{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 1.0380889177322388, "min": 0.8830379247665405, "max": 1.0959848165512085, "count": 200 }, "Agent.Policy.Entropy.sum": { "value": 41548.47265625, "min": 35314.453125, "max": 43883.23046875, "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": 9.131550788879395, "min": 0.11973758786916733, "max": 9.549927711486816, "count": 200 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 219.1572265625, "min": 2.873702049255371, "max": 229.19827270507812, "count": 200 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.048034041874907125, "min": 0.04580663198315065, "max": 0.054690147842472746, "count": 200 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.14410212562472138, "min": 0.10218805785067767, "max": 0.16407044352741823, "count": 200 }, "Agent.Losses.ValueLoss.mean": { "value": 0.24561994275011656, "min": 0.05102165775107486, "max": 1.3097947237547487, "count": 200 }, "Agent.Losses.ValueLoss.sum": { "value": 0.7368598282503497, "min": 0.15306497325322457, "max": 2.6195894475094974, "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": 4526.188629150391, "min": 127.83679389953613, "max": 4709.7381591796875, "count": 200 }, "Agent.WindFarmControl.IndividualPerformance.sum": { "value": 36209.509033203125, "min": 1022.6943511962891, "max": 37677.9052734375, "count": 200 }, "Agent.Environment.CumulativeReward.mean": { "value": 4515.375778198242, "min": 135.81824522610202, "max": 4678.512313842773, "count": 200 }, "Agent.Environment.CumulativeReward.sum": { "value": 36123.00622558594, "min": 1086.5459618088162, "max": 37428.09851074219, "count": 200 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 4515.375778198242, "min": 135.81824522610202, "max": 4678.512313842773, "count": 200 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 36123.00622558594, "min": 1086.5459618088162, "max": 37428.09851074219, "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": "1715205914", "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_0_run_id_0_train.yaml --run-id=WindFarmControl/train/WindFarmControl_pattern_7_task_0_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": "1715209513" }, "total": 3599.5111461, "count": 1, "self": 0.16563429999996515, "children": { "run_training.setup": { "total": 0.053839700000000046, "count": 1, "self": 0.053839700000000046 }, "TrainerController.start_learning": { "total": 3599.2916721, "count": 1, "self": 10.52767030000723, "children": { "TrainerController._reset_env": { "total": 1.6289813, "count": 1, "self": 1.6289813 }, "TrainerController.advance": { "total": 3587.108129099993, "count": 1002049, "self": 9.584680699938872, "children": { "env_step": { "total": 3577.5234484000543, "count": 1002049, "self": 1620.3160727001416, "children": { "SubprocessEnvManager._take_step": { "total": 1952.027939000039, "count": 1002049, "self": 24.735151999939717, "children": { "TorchPolicy.evaluate": { "total": 1927.2927870000992, "count": 1002049, "self": 1927.2927870000992 } } }, "workers": { "total": 5.1794366998738415, "count": 1002049, "self": 0.0, "children": { "worker_root": { "total": 3582.202408899786, "count": 1002049, "is_parallel": true, "self": 2626.5963989996867, "children": { "steps_from_proto": { "total": 0.0002340000000000675, "count": 1, "is_parallel": true, "self": 0.00010760000000009651, "children": { "_process_rank_one_or_two_observation": { "total": 0.00012639999999997098, "count": 2, "is_parallel": true, "self": 0.00012639999999997098 } } }, "UnityEnvironment.step": { "total": 955.6057759000992, "count": 1002049, "is_parallel": true, "self": 46.327568599968004, "children": { "UnityEnvironment._generate_step_input": { "total": 64.54040490016722, "count": 1002049, "is_parallel": true, "self": 64.54040490016722 }, "communicator.exchange": { "total": 718.9283392000389, "count": 1002049, "is_parallel": true, "self": 718.9283392000389 }, "steps_from_proto": { "total": 125.80946319992506, "count": 1002049, "is_parallel": true, "self": 69.09548659991334, "children": { "_process_rank_one_or_two_observation": { "total": 56.71397660001172, "count": 2004098, "is_parallel": true, "self": 56.71397660001172 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.4899999971239595e-05, "count": 1, "self": 2.4899999971239595e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 3596.8486651999333, "count": 117157, "is_parallel": true, "self": 4.129057599956923, "children": { "process_trajectory": { "total": 2018.4488423999678, "count": 117157, "is_parallel": true, "self": 2018.0572649999674, "children": { "RLTrainer._checkpoint": { "total": 0.39157740000041485, "count": 16, "is_parallel": true, "self": 0.39157740000041485 } } }, "_update_policy": { "total": 1574.2707652000083, "count": 600, "is_parallel": true, "self": 567.0298861000593, "children": { "TorchPPOOptimizer.update": { "total": 1007.240879099949, "count": 93600, "is_parallel": true, "self": 1007.240879099949 } } } } } } } } }, "TrainerController._save_models": { "total": 0.02686649999986912, "count": 1, "self": 0.006530999999995402, "children": { "RLTrainer._checkpoint": { "total": 0.02033549999987372, "count": 1, "self": 0.02033549999987372 } } } } } } }