{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001383113,0.0001327017,0.0002225027,0.0002262412,0.0004409614,0.0004474655,0.0009377992,0.0000939779,0.00003341326],"category_scores_gemma":[0.00118685,0.0001077161,0.00006819626,0.001154638,0.00008480126,0.0004715982,0.0001245445,0.000292483,0.00003767866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004381377,"about_ca_system_score_gemma":0.0001426037,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001526928,"about_ca_topic_score_gemma":0.00004704089,"domain_scores_codex":[0.99747,0.0001251232,0.000627112,0.0003528023,0.001033331,0.0003916454],"domain_scores_gemma":[0.9974988,0.0003739301,0.0000595847,0.0007713216,0.001149397,0.0001470211],"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":[0.0004252811,0.002236798,0.0000827004,0.0002497555,0.0001381366,0.0001048918,0.01266496,0.5055092,0.01374402,0.10164,0.01366183,0.3495424],"study_design_scores_gemma":[0.0006631888,0.000213821,0.0009707122,0.00006845814,0.000002828436,0.00001474714,0.0001338499,0.9821005,0.005838759,0.009717737,0.0001448405,0.0001304876],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2631129,0.0000599069,0.7320087,0.001652372,0.0002262038,0.0007336044,0.00003985196,0.000148263,0.002018206],"genre_scores_gemma":[0.8213294,0.00001441954,0.1782153,0.00002292387,0.00005811736,0.00001697903,0.00001761954,0.000006615153,0.0003186439],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5582165,"threshold_uncertainty_score":0.4392536,"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."}}