{"id":"W1998039896","doi":"10.1287/moor.1080.0371","title":"Partially Observed Markov Decision Process Multiarmed Bandits—Structural Results","year":2009,"lang":"en","type":"article","venue":"Mathematics of Operations Research","topic":"Distributed Sensor Networks and Detection Algorithms","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Markov decision process; Mathematics; Monotone polygon; Mathematical optimization; Partially observable Markov decision process; Markov process; Exploit; Monotonic function; Markov chain; Scheduling (production processes); Computer science; Statistics","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":[0.003175688,0.001044429,0.001516531,0.0008318096,0.0009537921,0.002421685,0.001544639,0.001837307,0.004188333],"category_scores_gemma":[0.01417608,0.0008345696,0.0009576748,0.001072279,0.002463603,0.003633062,0.001849509,0.00308052,0.0007080167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001875415,"about_ca_system_score_gemma":0.00146544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001938869,"about_ca_topic_score_gemma":0.001501453,"domain_scores_codex":[0.9983494,0.0007455974,0.00005923864,0.0002450262,0.0003607933,0.0002398861],"domain_scores_gemma":[0.9912509,0.006656968,0.0008826642,0.0004806504,0.0004504632,0.0002784072],"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":[0.00007855062,0.00005189612,0.0005559467,0.00007147601,0.00002823785,0.00006929662,0.00008689754,0.5323331,0.0005898037,0.4546331,0.0006988066,0.01080287],"study_design_scores_gemma":[0.000009657303,0.00001637763,0.00006868214,0.00001123065,0.000004531837,0.00001160639,0.00001079202,0.8808936,0.0001906357,0.1184659,0.0003101918,0.000006702004],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02800952,0.0005262399,0.9628481,0.0007686306,0.00004532471,0.00004065028,0.00009444894,0.0001005442,0.007566546],"genre_scores_gemma":[0.8557331,0.001142602,0.1358689,0.000251946,0.0001308368,0.0003022398,0.0002507965,0.00009251461,0.006227074],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004188333,"threshold_uncertainty_score":0.01679486,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.083850938900528,"score_gpt":0.3832298800101856,"score_spread":0.2993789411096576,"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."}}