{"id":"W4416128579","doi":"10.1002/ese3.70343","title":"Enhancing Hybrid Microgrid Dynamics Using an Agent‐Based Reinforcement Learning (RL) Framework","year":2025,"lang":"en","type":"article","venue":"Energy Science & Engineering","topic":"Microgrid Control and Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Microgrid; Reinforcement learning; Artificial neural network; Converters; Wind power; Hybrid power; Power (physics); Control theory (sociology); Hybrid system","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000345172,0.0002636116,0.0002114287,0.0005314708,0.0002932296,0.0002300706,0.0004040244,0.0000747789,0.00002246116],"category_scores_gemma":[0.00009287842,0.0003032458,0.00006731477,0.001017665,0.00006104341,0.0005150239,0.00007077612,0.0002826244,0.000002721702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005439843,"about_ca_system_score_gemma":0.0001127333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005414955,"about_ca_topic_score_gemma":0.00001471974,"domain_scores_codex":[0.9983867,0.00001261756,0.0003350584,0.000358094,0.0002737597,0.0006337304],"domain_scores_gemma":[0.9993594,0.00004651234,0.00004304153,0.0003227291,0.00008113803,0.000147128],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002110311,0.000007185833,0.00004286712,0.000009661934,0.00001133931,0.000004160931,0.00004188186,0.8717455,0.1121295,0.01348732,0.000002203878,0.002516309],"study_design_scores_gemma":[0.0001464813,0.00001703832,0.00003429624,0.000131539,0.00001550514,0.000003116826,0.00003376591,0.8745021,0.1199962,0.00002233354,0.004830744,0.0002668389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08415891,0.0007655296,0.9131034,0.0000139712,0.001048718,0.00006945691,0.000001185634,0.0005690938,0.0002697223],"genre_scores_gemma":[0.9622059,0.00007649738,0.0373987,0.00008090776,0.0001132515,0.0000146524,0.00002039494,0.00003865419,0.0000510488],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.878047,"threshold_uncertainty_score":0.9999419,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004096288242979232,"score_gpt":0.2018605726202398,"score_spread":0.1977642843772605,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}