{"id":"W4226099433","doi":"10.1007/s00498-022-00323-4","title":"Logarithmic regret in online linear quadratic control using Riccati updates","year":2022,"lang":"en","type":"article","venue":"Mathematics of Control Signals and Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Regret; Logarithm; Sublinear function; Linear-quadratic regulator; Mathematics; Controller (irrigation); Hindsight bias; Riccati equation; Linear-quadratic-Gaussian control; Mathematical optimization; Optimal control; Control (management); Computer science; Control theory (sociology); Discrete mathematics; Statistics; Artificial intelligence; Differential equation","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":[0.006534762,0.0002156851,0.001158612,0.0005435919,0.0002118,0.0001399506,0.0007058544,0.00006814316,0.0001541276],"category_scores_gemma":[0.002019071,0.0001613175,0.0001133679,0.0007333024,0.0001444051,0.0002046387,0.0001616857,0.0003091049,0.000009139932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008997912,"about_ca_system_score_gemma":0.0001289672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001449281,"about_ca_topic_score_gemma":0.00002389286,"domain_scores_codex":[0.9946733,0.0008054863,0.001725505,0.000415985,0.00197874,0.0004010479],"domain_scores_gemma":[0.9940018,0.004092578,0.0008180125,0.0005632514,0.0004051271,0.0001192431],"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":[0.0003930215,0.001712768,0.007013188,0.0005972928,0.0002896136,0.0001588547,0.003819661,0.9536222,0.02235168,0.003467003,0.0005305188,0.00604421],"study_design_scores_gemma":[0.002474718,0.0001973562,0.0001499736,0.00007590037,0.00002296065,0.00003788716,0.004188629,0.9788604,0.00004342887,0.01334585,0.0004314604,0.000171384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4355458,0.004578216,0.5559345,0.0004960448,0.0003817344,0.002277327,0.0005721189,0.00003655236,0.0001777537],"genre_scores_gemma":[0.9974689,0.00002389857,0.002056443,0.00004528699,0.00007704875,0.00007765875,0.000005670937,0.00002444342,0.0002206727],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5619231,"threshold_uncertainty_score":0.6578335,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1352701255915641,"score_gpt":0.4094376742189131,"score_spread":0.2741675486273489,"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."}}