{"id":"W4416394014","doi":"10.1016/j.ifacol.2025.11.073","title":"An adaptive extremum-seeking control approach to reinforcement learning","year":2025,"lang":"en","type":"article","venue":"IFAC-PapersOnLine","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Reinforcement learning; Control theory (sociology); Adaptive control; Nonlinear system; Convergence (economics); Basis (linear algebra); Stability (learning theory); Parametrization (atmospheric modeling); Optimal 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":[0.001181174,0.0008374781,0.0009949887,0.0003783631,0.0003060864,0.0007189524,0.001223594,0.001064837,0.001410521],"category_scores_gemma":[0.001898466,0.000292552,0.0005221676,0.0003254166,0.001035018,0.0005671632,0.00090078,0.001237462,0.0001623867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007045195,"about_ca_system_score_gemma":0.0007030174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00234765,"about_ca_topic_score_gemma":0.001224064,"domain_scores_codex":[0.9995332,0.0002087557,0.00001708711,0.00008875688,0.0001104129,0.00004178516],"domain_scores_gemma":[0.9994563,0.0002906233,0.00007603665,0.00002575766,0.0001199704,0.00003130027],"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":[0.00004582785,0.00004835089,0.0002686277,0.0001046185,0.00005917255,0.00009875253,0.00008770985,0.9344872,0.002900173,0.03828453,0.0005067326,0.02310836],"study_design_scores_gemma":[0.000006406366,0.00003691823,0.00002558351,0.000004568666,0.000004119404,0.000008496037,0.000002856722,0.9967212,0.0001857654,0.002732407,0.000267834,0.000003759598],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007232996,0.0003013179,0.9901847,0.0001420422,0.00003761637,0.0000257407,0.00000718721,0.00005836492,0.002009969],"genre_scores_gemma":[0.903281,0.0004233984,0.09237069,0.0001457319,0.00007885989,0.0002103239,0.00002445709,0.00002396562,0.00344161],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00234765,"threshold_uncertainty_score":0.006246686,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01135421108328482,"score_gpt":0.2549083754554547,"score_spread":0.2435541643721699,"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."}}