{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001490871,0.001169369,0.001326086,0.0005261432,0.0004967883,0.0009851439,0.001674598,0.001442421,0.003914734],"category_scores_gemma":[0.004061399,0.0005169484,0.0006613665,0.0009844853,0.00117841,0.001160475,0.001266268,0.002452473,0.001070422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001317855,"about_ca_system_score_gemma":0.001818795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004541216,"about_ca_topic_score_gemma":0.003575367,"domain_scores_codex":[0.9988404,0.0003769177,0.00005069876,0.0002714435,0.0003328242,0.0001278012],"domain_scores_gemma":[0.9985948,0.0008527531,0.0001348249,0.0001443611,0.0002232527,0.00004993928],"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":[0.0001312713,0.0001302435,0.000248772,0.0001309107,0.00005312303,0.00007388877,0.00009972144,0.8352742,0.002342844,0.06440178,0.003917895,0.09319548],"study_design_scores_gemma":[0.00001175192,0.00002363284,0.00002540233,0.000003846369,0.000002780244,0.0000102458,0.000002852083,0.9917269,0.0003156086,0.007282665,0.0005899846,0.000004295577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002820173,0.000213505,0.9929845,0.0001527037,0.00003705575,0.00005239871,0.00002595179,0.000370318,0.003343383],"genre_scores_gemma":[0.5628035,0.0004808826,0.4257374,0.0003462484,0.0001460983,0.0004928939,0.0002634285,0.0002561916,0.009473287],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004541216,"threshold_uncertainty_score":0.01309609,"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."}}