{"id":"W1838526237","doi":"10.1287/mnsc.2015.2153","title":"Robust Multiarmed Bandit Problems","year":2015,"lang":"en","type":"article","venue":"Management Science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematical optimization; Computer science; Bellman equation; Robust optimization; Dynamic programming; Dynamic pricing; Decision maker; Multi-armed bandit; Regret; Mathematics; Operations research; 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01053293,0.0001567375,0.0001930507,0.000962803,0.0004094267,0.000818258,0.003322052,0.00002928693,0.0002836807],"category_scores_gemma":[0.002451563,0.0001113661,0.0000507324,0.004955589,0.0009855174,0.001536119,0.001417781,0.000150741,0.002990739],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002340501,"about_ca_system_score_gemma":0.0001143354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001755271,"about_ca_topic_score_gemma":0.00001669543,"domain_scores_codex":[0.9912472,0.00009126709,0.0004532227,0.001062702,0.006355248,0.0007903551],"domain_scores_gemma":[0.9973971,0.0002012936,0.0001412987,0.001165965,0.0005899898,0.000504365],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008320082,0.0005008272,0.01442609,0.00003265156,0.0000345935,0.0003077593,0.00265445,0.4468516,0.0005004461,0.01238126,0.1033533,0.4188738],"study_design_scores_gemma":[0.002785653,0.0002898595,0.03959691,0.00004416171,0.00001402479,0.00002056124,0.005940289,0.3617596,0.001288521,0.09879869,0.4886388,0.0008228597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02138115,0.000158393,0.7890342,0.003135924,0.00212113,0.00164524,0.000008173848,0.0002877404,0.1822281],"genre_scores_gemma":[0.9237496,0.00001686948,0.03585848,0.0002582208,0.0001205823,0.00008448456,0.00000172262,0.00001666217,0.03989341],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9023684,"threshold_uncertainty_score":0.9977856,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3788463044400635,"score_gpt":0.4460406049573264,"score_spread":0.06719430051726294,"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."}}