{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006262658,0.001752922,0.001956349,0.0008353637,0.0009905315,0.003138911,0.002848126,0.002332077,0.005086148],"category_scores_gemma":[0.03448705,0.0008251545,0.001066117,0.001123942,0.002679692,0.003705124,0.002134305,0.00453853,0.0007702297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003715884,"about_ca_system_score_gemma":0.002778605,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003164848,"about_ca_topic_score_gemma":0.002919307,"domain_scores_codex":[0.9972795,0.001235446,0.00008970468,0.0003938606,0.0006071026,0.0003943029],"domain_scores_gemma":[0.9700551,0.02480128,0.001869818,0.001520952,0.0008404811,0.0009123874],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004428278,0.0001674261,0.00105431,0.0001237854,0.0000848457,0.0001099913,0.0001423077,0.7868656,0.001585216,0.1829065,0.003356966,0.02316013],"study_design_scores_gemma":[0.00001909211,0.00003834487,0.0001273065,0.00001406645,0.000009513215,0.00001777325,0.00001216911,0.9539686,0.000384003,0.04514504,0.0002535439,0.00001053611],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06562682,0.0009926417,0.917113,0.001542477,0.0001326301,0.0001034739,0.0001916948,0.0006233411,0.01367398],"genre_scores_gemma":[0.8792983,0.0008725304,0.1113256,0.0005221107,0.0002306691,0.0002587755,0.0002875244,0.0002914123,0.006913028],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006262658,"threshold_uncertainty_score":0.03312051,"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."}}