{"id":"W4286713636","doi":"10.48550/arxiv.2108.00892","title":"Indexability and Rollout Policy for Multi-State Partially Observable\\n Restless Bandits","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Observable; Monte Carlo method; State (computer science); Index (typography); Mathematical optimization; Computation; Computer science; Mathematical economics; Mathematics; Algorithm; Physics; 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":[0.003809125,0.001255282,0.001709885,0.0008013422,0.001011612,0.002449264,0.001765612,0.001885318,0.003725877],"category_scores_gemma":[0.01857448,0.0006379839,0.0008804695,0.0006341276,0.002410418,0.003077599,0.001637335,0.002594188,0.00042275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002505741,"about_ca_system_score_gemma":0.001804496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006810185,"about_ca_topic_score_gemma":0.003895015,"domain_scores_codex":[0.9978447,0.0007373973,0.000135859,0.0004376177,0.000299836,0.0005445472],"domain_scores_gemma":[0.9875132,0.008345574,0.001877835,0.0009199711,0.0006181824,0.0007251421],"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":[0.0005639898,0.0001556933,0.002087992,0.00008452262,0.00005338406,0.0002191148,0.000200069,0.9049485,0.002164583,0.07376359,0.001027728,0.01473079],"study_design_scores_gemma":[0.00001838975,0.00004373561,0.0001739484,0.000007779718,0.000007949669,0.00001285611,0.00001614982,0.9880632,0.0004644011,0.01105657,0.0001261695,0.000008970401],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2662717,0.0004904859,0.7229492,0.001047468,0.00007396714,0.000208007,0.0003542555,0.0007650424,0.007839822],"genre_scores_gemma":[0.9789277,0.0001307291,0.01768112,0.0001024991,0.00002420999,0.00009404832,0.0001395532,0.00005238797,0.002847789],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006810185,"threshold_uncertainty_score":0.02014482,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4995689698780204,"score_gpt":0.375060370729575,"score_spread":0.1245085991484453,"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."}}