{"id":"W4319459070","doi":"10.1109/access.2023.3243549","title":"A Comparative Study of Reinforcement Learning Algorithms for Distribution Network Reconfiguration With Deep Q-Learning-Based Action Sampling","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"Optimal Power Flow Distribution","field":"Engineering","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Electric System Operator","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Q-learning; Machine learning; Scalability; Control reconfiguration; Deep learning; Node (physics); Action (physics); Algorithm","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0002991678,0.0001756126,0.0002568109,0.00007956603,0.0002183132,0.00009271242,0.000127735,0.00006907526,0.00001306815],"category_scores_gemma":[0.00003400316,0.000177565,0.0000440042,0.0006789912,0.00001867704,0.0003954204,0.00001326016,0.000219826,0.000009714098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001801421,"about_ca_system_score_gemma":0.00001875944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003932949,"about_ca_topic_score_gemma":0.00009673744,"domain_scores_codex":[0.9988717,0.00005348679,0.0003363231,0.0002149557,0.0002254164,0.0002981414],"domain_scores_gemma":[0.9993005,0.0001564655,0.0001630389,0.0001269932,0.0002059782,0.00004698645],"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":[0.0001569474,0.00003729453,0.001274856,0.00007204036,0.00007656305,6.848326e-7,0.0003286618,0.9948316,0.0005644421,0.000007567548,0.0002307083,0.002418626],"study_design_scores_gemma":[0.00112073,0.0008828185,0.008303174,0.00006193446,0.00005930912,5.393169e-7,0.0008895821,0.9803048,0.007607854,0.00001307737,0.0005531213,0.0002030001],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4491351,0.0000074745,0.549665,0.00000568667,0.0002460491,0.0005969757,0.000009575884,0.0002964025,0.00003773086],"genre_scores_gemma":[0.9978315,0.000007093214,0.0002182315,0.000002412207,0.0001416289,0.0002784262,0.001477468,0.00002632404,0.00001696784],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5494468,"threshold_uncertainty_score":0.7240891,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0783149267901439,"score_gpt":0.3453562733269437,"score_spread":0.2670413465367998,"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."}}