{"id":"W4314947473","doi":"10.1109/cdc51059.2022.9992636","title":"Achieving Logarithmic Regret via Hints in Online Learning of Noisy LQR Systems","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 61st Conference on Decision and Control (CDC)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regret; Logarithm; Sublinear function; Matrix (chemical analysis); Computer science; Mathematical optimization; Limit (mathematics); Square root; Mathematics; Algorithm; Discrete mathematics; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.005638317,0.001917465,0.002097147,0.0006346627,0.0005726634,0.001822858,0.001697191,0.002185258,0.001566847],"category_scores_gemma":[0.0331175,0.0009216571,0.0005810834,0.0006285165,0.0029128,0.003233841,0.002248744,0.003110781,0.0004631396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001605032,"about_ca_system_score_gemma":0.001306584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003167576,"about_ca_topic_score_gemma":0.002146251,"domain_scores_codex":[0.9973023,0.00138795,0.0001192438,0.0003852031,0.0004991377,0.0003062199],"domain_scores_gemma":[0.9753106,0.02114847,0.001333713,0.0009616072,0.0008435438,0.0004021784],"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":[0.0002994059,0.00005339734,0.0004931063,0.00009192718,0.00002563729,0.00007199267,0.00006036614,0.9789333,0.0004982033,0.01102766,0.0004122003,0.008032789],"study_design_scores_gemma":[0.00001891348,0.00004143853,0.00006750506,0.000007608652,0.000004133605,0.000009226447,0.000005449453,0.9893283,0.0003220502,0.01012197,0.00006719739,0.000006139455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05328366,0.0006793823,0.941285,0.0009328501,0.00005204801,0.00005406246,0.00009492067,0.001055924,0.002562264],"genre_scores_gemma":[0.946075,0.0002992871,0.05119001,0.0003489167,0.00008210443,0.000118075,0.0001249957,0.0001303847,0.001631301],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005638317,"threshold_uncertainty_score":0.02981859,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08411755925804429,"score_gpt":0.385170558163397,"score_spread":0.3010529989053526,"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."}}