{"id":"W1733260092","doi":"10.1109/iccas.2010.5669655","title":"Dynamic tuning of PI-controllers based on model-free Reinforcement Learning methods","year":2010,"lang":"en","type":"article","venue":"ICCAS 2010","topic":"Iterative Learning Control Systems","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; PID controller; Control theory (sociology); Reinforcement; Control engineering; Artificial intelligence; Control (management); Engineering; Temperature control","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":[0.0009970446,0.0002610951,0.0004164189,0.0002568351,0.00009392607,0.00004576105,0.0003382736,0.0001822192,0.0001234376],"category_scores_gemma":[0.0004328051,0.0002522052,0.0001417845,0.0001446197,0.0000492002,0.0001198959,0.00003885812,0.001038584,0.00003805256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007161812,"about_ca_system_score_gemma":0.00003581807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003188288,"about_ca_topic_score_gemma":0.00003193778,"domain_scores_codex":[0.998548,0.0001439433,0.0004289837,0.0002285776,0.0002814315,0.0003690952],"domain_scores_gemma":[0.9986986,0.0003330476,0.0001404469,0.0006416478,0.00008917789,0.00009710971],"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":[0.00003117359,0.000007111099,0.0001208084,0.00003636678,0.00003615107,0.000002110662,0.0002832045,0.7578836,0.2385886,0.0002916206,0.0001364527,0.002582846],"study_design_scores_gemma":[0.001592779,0.000116209,0.0002220693,0.0000611436,0.00002299805,0.000001979975,0.00002602952,0.9930453,0.002601356,0.00007048149,0.002000396,0.0002393029],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0669449,0.00006271793,0.904731,0.0001512658,0.001479575,0.0004249288,0.000004403878,0.0004431582,0.02575799],"genre_scores_gemma":[0.9621999,0.000001559818,0.03559951,0.00005171189,0.00006421613,0.00004196602,0.000009824585,0.00007429502,0.001957002],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.895255,"threshold_uncertainty_score":0.999993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009195943566280266,"score_gpt":0.264833981451457,"score_spread":0.2556380378851767,"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."}}