{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002781152,0.0001785817,0.0003802846,0.00008610889,0.0001929222,0.00006345574,0.0009594376,0.00002639783,0.000009883095],"category_scores_gemma":[0.00009584519,0.0001468208,0.0000464944,0.0002254236,0.0002089096,0.0002741622,0.0006057485,0.0001466398,0.000004906896],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007571077,"about_ca_system_score_gemma":0.0001051827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003004917,"about_ca_topic_score_gemma":0.000001344789,"domain_scores_codex":[0.9984453,0.0001720573,0.0002769168,0.000393401,0.0004322759,0.0002800731],"domain_scores_gemma":[0.9983096,0.0004817165,0.0002714187,0.0007285756,0.000117653,0.00009109327],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006214969,0.0009697709,0.0006994579,0.0002146216,0.001669865,0.000137794,0.01742964,0.3613494,0.003883391,0.5592153,0.001675407,0.05213385],"study_design_scores_gemma":[0.001545397,0.0004696646,0.0003879746,0.00002411295,0.00003868133,0.00002999041,0.0002413564,0.9963269,0.00002824985,0.000640495,0.00008667986,0.0001804691],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01791653,0.0001828049,0.9796624,0.0004390115,0.00002725383,0.0008306293,0.0002580978,0.0002513204,0.0004319955],"genre_scores_gemma":[0.9112527,0.000001036789,0.08808421,0.00005684419,0.000008509615,0.0004587302,0.000006124767,0.0000149729,0.0001169248],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8933361,"threshold_uncertainty_score":0.5987177,"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."}}