{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000669462,0.0003689294,0.000443503,0.0003146008,0.0003560196,0.000264354,0.001476604,0.000125352,0.000008684463],"category_scores_gemma":[0.0001897995,0.0003539052,0.0001447945,0.0007816355,0.00007201308,0.0005577328,0.0002796763,0.0004680892,0.00004745953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002652114,"about_ca_system_score_gemma":0.0001684062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001020735,"about_ca_topic_score_gemma":0.00001985101,"domain_scores_codex":[0.9972062,0.000211319,0.0004408724,0.0009353316,0.0004666811,0.0007396347],"domain_scores_gemma":[0.9983289,0.0001869913,0.0001579583,0.0008458094,0.0002256913,0.0002545994],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004975452,0.000727143,0.00124768,0.00004907024,0.0004867335,0.00005554072,0.00458711,0.2994322,0.03303388,0.209008,0.00002824241,0.4508469],"study_design_scores_gemma":[0.001431256,0.0005113051,0.0004877559,0.00005341626,0.00003236538,0.000006061012,0.0004554652,0.9946445,0.00004657766,0.0002037786,0.001762164,0.0003653203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001150543,0.0001446171,0.9869556,0.001241985,0.0002838359,0.0007989517,0.000003694362,0.0005717949,0.008849001],"genre_scores_gemma":[0.5620399,0.000001921197,0.4348711,0.00149811,0.00009071458,0.00008660626,0.0000118404,0.00001510118,0.001384755],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6952124,"threshold_uncertainty_score":0.9998913,"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."}}