{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006088711,0.0004801266,0.001044877,0.0009301783,0.00180149,0.0008499036,0.001500248,0.00017326,0.001166684],"category_scores_gemma":[0.003411404,0.0003900482,0.0003237433,0.001167547,0.0001984352,0.0002809656,0.0002864593,0.00117139,0.0001292543],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002095053,"about_ca_system_score_gemma":0.0004438816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004018681,"about_ca_topic_score_gemma":0.00001860429,"domain_scores_codex":[0.991274,0.0009327751,0.001245629,0.001622129,0.004014019,0.0009114338],"domain_scores_gemma":[0.9887778,0.00812705,0.0005478251,0.0009991669,0.001091915,0.0004562072],"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":[0.001405009,0.0002083052,0.00005815445,0.000008736198,0.00004136377,0.00003595213,0.0001296215,0.2419979,0.0007401182,0.001557965,0.001653434,0.7521634],"study_design_scores_gemma":[0.005867977,0.001263211,0.0001101629,0.00003638145,0.00002149529,0.00001588425,0.0009990607,0.8766766,0.0000719495,0.006056639,0.1084645,0.0004162247],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007104216,0.0004876305,0.9870433,0.0008046731,0.001802342,0.00165205,0.0005219445,0.0001406272,0.0004431799],"genre_scores_gemma":[0.9804675,0.00007448302,0.009271104,0.0006436392,0.0004291197,0.001298381,0.00005698419,0.00008227506,0.007676538],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9777722,"threshold_uncertainty_score":0.9998552,"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."}}