{ "name": "root", "gauges": { "Agent.Policy.Entropy.mean": { "value": 0.8137915730476379, "min": 0.637660026550293, "max": 1.0954152345657349, "count": 200 }, "Agent.Policy.Entropy.sum": { "value": 32564.68359375, "min": 25511.501953125, "max": 43913.00390625, "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": 9.501697540283203, "min": 2.3389432430267334, "max": 9.816634178161621, "count": 200 }, "Agent.Policy.ExtrinsicValueEstimate.sum": { "value": 228.04074096679688, "min": 53.79569625854492, "max": 235.59921264648438, "count": 200 }, "Agent.Losses.PolicyLoss.mean": { "value": 0.04955274910441534, "min": 0.04477203898718543, "max": 0.05425709840785694, "count": 200 }, "Agent.Losses.PolicyLoss.sum": { "value": 0.148658247313246, "min": 0.10508813887524109, "max": 0.1627712952235708, "count": 200 }, "Agent.Losses.ValueLoss.mean": { "value": 0.009523128849058782, "min": 0.002932505446306239, "max": 3.669854566144447, "count": 200 }, "Agent.Losses.ValueLoss.sum": { "value": 0.028569386547176345, "min": 0.008797516338918718, "max": 10.79426912023198, "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": 4709.554931640625, "min": 1613.9169616699219, "max": 4892.742919921875, "count": 200 }, "Agent.WindFarmControl.AvoidDamageReward.sum": { "value": 37676.439453125, "min": 12911.335693359375, "max": 39141.943359375, "count": 200 }, "Agent.Environment.CumulativeReward.mean": { "value": 4726.380996704102, "min": 1765.8604888916016, "max": 4889.912284851074, "count": 200 }, "Agent.Environment.CumulativeReward.sum": { "value": 37811.04797363281, "min": 14126.883911132812, "max": 39119.298278808594, "count": 200 }, "Agent.Policy.ExtrinsicReward.mean": { "value": 4726.380996704102, "min": 1765.8604888916016, "max": 4889.912284851074, "count": 200 }, "Agent.Policy.ExtrinsicReward.sum": { "value": 37811.04797363281, "min": 14126.883911132812, "max": 39119.298278808594, "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": "1715171861", "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_2_task_1_run_id_0_train.yaml --run-id=WindFarmControl/train/WindFarmControl_pattern_2_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": "1715175583" }, "total": 3722.4016714, "count": 1, "self": 0.16862429999991946, "children": { "run_training.setup": { "total": 0.04616050000000005, "count": 1, "self": 0.04616050000000005 }, "TrainerController.start_learning": { "total": 3722.1868866, "count": 1, "self": 10.338838699990902, "children": { "TrainerController._reset_env": { "total": 1.619233, "count": 1, "self": 1.619233 }, "TrainerController.advance": { "total": 3710.201611300009, "count": 1002052, "self": 9.984701399917412, "children": { "env_step": { "total": 3700.2169099000917, "count": 1002052, "self": 1570.7886952000463, "children": { "SubprocessEnvManager._take_step": { "total": 2123.541292500062, "count": 1002052, "self": 26.114850999963437, "children": { "TorchPolicy.evaluate": { "total": 2097.4264415000985, "count": 1002052, "self": 2097.4264415000985 } } }, "workers": { "total": 5.88692219998325, "count": 1002052, "self": 0.0, "children": { "worker_root": { "total": 3708.38345829974, "count": 1002052, "is_parallel": true, "self": 2791.9995448996156, "children": { "steps_from_proto": { "total": 0.00025439999999998797, "count": 1, "is_parallel": true, "self": 0.00012109999999998511, "children": { "_process_rank_one_or_two_observation": { "total": 0.00013330000000000286, "count": 2, "is_parallel": true, "self": 0.00013330000000000286 } } }, "UnityEnvironment.step": { "total": 916.3836590001247, "count": 1002052, "is_parallel": true, "self": 45.25587559998246, "children": { "UnityEnvironment._generate_step_input": { "total": 68.96804120012082, "count": 1002052, "is_parallel": true, "self": 68.96804120012082 }, "communicator.exchange": { "total": 678.288798699905, "count": 1002052, "is_parallel": true, "self": 678.288798699905 }, "steps_from_proto": { "total": 123.87094350011637, "count": 1002052, "is_parallel": true, "self": 69.59912830032582, "children": { "_process_rank_one_or_two_observation": { "total": 54.27181519979056, "count": 2004104, "is_parallel": true, "self": 54.27181519979056 } } } } } } } } } } } } }, "trainer_threads": { "total": 2.210000002378365e-05, "count": 1, "self": 2.210000002378365e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 3719.5350889999454, "count": 109540, "is_parallel": true, "self": 4.837310999988404, "children": { "process_trajectory": { "total": 1914.3180694999548, "count": 109540, "is_parallel": true, "self": 1913.9023417999551, "children": { "RLTrainer._checkpoint": { "total": 0.4157276999997066, "count": 16, "is_parallel": true, "self": 0.4157276999997066 } } }, "_update_policy": { "total": 1800.379708500002, "count": 600, "is_parallel": true, "self": 575.0998159000906, "children": { "TorchPPOOptimizer.update": { "total": 1225.2798925999114, "count": 93600, "is_parallel": true, "self": 1225.2798925999114 } } } } } } } } }, "TrainerController._save_models": { "total": 0.027181500000097003, "count": 1, "self": 0.006050400000276568, "children": { "RLTrainer._checkpoint": { "total": 0.021131099999820435, "count": 1, "self": 0.021131099999820435 } } } } } } }