{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002845495,0.0002554776,0.0007076779,0.0008712414,0.0005421899,0.0001858513,0.0005837163,0.0001713606,0.00004446173],"category_scores_gemma":[0.0003720835,0.0001824341,0.0001914162,0.00302029,0.000155622,0.0002416631,0.000002822844,0.000467513,0.0002099738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001369868,"about_ca_system_score_gemma":0.0002395933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001068185,"about_ca_topic_score_gemma":0.0001124803,"domain_scores_codex":[0.9954945,0.0004680472,0.0007659551,0.0006392722,0.001870482,0.0007616786],"domain_scores_gemma":[0.9913106,0.006780711,0.0003630807,0.0006917206,0.0006533468,0.0002005164],"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":[0.001163417,0.00005234851,0.0001965634,0.00002117701,0.00008646934,0.00001046863,0.00006972167,0.9849778,0.00004511598,0.0001956694,0.00505465,0.008126573],"study_design_scores_gemma":[0.005277573,0.001660103,0.0007158947,0.0004229148,0.00003341844,0.00001836919,0.0004237194,0.9742419,0.0002316949,0.001861241,0.01476493,0.0003482898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004385437,0.0000819527,0.9917307,0.0006520635,0.001071873,0.001211918,0.0001107452,0.0001590846,0.0005962281],"genre_scores_gemma":[0.9867285,0.00002392212,0.0001212794,0.00004916799,0.0005681025,0.0003786308,0.000004080612,0.00005576691,0.01207052],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9916094,"threshold_uncertainty_score":0.7439449,"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."}}