{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001104434,0.0008747848,0.0007174351,0.0004500302,0.0003757,0.0008113756,0.00104087,0.0006626529,0.001334119],"category_scores_gemma":[0.002784662,0.0003330428,0.0003974404,0.0002339658,0.0006675823,0.0004436175,0.0005529446,0.001105989,0.0003637771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005697396,"about_ca_system_score_gemma":0.00083945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003097446,"about_ca_topic_score_gemma":0.002380736,"domain_scores_codex":[0.9995518,0.0001160604,0.00003000946,0.00008801147,0.0001612778,0.00005267518],"domain_scores_gemma":[0.9989346,0.0005426595,0.0001659635,0.00008373444,0.0002379989,0.00003494998],"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":[0.00008828112,0.0001112609,0.0004085123,0.0001025892,0.00004357801,0.00005929893,0.00008701736,0.9203445,0.008566973,0.003050801,0.0004615565,0.0666756],"study_design_scores_gemma":[0.00001356085,0.00003958946,0.00006837909,0.000004234353,0.000004366507,0.00000992665,0.000002414761,0.997672,0.001640929,0.0002934514,0.000247133,0.000003991699],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02733541,0.0001988068,0.9666773,0.00008513471,0.00004847268,0.0001281915,0.00001428571,0.001496167,0.004016226],"genre_scores_gemma":[0.8925443,0.0000977997,0.1052623,0.00006274816,0.00001975248,0.0002782079,0.00002877662,0.00005839029,0.001647734],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003097446,"threshold_uncertainty_score":0.006158829,"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."}}