{"id":"W2963004847","doi":"","title":"Regret Analysis of the Finite-Horizon Gittins Index Strategy for Multi-Armed Bandits","year":2016,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Thompson sampling; Asymptotically optimal algorithm; Index (typography); Frequentist inference; Gaussian; Mathematical optimization; Computer science; Mathematics; Mathematical economics; Bayesian probability; Statistics; Artificial intelligence; Bayesian inference","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":[0.005132541,0.0002143145,0.0005271848,0.0006949424,0.0003150851,0.0001221389,0.001501172,0.000152001,0.001444912],"category_scores_gemma":[0.03011402,0.0001028315,0.0003662045,0.00175835,0.0005965302,0.0002201828,0.0002208341,0.0003834568,0.0001047312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006367914,"about_ca_system_score_gemma":0.0002685223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006299238,"about_ca_topic_score_gemma":0.00003672866,"domain_scores_codex":[0.9958889,0.001059342,0.000620124,0.0006786544,0.001290598,0.0004623496],"domain_scores_gemma":[0.9856378,0.01171986,0.0005593101,0.0009901285,0.0009646298,0.0001282036],"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":[0.0009838894,0.0001910095,0.02622584,0.00001150878,0.0005148713,0.000004701164,0.0008760566,0.04110095,0.003054271,0.05527896,0.0003487114,0.8714092],"study_design_scores_gemma":[0.005262834,0.002330934,0.2075582,0.0003654215,0.0004247942,0.000002146471,0.005722305,0.4752063,0.01167509,0.2747179,0.01569265,0.001041397],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0753321,0.0000376748,0.9213135,0.0005330324,0.0002418849,0.0004441826,0.00009442045,0.0000554321,0.001947833],"genre_scores_gemma":[0.9746224,0.00002971656,0.0003780579,0.00002814808,0.00005332951,0.00004372451,0.000004959138,0.00002018449,0.02481949],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9209354,"threshold_uncertainty_score":0.9994679,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2738514103519363,"score_gpt":0.459272651460563,"score_spread":0.1854212411086267,"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."}}