168334961, "min": 2012.046220779419, "max": 4892.310653686523, "count": 200 }, "Agent.Environment.CumulativeReward.sum": { "value": 38870.10534667969, "min": 16096.369766235352, "max": 39138.48522949219, "count": 200 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 4858.763168334961, "min": 2012.046220779419, "max": 4892.310653686523, "count": 200 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 38870.10534667969, "min": 16096.369766235352, "max": 39138.48522949219, "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": "1715209514", "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_7_task_1_run_id_0_train.yaml --run-id=WindFarmControl/train/WindFarmControl_pattern_7_task_1_run_id_0_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": "1715213110" }, "total": 3596.5640862, "count": 1, "self": 0.15421680000008564, "children": { "run_training.setup": { "total": 0.04480879999999998, "count": 1, "self": 0.04480879999999998 }, "TrainerController.start_learning": { "total": 3596.3650606, "count": 1, "self": 10.14600269999346, "children": { "TrainerController._reset_env": { "total": 1.6028471999999998, "count": 1, "self": 1.6028471999999998 }, "TrainerController.advance": { "total": 3584.591292600007, "count": 1002054, "self": 10.10478889984961, "children": { "env_step": { "total": 3574.4865037001573, "count": 1002054, "self": 1484.0113817003808, "children": { "SubprocessEnvManager._take_step": { "total": 2084.851164899848, "count": 1002054, "self": 24.870305299856682, "children": { "TorchPolicy.evaluate": { "total": 2059.980859599991, "count": 1002054, "self": 2059.980859599991 } } }, "workers": { "total": 5.623957099928658, "count": 1002054, "self": 0.0, "children": { "worker_root": { "total": 3583.253869400173, "count": 1002054, "is_parallel": true, "self": 2731.6951565001973, "children": { "steps_from_proto": { "total": 0.00026919999999996946, "count": 1, "is_parallel": true, "self": 0.00012839999999991747, "children": { "_process_rank_one_or_two_observation": { "total": 0.000140800000000052, "count": 2, "is_parallel": true, "self": 0.000140800000000052 } } }, "UnityEnvironment.step": { "total": 851.5584436999753, "count": 1002054, "is_parallel": true, "self": 41.915615699938826, "children": { "UnityEnvironment._generate_step_input": { "total": 62.60759630015947, "count": 1002054, "is_parallel": true, "self": 62.60759630015947 }, "communicator.exchange": { "total": 630.67775389993, "count": 1002054, "is_parallel": true, "self": 630.67775389993 }, "steps_from_proto": { "total": 116.35747779994699, "count": 1002054, "is_parallel": true, "self": 65.04441319959759, "children": { "_process_rank_one_or_two_observation": { "total": 51.3130646003494, "count": 2004108, "is_parallel": true, "self": 51.3130646003494 } } } } } } } } } } } } }, "trainer_threads": { "total": 1.9699999938893598e-05, "count": 1, "self": 1.9699999938893598e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 3593.8822137000634, "count": 105532, "is_parallel": true, "self": 4.550150600014604, "children": { "process_trajectory": { "total": 1845.2927558000436, "count": 105532, "is_parallel": true, "self": 1844.892434400044, "children": { "RLTrainer._checkpoint": { "total": 0.4003213999994273, "count": 16, "is_parallel": true, "self": 0.4003213999994273 } } }, "_update_policy": { "total": 1744.0393073000055, "count": 600, "is_parallel": true, "self": 575.0468961000615, "children": { "TorchPPOOptimizer.update": { "total": 1168.992411199944, "count": 93600, "is_parallel": true, "self": 1168.992411199944 } } } } } } } } }, "TrainerController._save_models": { "total": 0.024898399999983667, "count": 1, "self": 0.004862000000230182, "children": { "RLTrainer._checkpoint": { "total": 0.020036399999753485, "count": 1, "self": 0.020036399999753485 } } } } } } }