{"id":"W4390757324","doi":"10.22190/fume231011044z","title":"Q-LEARNING, POLICY ITERATION AND ACTOR-CRITIC REINFORCEMENT LEARNING COMBINED WITH METAHEURISTIC ALGORITHMS IN SERVO SYSTEM CONTROL","year":2023,"lang":"en","type":"article","venue":"Facta Universitatis Series Mechanical Engineering","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii","keywords":"Reinforcement learning; Initialization; Computer science; Artificial neural network; Metaheuristic; Servomechanism; Algorithm; Mathematical optimization; Parametric statistics; Artificial intelligence; Machine learning; Mathematics; Control engineering; Engineering","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":[0.0002737512,0.000237157,0.0003354177,0.0004270031,0.0001569028,0.0001637893,0.0003110416,0.00007728941,0.000002473287],"category_scores_gemma":[0.0002326015,0.0002421123,0.00003907815,0.0008328305,0.00002497529,0.0008415338,0.000191505,0.0003489773,0.000009433037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002968205,"about_ca_system_score_gemma":0.00005877617,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008636097,"about_ca_topic_score_gemma":0.0000142118,"domain_scores_codex":[0.9985327,0.0001078897,0.0002359047,0.0003817099,0.0002831705,0.0004586286],"domain_scores_gemma":[0.9992022,0.0002836371,0.00008462312,0.000193338,0.00008753432,0.0001486619],"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":[0.0001485317,0.00001841087,0.0002260587,0.000245463,0.0001843388,0.0004792929,0.002196113,0.5689987,0.003349237,0.4198808,0.000005990868,0.004267027],"study_design_scores_gemma":[0.001612378,0.000856215,0.0007252793,0.0001267198,0.00002367599,0.0000266118,0.0009233522,0.9950506,0.00006455342,0.00005638882,0.0002723548,0.0002618621],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02208812,0.00001585583,0.9760763,0.0004677481,0.0001101696,0.0003567356,0.000002890345,0.0008212299,0.00006094581],"genre_scores_gemma":[0.9902481,0.00001033981,0.009354164,0.00001602285,0.00002213525,0.00001932893,0.00001947367,0.0000237781,0.000286662],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.96816,"threshold_uncertainty_score":0.9873052,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004149845208367344,"score_gpt":0.1843646881307481,"score_spread":0.1802148429223808,"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."}}