{"id":"W4388740203","doi":"10.1109/tcns.2023.3333402","title":"On Learning Whittle Index Policy for Restless Bandits With Scalable Regret","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Control of Network Systems","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Scalability; Notation; Discrete mathematics; Mathematics; Computer science; Artificial intelligence; Machine learning; Arithmetic","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":[0.005123185,0.002100114,0.00315106,0.0008522592,0.0008028923,0.001972438,0.002426728,0.00251119,0.003894216],"category_scores_gemma":[0.02138646,0.000893716,0.001114499,0.001037391,0.002915973,0.003551753,0.002420757,0.003845217,0.0009229775],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002610518,"about_ca_system_score_gemma":0.00278599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005987807,"about_ca_topic_score_gemma":0.004869709,"domain_scores_codex":[0.9979024,0.001024829,0.0000893472,0.0003307358,0.0003597798,0.0002929777],"domain_scores_gemma":[0.9876573,0.009832646,0.0008594238,0.0007579002,0.0004605462,0.0004321889],"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":[0.0001849552,0.0000828497,0.0005423764,0.00005906754,0.00003670694,0.00005376797,0.00004430263,0.9579166,0.0004526834,0.02518004,0.001164365,0.01428238],"study_design_scores_gemma":[0.00001186291,0.0000207787,0.00002776332,0.000005109444,0.000002807399,0.000005143618,0.000002335324,0.9924448,0.00009724584,0.007317552,0.00006121462,0.000003407735],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02973469,0.0005305832,0.9645248,0.0007081341,0.00005995612,0.00009558128,0.00009694149,0.0009028813,0.003346444],"genre_scores_gemma":[0.8234594,0.0005546176,0.1685115,0.0009036909,0.0002177457,0.0004554677,0.0003677489,0.0003585762,0.005171178],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005987807,"threshold_uncertainty_score":0.0270943,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0682088884693561,"score_gpt":0.3776760523188988,"score_spread":0.3094671638495426,"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."}}