{"id":"W2964007796","doi":"","title":"{Tight Regret Bounds for Stochastic Combinatorial Semi-Bandits}","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":122,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Stochastic game; Upper and lower bounds; Combinatorics; Mathematics; Constant (computer programming); Combinatorial optimization; Discrete mathematics; Mathematical optimization; Computer science; Mathematical economics","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":[],"category_scores_codex":[0.003840966,0.0001933882,0.0003857032,0.0003195566,0.0002355452,0.0004365564,0.001111677,0.0001372981,0.0005143999],"category_scores_gemma":[0.01321719,0.0001303017,0.0001333852,0.0008715993,0.0002349067,0.0005691227,0.0002308026,0.0002089794,0.0008898574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001689214,"about_ca_system_score_gemma":0.0004290447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001940517,"about_ca_topic_score_gemma":0.00002488951,"domain_scores_codex":[0.9952238,0.0001320132,0.0005732274,0.000657925,0.002807823,0.0006052182],"domain_scores_gemma":[0.9943799,0.002688484,0.0001477588,0.0007933612,0.001478438,0.000511998],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008359877,0.0002571255,0.00030989,0.000007616881,0.00004828667,0.00002428881,0.0008265041,0.003415837,0.0001465249,0.05527543,0.919773,0.01907953],"study_design_scores_gemma":[0.003542617,0.0005542379,0.00007194551,0.000007296758,0.000007738437,0.00001498717,0.0006039245,0.0231155,0.000782885,0.7750989,0.1959137,0.0002862992],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003497857,0.0001330417,0.9798943,0.00133653,0.004442195,0.0007228196,0.00005235331,0.0001242856,0.009796612],"genre_scores_gemma":[0.9343542,0.000002419884,0.0107506,0.0002084042,0.001868597,0.0001773116,0.0000293766,0.00005262629,0.05255643],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9691437,"threshold_uncertainty_score":0.9998881,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2749472121146019,"score_gpt":0.4837384434734039,"score_spread":0.208791231358802,"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."}}