{"id":"W4413394567","doi":"10.23919/acc63710.2025.11108120","title":"Reinforcement Learning-Based Robust Model Predictive Control for Unknown Dynamics with Convergence and Stability Guarantees","year":2025,"lang":"en","type":"article","venue":"","topic":"Advanced Control Systems Optimization","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Convergence (economics); Computer science; Stability (learning theory); Model predictive control; Dynamics (music); Control theory (sociology); Control (management); Artificial intelligence; Machine learning; Psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0001191692,0.0001496059,0.0002084149,0.0000513028,0.00007353273,0.00002038439,0.00005883672,0.00005758173,0.000006357961],"category_scores_gemma":[0.00005194955,0.0001293209,0.00002543786,0.00009526189,0.00004576869,0.0001410478,0.000007828688,0.00008542902,3.116546e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002027377,"about_ca_system_score_gemma":0.00005054672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001117662,"about_ca_topic_score_gemma":0.0001218734,"domain_scores_codex":[0.9992998,0.00001500734,0.0002201012,0.0001935103,0.0000881408,0.0001834744],"domain_scores_gemma":[0.9994913,0.0001267543,0.00003840816,0.0001463755,0.0001621228,0.00003504495],"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":[0.0002305598,0.00000748267,0.00102141,0.0001521271,0.00006076708,1.246875e-7,0.00003463448,0.9942855,0.0001060613,0.003963449,0.00001219267,0.0001256434],"study_design_scores_gemma":[0.002426283,0.000114549,0.00005653305,0.00004637189,0.00004412312,1.847778e-7,0.00009398074,0.9966273,0.0003040619,0.0001259442,0.00003050261,0.00013011],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00259655,0.00007761119,0.9942202,0.00006539304,0.00005973175,0.001096956,0.00001725917,0.0003104238,0.001555869],"genre_scores_gemma":[0.9907079,0.000008966575,0.008568987,0.0000384632,0.000006858442,0.0002658067,0.00002496604,0.00001795788,0.0003600871],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9881114,"threshold_uncertainty_score":0.5273551,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005505492529647752,"score_gpt":0.1948078116055051,"score_spread":0.1893023190758573,"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."}}