{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00267346,0.0007049993,0.0009790629,0.0005233223,0.0003179786,0.0009616118,0.0006848638,0.0009971362,0.0005532127],"category_scores_gemma":[0.00371927,0.0003509038,0.0004589864,0.0005844657,0.001192375,0.0008316241,0.0005868652,0.001008213,0.0001034446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008413225,"about_ca_system_score_gemma":0.0009829478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003746431,"about_ca_topic_score_gemma":0.001698975,"domain_scores_codex":[0.9991282,0.000461612,0.00004075035,0.00007741978,0.0002188943,0.00007318928],"domain_scores_gemma":[0.9985718,0.0009997556,0.000130413,0.00006153787,0.0001991649,0.00003726052],"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":[0.00004466507,0.00003278085,0.000401058,0.00005985243,0.00005111429,0.00002807732,0.00003115004,0.9605875,0.0007466871,0.01089077,0.00017459,0.02695184],"study_design_scores_gemma":[0.000004297654,0.00003715908,0.00007284128,0.000004015665,0.000004184329,0.000006121371,0.000002566748,0.9972655,0.0002490598,0.00218728,0.0001644968,0.000002502874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02782281,0.001816803,0.9665845,0.0002996528,0.00006824667,0.00003824288,0.000007968437,0.0001732525,0.003188557],"genre_scores_gemma":[0.9193789,0.0008103973,0.07765776,0.00008182077,0.00006449541,0.00008527859,0.00001414918,0.00003906454,0.001868167],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003746431,"threshold_uncertainty_score":0.01413876,"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."}}