{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 0.9746847748756409, "min": 0.9654285907745361, "max": 1.0961092710494995, "count": 200 }, "Agent.Policy.Entropy.sum": { "value": 38987.390625, "min": 38605.11328125, "max": 43905.75390625, "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": 9.22942066192627, "min": -0.15079741179943085, "max": 9.799691200256348, "count": 200 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 221.50608825683594, "min": -3.61913800239563, "max": 235.19259643554688, "count": 200 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.05077317207571238, "min": 0.045420708714306195, "max": 0.05415981267796024, "count": 200 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.15231951622713713, "min": 0.09837574745567206, "max": 0.1624794380338807, "count": 200 }, "Agent.Losses.ValueLoss.mean": { "value": 0.2318491361220367, "min": 0.08245199396125308, "max": 1.626629980203385, "count": 200 }, "Agent.Losses.ValueLoss.sum": { "value": 0.6955474083661101, "min": 0.24735598188375924, "max": 3.25325996040677, "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": 4602.086669921875, "min": 350.05101573467255, "max": 4690.645080566406, "count": 200 }, "Agent.WindFarmControl.IndividualPerformance.sum": { "value": 36816.693359375, "min": 2800.4081258773804, "max": 37525.16064453125, "count": 200 }, "Agent.Environment.CumulativeReward.mean": { "value": 4597.064208984375, "min": 556.156599574346, "max": 4678.725608825684, "count": 200 }, "Agent.Environment.CumulativeReward.sum": { "value": 36776.513671875, "min": 4449.252796594768, "max": 37429.80487060547, "count": 200 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 4597.064208984375, "min": 556.156599574346, "max": 4678.725608825684, "count": 200 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 36776.513671875, "min": 4449.252796594768, "max": 37429.80487060547, "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": "1715289188", "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_0_run_id_2_train.yaml --run-id=WindFarmControl/train/WindFarmControl_pattern_0_task_0_run_id_2_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": "1715292998" }, "total": 3810.2279147, "count": 1, "self": 0.1470408000000134, "children": { "run_training.setup": { "total": 0.04447270000000003, "count": 1, "self": 0.04447270000000003 }, "TrainerController.start_learning": { "total": 3810.0364012, "count": 1, "self": 10.68699860020888, "children": { "TrainerController._reset_env": { "total": 1.6128947, "count": 1, "self": 1.6128947 }, "TrainerController.advance": { "total": 3797.709553799791, "count": 1002054, "self": 10.49146689985173, "children": { "env_step": { "total": 3787.2180868999394, "count": 1002054, "self": 1600.823650799819, "children": { "SubprocessEnvManager._take_step": { "total": 2180.4120274001375, "count": 1002054, "self": 26.511826300127268, "children": { "TorchPolicy.evaluate": { "total": 2153.9002011000102, "count": 1002054, "self": 2153.9002011000102 } } }, "workers": { "total": 5.982408699982956, "count": 1002054, "self": 0.0, "children": { "worker_root": { "total": 3795.3262546001315, "count": 1002054, "is_parallel": true, "self": 2848.4071449002718, "children": { "steps_from_proto": { "total": 0.00023459999999997372, "count": 1, "is_parallel": true, "self": 0.00010929999999997886, "children": { "_process_rank_one_or_two_observation": { "total": 0.00012529999999999486, "count": 2, "is_parallel": true, "self": 0.00012529999999999486 } } }, "UnityEnvironment.step": { "total": 946.9188750998599, "count": 1002054, "is_parallel": true, "self": 52.065283599650115, "children": { "UnityEnvironment._generate_step_input": { "total": 86.63877530011705, "count": 1002054, "is_parallel": true, "self": 86.63877530011705 }, "communicator.exchange": { "total": 665.8185351999875, "count": 1002054, "is_parallel": true, "self": 665.8185351999875 }, "steps_from_proto": { "total": 142.39628100010523, "count": 1002054, "is_parallel": true, "self": 81.08001270021317, "children": { "_process_rank_one_or_two_observation": { "total": 61.31626829989206, "count": 2004108, "is_parallel": true, "self": 61.31626829989206 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.080000012938399e-05, "count": 1, "self": 2.080000012938399e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 3807.616727500033, "count": 108961, "is_parallel": true, "self": 4.302358899984483, "children": { "process_trajectory": { "total": 1921.866013500047, "count": 108961, "is_parallel": true, "self": 1921.4277310000475, "children": { "RLTrainer._checkpoint": { "total": 0.43828249999967284, "count": 16, "is_parallel": true, "self": 0.43828249999967284 } } }, "_update_policy": { "total": 1881.4483551000017, "count": 600, "is_parallel": true, "self": 571.8847141000313, "children": { "TorchPPOOptimizer.update": { "total": 1309.5636409999704, "count": 93600, "is_parallel": true, "self": 1309.5636409999704 } } } } } } } } }, "TrainerController._save_models": { "total": 0.02693329999965499, "count": 1, "self": 0.005950299999312847, "children": { "RLTrainer._checkpoint": { "total": 0.020983000000342145, "count": 1, "self": 0.020983000000342145 } } } } } } }