{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004043092,0.002874101,0.00411194,0.001001208,0.0008940903,0.003124847,0.002599478,0.003549905,0.00499654],"category_scores_gemma":[0.01791564,0.001250066,0.001445401,0.001489424,0.002327514,0.003655832,0.002702119,0.003669628,0.001090113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00185789,"about_ca_system_score_gemma":0.001237818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004075886,"about_ca_topic_score_gemma":0.003937348,"domain_scores_codex":[0.996253,0.001801887,0.0001738286,0.0008987352,0.0004207453,0.0004516354],"domain_scores_gemma":[0.9856469,0.01100053,0.001524853,0.0007587839,0.0005427259,0.0005261911],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004506129,0.0001539501,0.001342839,0.0002772719,0.0001491485,0.0001519984,0.00008571783,0.9167882,0.0005399465,0.06296613,0.002144656,0.01494963],"study_design_scores_gemma":[0.00003307086,0.00006225899,0.0001281324,0.00002670605,0.00002029145,0.00001656197,0.00001309289,0.9772296,0.0001283587,0.02181174,0.0005194857,0.00001086111],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06995278,0.006140204,0.9068397,0.002240302,0.0003125595,0.0002665212,0.0008018083,0.001032833,0.0124134],"genre_scores_gemma":[0.8961424,0.001797979,0.0923494,0.0008404812,0.000470331,0.0004366832,0.0007244437,0.0001217503,0.00711659],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00499654,"threshold_uncertainty_score":0.02138215,"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."}}