{"id":"W2142560736","doi":"10.1109/pes.2009.5275575","title":"Near optimal control policy for controlling power system stabilizers using reinforcement learning","year":2009,"lang":"en","type":"article","venue":"","topic":"Power System Optimization and Stability","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Reinforcement learning; Control theory (sociology); Electric power system; Computer science; Stability (learning theory); Optimal control; Control (management); Power (physics); Q-learning; Control system; Mode (computer interface); Control engineering; Engineering; Mathematical optimization; Artificial intelligence; Machine learning; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0004655849,0.000225824,0.0003959789,0.0001034212,0.0002071978,0.0001395753,0.0001167919,0.0001024239,0.00005369053],"category_scores_gemma":[0.0001087139,0.0002141744,0.00015235,0.000177423,0.00002281354,0.0001885497,0.00000753254,0.0001202289,0.000009142716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004652958,"about_ca_system_score_gemma":0.00007420815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002567042,"about_ca_topic_score_gemma":0.000001254784,"domain_scores_codex":[0.9985389,0.00004953086,0.000536528,0.00021824,0.0001890272,0.0004677854],"domain_scores_gemma":[0.9993377,0.00009251011,0.00006955855,0.0002282538,0.0001342061,0.0001377104],"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":[0.00006384101,0.000008184194,0.000104112,0.00006585959,0.00004214361,7.713551e-7,0.0003095198,0.9942982,0.001059252,0.003920432,0.00003422281,0.000093415],"study_design_scores_gemma":[0.002197046,0.0001229699,0.00003603764,0.00003539383,0.00002239445,0.000005287168,0.0006086568,0.9937106,0.0002368532,0.000004146571,0.002787995,0.0002326713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02574972,0.00009798798,0.9602442,0.00007141864,0.0002491937,0.0009131019,0.000006667727,0.000794957,0.0118727],"genre_scores_gemma":[0.9910014,0.000001596706,0.008631095,0.0001339878,0.00005118511,0.00002444369,0.000005811197,0.00003150232,0.000118922],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9652517,"threshold_uncertainty_score":0.873378,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009399070216266415,"score_gpt":0.2363096859550622,"score_spread":0.2269106157387958,"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."}}