{"id":"W2995725691","doi":"10.48550/arxiv.1912.09451","title":"An Iterative Riccati Algorithm for Online Linear Quadratic Control","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Regret; Sublinear function; Linear-quadratic regulator; Logarithm; Mathematics; Mathematical optimization; Hindsight bias; Controller (irrigation); Linear-quadratic-Gaussian control; Optimal control; Linear system; Riccati equation; Smoothing; Sequence (biology); Computer science; Discrete mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001720392,0.0005644279,0.001068421,0.0008722047,0.0003106708,0.0003453533,0.003177165,0.0005183334,0.0002638465],"category_scores_gemma":[0.001284705,0.000514873,0.0004907564,0.001150468,0.0003332137,0.0008694046,0.0007770507,0.001058829,0.0005087605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003628729,"about_ca_system_score_gemma":0.0006673119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007387415,"about_ca_topic_score_gemma":0.00009314954,"domain_scores_codex":[0.9947598,0.0007012526,0.0007227077,0.002376012,0.0006944895,0.0007457662],"domain_scores_gemma":[0.9912169,0.002997594,0.0007117286,0.002478536,0.002162512,0.0004327179],"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":[0.0002558461,0.0005622343,0.0008103357,0.000041427,0.0002018057,0.0001505542,0.0003469366,0.9566661,0.00003160174,0.001301132,0.0008763406,0.03875567],"study_design_scores_gemma":[0.002098696,0.0004006269,0.0005158705,0.00004528333,0.00007596416,0.000002075603,0.0006241273,0.9390574,0.0000630157,0.0529129,0.003650583,0.0005534235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03058171,0.0001107012,0.964206,0.0001397911,0.001058212,0.001937644,0.001693147,0.0001210742,0.0001517104],"genre_scores_gemma":[0.9393577,0.0001093693,0.04402362,0.0002343263,0.0007282944,0.00001305382,0.000450142,0.00008773939,0.01499577],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9201824,"threshold_uncertainty_score":0.9997303,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2256580204766622,"score_gpt":0.3500820730083962,"score_spread":0.124424052531734,"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."}}