{"id":"W2912832158","doi":"10.1109/tcyb.2018.2890046","title":"Optimal Output Regulation of Linear Discrete-Time Systems With Unknown Dynamics Using Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":132,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; Higher Education Discipline Innovation Project; Northeastern University; National Natural Science Foundation of China","keywords":"Reinforcement learning; Optimization problem; Optimal control; Mathematical optimization; Control theory (sociology); Computer science; Discrete time and continuous time; Discrete optimization; Noise (video); System dynamics; Control (management); Mathematics; 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":[0.000220691,0.000223811,0.0002988975,0.0001746528,0.0001271518,0.00007851372,0.0003880321,0.0001074578,0.000008389435],"category_scores_gemma":[0.000004187186,0.0002048854,0.00009157255,0.0003518274,0.00007821956,0.0002824537,0.000006892122,0.0002989393,0.00004149703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002589643,"about_ca_system_score_gemma":0.00009505002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001114432,"about_ca_topic_score_gemma":0.0000104207,"domain_scores_codex":[0.9983357,0.00009001292,0.0003924385,0.0003737748,0.0004980206,0.0003100441],"domain_scores_gemma":[0.9987833,0.0001119133,0.0002715271,0.0005453208,0.0002115954,0.00007628662],"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":[0.00004886964,0.00004748647,0.00004815929,0.00002585362,0.00007060875,0.000001602188,0.000267196,0.9925767,0.0009848162,0.002200963,6.952109e-7,0.003727091],"study_design_scores_gemma":[0.0006707042,0.0006743278,0.00005939414,0.0001312147,0.00005210214,0.00001616909,0.00005753947,0.9970777,0.0008823477,0.000009718563,0.0001352555,0.0002335321],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06811907,0.00001433037,0.930522,0.00003264903,0.0003056104,0.0005023485,0.00000413216,0.0001360873,0.0003637435],"genre_scores_gemma":[0.9428082,0.000002904211,0.053389,0.000009933794,0.00002023783,0.00001120303,0.000005184946,0.0000292577,0.003724102],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.877133,"threshold_uncertainty_score":0.8354985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009236036983152505,"score_gpt":0.2210814403115666,"score_spread":0.2118454033284141,"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."}}