{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007608545,0.00297251,0.004515287,0.001244626,0.0008917429,0.004898388,0.003233871,0.005656354,0.008723812],"category_scores_gemma":[0.02364395,0.001474137,0.001723929,0.001988665,0.002946409,0.003443465,0.00223937,0.004219184,0.001662008],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002793477,"about_ca_system_score_gemma":0.00186046,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004811341,"about_ca_topic_score_gemma":0.002622425,"domain_scores_codex":[0.9943896,0.00261189,0.0003345935,0.001207378,0.0007679558,0.0006886446],"domain_scores_gemma":[0.9790853,0.01671571,0.002102536,0.0007310982,0.0009920828,0.0003732542],"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":[0.0001645413,0.00007961082,0.0005363059,0.0001667429,0.0001072336,0.0001737753,0.00007453511,0.8656985,0.0004680108,0.1181354,0.001709201,0.0126861],"study_design_scores_gemma":[0.00002934363,0.00003186399,0.00009695516,0.00002354811,0.00001907842,0.00002197285,0.00001759824,0.9519767,0.0001737521,0.04699599,0.0005962992,0.00001681903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01345697,0.001288051,0.9745821,0.001133578,0.0001122169,0.0001690388,0.0004297222,0.0003012716,0.00852709],"genre_scores_gemma":[0.8114837,0.002597184,0.1618967,0.0009412997,0.0003819363,0.000884904,0.0008787171,0.0002267878,0.02070879],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008723812,"threshold_uncertainty_score":0.04023832,"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."}}