{"id":"W2142971854","doi":"10.1016/j.tcs.2009.01.016","title":"Exploration–exploitation tradeoff using variance estimates in multi-armed bandits","year":2009,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":566,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Variance (accounting); Stochastic game; Upper and lower bounds; Logarithm; Mathematical optimization; Computer science; Multi-armed bandit; Interval (graph theory); Mathematics; Mathematical economics; Machine learning; 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":[],"consensus_categories":[],"category_scores_codex":[0.004961226,0.0001914336,0.0003035006,0.0006995567,0.000421003,0.0007090758,0.001706918,0.00006412726,0.0001115561],"category_scores_gemma":[0.003552325,0.0001460072,0.00005309462,0.0037928,0.00208444,0.002605985,0.0002164279,0.0002780382,0.0001256053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001589192,"about_ca_system_score_gemma":0.0001891846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003252734,"about_ca_topic_score_gemma":0.000002405841,"domain_scores_codex":[0.9950902,0.0002316002,0.0006439523,0.0009440239,0.002380779,0.0007093957],"domain_scores_gemma":[0.9970365,0.001455825,0.0001241576,0.000624703,0.0004865764,0.0002722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001266582,0.0005823241,0.0006630308,0.000005642567,0.000003935347,0.0001123606,0.004644006,0.2623552,0.01075951,0.4575307,0.00007088121,0.2631457],"study_design_scores_gemma":[0.0003203843,0.0001068653,0.006729311,0.00001971784,0.000001105849,0.00001022147,0.00005283072,0.6571352,0.002933874,0.3325493,0.00001185038,0.0001293375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05795958,0.00002653591,0.9399899,0.001227842,0.0003182754,0.000268552,0.000002364089,0.00006324568,0.0001436943],"genre_scores_gemma":[0.7182841,0.000002867622,0.281456,0.0001675178,0.00006754688,0.000004698677,7.909129e-7,0.00000566004,0.00001083677],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6603246,"threshold_uncertainty_score":0.7680205,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2025090972907981,"score_gpt":0.4631392662511002,"score_spread":0.2606301689603022,"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."}}