{"id":"W4314946896","doi":"10.1109/cdc51059.2022.9992683","title":"A modified Thompson sampling-based learning algorithm for unknown linear 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":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Upper and lower bounds; Norm (philosophy); Algorithm; Thompson sampling; Combinatorics; Quadratic equation; Sampling (signal processing); Discrete mathematics; Mathematics; Computer science; Statistics; Mathematical analysis; Philosophy","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":[0.001580192,0.001124797,0.001827913,0.0005642105,0.0005442304,0.001080753,0.002572333,0.001984337,0.004347164],"category_scores_gemma":[0.006030429,0.0005939138,0.0007144575,0.0008401957,0.0009343281,0.00149213,0.001397706,0.002082581,0.0009436007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001200915,"about_ca_system_score_gemma":0.001720704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00896596,"about_ca_topic_score_gemma":0.008163284,"domain_scores_codex":[0.998875,0.0003591923,0.00005603254,0.0002472934,0.000350951,0.0001115273],"domain_scores_gemma":[0.9980162,0.001190632,0.0001407307,0.0001798591,0.000367472,0.0001049952],"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":[0.0001650563,0.00008818825,0.0005192155,0.00008466419,0.00006115208,0.0000636228,0.00006723997,0.84928,0.001582602,0.01440479,0.002738399,0.130945],"study_design_scores_gemma":[0.00001760869,0.00002337132,0.00003420511,0.000002644349,0.000002707562,0.000007863228,0.000001468901,0.9971362,0.0001880897,0.002256541,0.0003256364,0.000003673869],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004763065,0.0001541329,0.9931253,0.0001526293,0.00004750112,0.0000661988,0.00003635752,0.0003875293,0.00126724],"genre_scores_gemma":[0.3605354,0.000252397,0.6312827,0.0005343693,0.0002159389,0.0005156254,0.00040351,0.0003110979,0.005948965],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00896596,"threshold_uncertainty_score":0.01782757,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1707192101122855,"score_gpt":0.4198898418535795,"score_spread":0.249170631741294,"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."}}