{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 0.8369514346122742, "min": 0.7041160464286804, "max": 1.096243143081665, "count": 200 }, "Agent.Policy.Entropy.sum": { "value": 33437.8828125, "min": 28164.642578125, "max": 43923.046875, "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": 9.684854507446289, "min": 2.500913619995117, "max": 9.834071159362793, "count": 200 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 232.43650817871094, "min": 57.52101516723633, "max": 236.01771545410156, "count": 200 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.049085859985285744, "min": 0.044494879220326855, "max": 0.05536894917618373, "count": 200 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.14725757995585723, "min": 0.10143189857626567, "max": 0.16610684752855118, "count": 200 }, "Agent.Losses.ValueLoss.mean": { "value": 0.004120568159845471, "min": 0.0032556263632281955, "max": 3.8101579174399376, "count": 200 }, "Agent.Losses.ValueLoss.sum": { "value": 0.012361704479536413, "min": 0.009766879089684587, "max": 8.377534157729574, "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": 4813.619445800781, "min": 1820.528305053711, "max": 4881.165771484375, "count": 200 }, "Agent.WindFarmControl.AvoidDamageReward.sum": { "value": 38508.95556640625, "min": 14564.226440429688, "max": 39049.326171875, "count": 200 }, "Agent.Environment.CumulativeReward.mean": { "value": 4833.473846435547, "min": 1856.2481536865234, "max": 4879.948081970215, "count": 200 }, "Agent.Environment.CumulativeReward.sum": { "value": 38667.790771484375, "min": 14849.985229492188, "max": 39039.58465576172, "count": 200 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 4833.473846435547, "min": 1856.2481536865234, "max": 4879.948081970215, "count": 200 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 38667.790771484375, "min": 14849.985229492188, "max": 39039.58465576172, "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": "1715223994", "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_0_task_1_run_id_1_train.yaml --run-id=WindFarmControl/train/WindFarmControl_pattern_0_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": "1715227591" }, "total": 3597.5215922, "count": 1, "self": 0.16180160000021715, "children": { "run_training.setup": { "total": 0.04441890000000004, "count": 1, "self": 0.04441890000000004 }, "TrainerController.start_learning": { "total": 3597.3153717, "count": 1, "self": 10.482027900219236, "children": { "TrainerController._reset_env": { "total": 2.8562113, "count": 1, "self": 2.8562113 }, "TrainerController.advance": { "total": 3583.9521339997805, "count": 1002052, "self": 9.5586081996762, "children": { "env_step": { "total": 3574.3935258001043, "count": 1002052, "self": 1481.5759796009006, "children": { "SubprocessEnvManager._take_step": { "total": 2087.161718399625, "count": 1002052, "self": 25.33664059985449, "children": { "TorchPolicy.evaluate": { "total": 2061.8250777997705, "count": 1002052, "self": 2061.8250777997705 } } }, "workers": { "total": 5.655827799578606, "count": 1002052, "self": 0.0, "children": { "worker_root": { "total": 3583.0113568997517, "count": 1002052, "is_parallel": true, "self": 2729.947583199875, "children": { "steps_from_proto": { "total": 0.0003031000000000006, "count": 1, "is_parallel": true, "self": 0.00012020000000001474, "children": { "_process_rank_one_or_two_observation": { "total": 0.00018289999999998585, "count": 2, "is_parallel": true, "self": 0.00018289999999998585 } } }, "UnityEnvironment.step": { "total": 853.0634705998764, "count": 1002052, "is_parallel": true, "self": 41.9990484997229, "children": { "UnityEnvironment._generate_step_input": { "total": 63.74244350002685, "count": 1002052, "is_parallel": true, "self": 63.74244350002685 }, "communicator.exchange": { "total": 631.3923290999431, "count": 1002052, "is_parallel": true, "self": 631.3923290999431 }, "steps_from_proto": { "total": 115.92964950018347, "count": 1002052, "is_parallel": true, "self": 64.59104660025498, "children": { "_process_rank_one_or_two_observation": { "total": 51.33860289992849, "count": 2004104, "is_parallel": true, "self": 51.33860289992849 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.7200000204175012e-05, "count": 1, "self": 2.7200000204175012e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 3593.521905900063, "count": 105114, "is_parallel": true, "self": 4.607845200071097, "children": { "process_trajectory": { "total": 1840.9422937999918, "count": 105114, "is_parallel": true, "self": 1840.5389830999923, "children": { "RLTrainer._checkpoint": { "total": 0.40331069999948, "count": 16, "is_parallel": true, "self": 0.40331069999948 } } }, "_update_policy": { "total": 1747.9717669000001, "count": 600, "is_parallel": true, "self": 570.650521000043, "children": { "TorchPPOOptimizer.update": { "total": 1177.3212458999571, "count": 93600, "is_parallel": true, "self": 1177.3212458999571 } } } } } } } } }, "TrainerController._save_models": { "total": 0.024971300000288466, "count": 1, "self": 0.0045406000003822555, "children": { "RLTrainer._checkpoint": { "total": 0.02043069999990621, "count": 1, "self": 0.02043069999990621 } } } } } } }