{"id":"W4308902993","doi":"10.1016/j.automatica.2022.110685","title":"Model-free optimal control of discrete-time systems with additive and multiplicative noises","year":2022,"lang":"en","type":"article","venue":"Automatica","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Algebraic Riccati equation; Multiplicative function; Reinforcement learning; Optimal control; Discrete time and continuous time; Mathematics; Stochastic control; Mathematical optimization; Convergence (economics); Iterative learning control; Markov decision process; Controller (irrigation); Control theory (sociology); Riccati equation; Computer science; Control (management); Markov process; Artificial intelligence","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":[0.0009935404,0.001390549,0.001287282,0.0005590799,0.0004948308,0.001656655,0.001032633,0.001315853,0.001225516],"category_scores_gemma":[0.003362476,0.0006727929,0.0007862569,0.0004791671,0.001384763,0.001013095,0.001491173,0.00118406,0.0001948597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009108389,"about_ca_system_score_gemma":0.001519003,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0071589,"about_ca_topic_score_gemma":0.004760858,"domain_scores_codex":[0.9992058,0.0002596502,0.00003044503,0.0001683323,0.0002042107,0.0001316256],"domain_scores_gemma":[0.9990981,0.000545238,0.0001233281,0.00004580542,0.0001444723,0.0000431952],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00010773,0.00004625567,0.0001386548,0.0001013783,0.00004824989,0.00004731874,0.00005549103,0.9625023,0.001847138,0.0259152,0.0004166041,0.008773654],"study_design_scores_gemma":[0.000009707629,0.00002654049,0.00008845133,0.000004802147,0.000008387379,0.000005681618,0.000005270246,0.9937742,0.0003227067,0.005567384,0.0001811746,0.000005740516],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03863682,0.0005982552,0.952022,0.0004742424,0.0001921443,0.00003160146,0.00006342922,0.0001762906,0.007805153],"genre_scores_gemma":[0.9814462,0.0003381002,0.01229118,0.00008321484,0.00005510798,0.0000751233,0.00006147427,0.00003653314,0.005613243],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0071589,"threshold_uncertainty_score":0.01423448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005472723485347404,"score_gpt":0.2031684351469034,"score_spread":0.197695711661556,"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."}}