{"id":"W2964278219","doi":"","title":"Thompson Sampling for Combinatorial Semi-Bandits.","year":2018,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Regret; Thompson sampling; Matroid; Oracle; Sampling (signal processing); Mathematics; Mathematical optimization; Independence (probability theory); Computer science; Combinatorics; Statistics","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":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002113881,0.0001987094,0.0002655023,0.0003421449,0.0004525436,0.0005660841,0.001254632,0.00009751853,0.003815005],"category_scores_gemma":[0.009208562,0.0001597294,0.0001263966,0.0003219855,0.0001887537,0.0003482532,0.0002205131,0.0005565715,0.0008005794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001156936,"about_ca_system_score_gemma":0.0001129099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002740748,"about_ca_topic_score_gemma":0.00002630027,"domain_scores_codex":[0.9963433,0.0001848431,0.0005057901,0.0006658003,0.001917236,0.0003830658],"domain_scores_gemma":[0.9956352,0.001881902,0.000279973,0.0003098725,0.001761424,0.0001316778],"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":[0.00301212,0.0003969056,0.01931644,0.00001495918,0.0002164804,0.00002651023,0.001865699,0.01281339,0.009623867,0.4660295,0.005327412,0.4813567],"study_design_scores_gemma":[0.001792186,0.0008651336,0.001680142,0.0000543652,0.000005380748,0.000009800691,0.0003037155,0.5374383,0.002210197,0.1996202,0.2556994,0.0003211928],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0388727,0.00005643524,0.876223,0.007860162,0.009188243,0.0006977632,0.0001550353,0.0002613452,0.06668529],"genre_scores_gemma":[0.9862724,0.00001403295,0.003384513,0.0001599853,0.001883771,0.00003815724,0.00006253165,0.00002628151,0.008158306],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9473997,"threshold_uncertainty_score":0.9999774,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2722630354409833,"score_gpt":0.5115727209194741,"score_spread":0.2393096854784908,"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."}}