{"id":"W7123338223","doi":"10.1109/cdc57313.2025.11312866","title":"Stochastic Reinforcement Learning with Stability Guarantees for Control of Unknown Nonlinear Systems","year":2025,"lang":"","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Convergence (economics); Stability (learning theory); Nonlinear system; Representation (politics); Control theory (sociology); Controller (irrigation); Control (management); Artificial neural network","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":[0.001955348,0.0005594899,0.001222032,0.0002777326,0.0003673234,0.0002940221,0.001241702,0.0001811293,0.00001637625],"category_scores_gemma":[0.0006988355,0.0004542466,0.0002838573,0.0007769697,0.0005081794,0.0004011864,0.0002886123,0.0004157611,0.000004905007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003106034,"about_ca_system_score_gemma":0.001080447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003099151,"about_ca_topic_score_gemma":0.00006506122,"domain_scores_codex":[0.9955465,0.0003094008,0.001433641,0.001081048,0.0006732303,0.0009562501],"domain_scores_gemma":[0.9945561,0.001654944,0.0007779575,0.001136372,0.001727912,0.0001466851],"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":[0.001493533,0.0003749576,0.0005551099,0.001012256,0.0009166552,0.0000030704,0.0006570102,0.7623119,0.0003927572,0.2092485,0.00001315453,0.02302102],"study_design_scores_gemma":[0.006924737,0.00265121,0.00007602813,0.0007259264,0.0003036584,0.000003589427,0.0005193201,0.9870769,0.0001371835,0.0001350631,0.001033073,0.0004133455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001983525,0.001077797,0.9895976,0.0004962015,0.0007743262,0.005208578,0.0000195855,0.0001732496,0.0006690973],"genre_scores_gemma":[0.9810605,0.000005012098,0.01535332,0.00009081487,0.00006747244,0.0003803346,0.000007776053,0.00002483799,0.003009922],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.979077,"threshold_uncertainty_score":0.9997909,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0109348647064978,"score_gpt":0.2436693270617748,"score_spread":0.232734462355277,"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."}}