{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 1.0538036823272705, "min": 0.8161932826042175, "max": 1.0959194898605347, "count": 200 }, "Agent.Policy.Entropy.sum": { "value": 42152.1484375, "min": 32641.201171875, "max": 43915.6875, "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": 9.070965766906738, "min": 0.40659329295158386, "max": 9.580119132995605, "count": 200 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 217.7031707763672, "min": 9.758238792419434, "max": 229.92286682128906, "count": 200 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.04760897559130431, "min": 0.04352403412370237, "max": 0.05461486716607367, "count": 200 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.14282692677391293, "min": 0.10052567585807992, "max": 0.16384460149822103, "count": 200 }, "Agent.Losses.ValueLoss.mean": { "value": 0.24837617975075746, "min": 0.06441270624377972, "max": 1.6263256006253262, "count": 200 }, "Agent.Losses.ValueLoss.sum": { "value": 0.7451285392522724, "min": 0.19323811873133914, "max": 3.2526512012506523, "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": 4535.950012207031, "min": 109.12000713031739, "max": 4682.008117675781, "count": 200 }, "Agent.WindFarmControl.IndividualPerformance.sum": { "value": 36287.60009765625, "min": 872.9600570425391, "max": 37456.06494140625, "count": 200 }, "Agent.Environment.CumulativeReward.mean": { "value": 4534.995567321777, "min": 183.15793666518283, "max": 4664.359016418457, "count": 200 }, "Agent.Environment.CumulativeReward.sum": { "value": 36279.96453857422, "min": 1465.2634933214626, "max": 37314.872131347656, "count": 200 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 4534.995567321777, "min": 183.15793666518283, "max": 4664.359016418457, "count": 200 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 36279.96453857422, "min": 1465.2634933214626, "max": 37314.872131347656, "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": "1715265317", "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_6_task_0_run_id_1_train.yaml --run-id=WindFarmControl/train/WindFarmControl_pattern_6_task_0_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": "1715269260" }, "total": 3943.4078246000004, "count": 1, "self": 0.16108900000017456, "children": { "run_training.setup": { "total": 0.04457129999999998, "count": 1, "self": 0.04457129999999998 }, "TrainerController.start_learning": { "total": 3943.2021643000003, "count": 1, "self": 10.747027800163323, "children": { "TrainerController._reset_env": { "total": 1.6132256999999999, "count": 1, "self": 1.6132256999999999 }, "TrainerController.advance": { "total": 3930.814697499837, "count": 1002052, "self": 10.428872899525231, "children": { "env_step": { "total": 3920.385824600312, "count": 1002052, "self": 1712.4296051002211, "children": { "SubprocessEnvManager._take_step": { "total": 2202.2326369000148, "count": 1002052, "self": 26.523862099877533, "children": { "TorchPolicy.evaluate": { "total": 2175.7087748001372, "count": 1002052, "self": 2175.7087748001372 } } }, "workers": { "total": 5.723582600075961, "count": 1002052, "self": 0.0, "children": { "worker_root": { "total": 3926.235519199897, "count": 1002052, "is_parallel": true, "self": 2889.4922947998657, "children": { "steps_from_proto": { "total": 0.00024530000000000385, "count": 1, "is_parallel": true, "self": 0.00011580000000011026, "children": { "_process_rank_one_or_two_observation": { "total": 0.0001294999999998936, "count": 2, "is_parallel": true, "self": 0.0001294999999998936 } } }, "UnityEnvironment.step": { "total": 1036.7429791000313, "count": 1002052, "is_parallel": true, "self": 55.44350770002029, "children": { "UnityEnvironment._generate_step_input": { "total": 88.42687889989358, "count": 1002052, "is_parallel": true, "self": 88.42687889989358 }, "communicator.exchange": { "total": 740.1925621001417, "count": 1002052, "is_parallel": true, "self": 740.1925621001417 }, "steps_from_proto": { "total": 152.6800303999758, "count": 1002052, "is_parallel": true, "self": 85.26830909995925, "children": { "_process_rank_one_or_two_observation": { "total": 67.41172130001655, "count": 2004104, "is_parallel": true, "self": 67.41172130001655 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.189999986512703e-05, "count": 1, "self": 2.189999986512703e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 3940.6640544999645, "count": 116636, "is_parallel": true, "self": 4.5521021999365985, "children": { "process_trajectory": { "total": 2043.5126325000251, "count": 116636, "is_parallel": true, "self": 2043.075050900024, "children": { "RLTrainer._checkpoint": { "total": 0.43758160000103885, "count": 16, "is_parallel": true, "self": 0.43758160000103885 } } }, "_update_policy": { "total": 1892.599319800003, "count": 600, "is_parallel": true, "self": 570.043004099949, "children": { "TorchPPOOptimizer.update": { "total": 1322.556315700054, "count": 93600, "is_parallel": true, "self": 1322.556315700054 } } } } } } } } }, "TrainerController._save_models": { "total": 0.027191399999992427, "count": 1, "self": 0.005660700000134966, "children": { "RLTrainer._checkpoint": { "total": 0.02153069999985746, "count": 1, "self": 0.02153069999985746 } } } } } } }