{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005406641,0.0003487864,0.001060791,0.001302463,0.0005098413,0.0002871174,0.001481784,0.000136287,0.001534446],"category_scores_gemma":[0.003693975,0.0002853943,0.0001645717,0.001515396,0.0002252292,0.0003477023,0.000539683,0.001508894,0.0000895908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002102586,"about_ca_system_score_gemma":0.0002052763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002077471,"about_ca_topic_score_gemma":0.0001486654,"domain_scores_codex":[0.9915338,0.00140848,0.001484586,0.001170082,0.003764625,0.0006384285],"domain_scores_gemma":[0.9933896,0.004257276,0.0006397472,0.000895724,0.0005581902,0.0002594548],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001956023,0.0005031338,0.01071117,0.0000185297,0.00004640941,0.0002539381,0.0006585432,0.06262957,0.01040405,0.0007078907,0.0007962201,0.9113145],"study_design_scores_gemma":[0.007784816,0.001660728,0.02517434,0.0001931514,0.00002113908,0.0001052834,0.007718415,0.9342589,0.0001303256,0.005802156,0.01649155,0.0006592011],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8042223,0.0007430475,0.1899611,0.0008150369,0.001637179,0.001157828,0.0002793684,0.00007021719,0.001113848],"genre_scores_gemma":[0.9969504,0.0002464324,0.000320603,0.0001482558,0.00009609853,0.0001026211,0.0000149482,0.00003198434,0.002088618],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9106553,"threshold_uncertainty_score":0.9999598,"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."}}