{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 0.855984091758728, "min": 0.505821704864502, "max": 1.0962650775909424, "count": 200 }, "Agent.Policy.Entropy.sum": { "value": 34225.66796875, "min": 20208.58984375, "max": 43911.99609375, "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": 9.723402976989746, "min": 2.2312328815460205, "max": 9.799125671386719, "count": 200 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 233.36167907714844, "min": 51.318355560302734, "max": 235.17901611328125, "count": 200 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.051323230499364735, "min": 0.04491637487173272, "max": 0.054505098355649456, "count": 200 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.1539696914980942, "min": 0.10527651318504164, "max": 0.16351529506694837, "count": 200 }, "Agent.Losses.ValueLoss.mean": { "value": 0.0049588195544192646, "min": 0.0030816976082167543, "max": 3.9712093503524857, "count": 200 }, "Agent.Losses.ValueLoss.sum": { "value": 0.014876458663257795, "min": 0.009245092824650263, "max": 7.942418700704971, "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": 4846.482971191406, "min": 1364.4507369995117, "max": 4881.824462890625, "count": 200 }, "Agent.WindFarmControl.AvoidDamageReward.sum": { "value": 38771.86376953125, "min": 10915.605895996094, "max": 39054.595703125, "count": 200 }, "Agent.Environment.CumulativeReward.mean": { "value": 4802.791069030762, "min": 1410.6444644927979, "max": 4871.900245666504, "count": 200 }, "Agent.Environment.CumulativeReward.sum": { "value": 38422.328552246094, "min": 11285.155715942383, "max": 38975.20196533203, "count": 200 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 4802.791069030762, "min": 1410.6444644927979, "max": 4871.900245666504, "count": 200 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 38422.328552246094, "min": 11285.155715942383, "max": 38975.20196533203, "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": "1715164204", "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_1_task_1_run_id_0_train.yaml --run-id=WindFarmControl/train/WindFarmControl_pattern_1_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": "1715167810" }, "total": 3606.8480412000004, "count": 1, "self": 0.1417844000002333, "children": { "run_training.setup": { "total": 0.045487500000000014, "count": 1, "self": 0.045487500000000014 }, "TrainerController.start_learning": { "total": 3606.6607693, "count": 1, "self": 10.57787299982374, "children": { "TrainerController._reset_env": { "total": 2.9059438999999996, "count": 1, "self": 2.9059438999999996 }, "TrainerController.advance": { "total": 3593.1502613001767, "count": 1002051, "self": 10.148106600211577, "children": { "env_step": { "total": 3583.002154699965, "count": 1002051, "self": 1495.395013600044, "children": { "SubprocessEnvManager._take_step": { "total": 2081.919388500077, "count": 1002051, "self": 24.965887699899213, "children": { "TorchPolicy.evaluate": { "total": 2056.9535008001776, "count": 1002051, "self": 2056.9535008001776 } } }, "workers": { "total": 5.687752599844124, "count": 1002051, "self": 0.0, "children": { "worker_root": { "total": 3592.1515751002244, "count": 1002051, "is_parallel": true, "self": 2734.081737800304, "children": { "steps_from_proto": { "total": 0.00025630000000020914, "count": 1, "is_parallel": true, "self": 0.00011340000000004125, "children": { "_process_rank_one_or_two_observation": { "total": 0.0001429000000001679, "count": 2, "is_parallel": true, "self": 0.0001429000000001679 } } }, "UnityEnvironment.step": { "total": 858.0695809999205, "count": 1002051, "is_parallel": true, "self": 41.71356829987474, "children": { "UnityEnvironment._generate_step_input": { "total": 62.90565180009499, "count": 1002051, "is_parallel": true, "self": 62.90565180009499 }, "communicator.exchange": { "total": 636.1016120999109, "count": 1002051, "is_parallel": true, "self": 636.1016120999109 }, "steps_from_proto": { "total": 117.34874880003984, "count": 1002051, "is_parallel": true, "self": 66.03595579985648, "children": { "_process_rank_one_or_two_observation": { "total": 51.31279300018337, "count": 2004102, "is_parallel": true, "self": 51.31279300018337 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.099999983329326e-05, "count": 1, "self": 2.099999983329326e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 3602.8280018999576, "count": 107125, "is_parallel": true, "self": 4.575515599927712, "children": { "process_trajectory": { "total": 1851.4764810000318, "count": 107125, "is_parallel": true, "self": 1851.063276800032, "children": { "RLTrainer._checkpoint": { "total": 0.4132041999995977, "count": 16, "is_parallel": true, "self": 0.4132041999995977 } } }, "_update_policy": { "total": 1746.776005299998, "count": 600, "is_parallel": true, "self": 578.3676885000043, "children": { "TorchPPOOptimizer.update": { "total": 1168.4083167999936, "count": 93600, "is_parallel": true, "self": 1168.4083167999936 } } } } } } } } }, "TrainerController._save_models": { "total": 0.02667010000004666, "count": 1, "self": 0.005927000000156113, "children": { "RLTrainer._checkpoint": { "total": 0.020743099999890546, "count": 1, "self": 0.020743099999890546 } } } } } } }