{"id":"W1917528016","doi":"","title":"Contextual Multi-Armed Bandits","year":2010,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":164,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; University of Toronto","funders":"","keywords":"Regret; Stochastic game; Multi-armed bandit; Context (archaeology); Metric space; Metric (unit); Computer science; Space (punctuation); Lipschitz continuity; Action (physics); Mathematics; Thompson sampling; Function (biology); Theoretical computer science; Mathematical optimization; Combinatorics; Discrete mathematics; Mathematical economics; Machine learning","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":[0.001967878,0.0001202634,0.0002078895,0.0002449387,0.0001729309,0.0002368206,0.001020035,0.0001000385,0.01170548],"category_scores_gemma":[0.009221193,0.00007516307,0.00006679836,0.0005934854,0.0002713644,0.0004266489,0.000223119,0.0004562532,0.006826063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001405422,"about_ca_system_score_gemma":0.00008828868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003040085,"about_ca_topic_score_gemma":0.0006122328,"domain_scores_codex":[0.9969215,0.00008151539,0.0003994549,0.0005077902,0.001678121,0.000411607],"domain_scores_gemma":[0.9966654,0.00171754,0.00007503064,0.0007537949,0.0005259534,0.0002622527],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001114112,0.000453923,0.01190749,0.000003496217,0.00003327284,0.0001244971,0.0007926279,0.000166334,0.07950337,0.006260823,0.1053999,0.7952429],"study_design_scores_gemma":[0.004980662,0.0002713888,0.1117887,0.000005497629,0.000008048734,0.0000874309,0.001840397,0.06486276,0.05215107,0.02941668,0.7337623,0.000825163],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2466856,0.0000485559,0.7191325,0.00203472,0.002783025,0.0005814793,0.00003381109,0.000262044,0.0284383],"genre_scores_gemma":[0.9191105,0.000002616151,0.01958762,0.0002179733,0.0002169906,0.00001580397,0.000002179026,0.00001301786,0.06083328],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7944177,"threshold_uncertainty_score":0.9991246,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2128862204345478,"score_gpt":0.5039623446227086,"score_spread":0.2910761241881608,"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."}}