{"id":"W4392487808","doi":"10.48550/arxiv.2403.01315","title":"Near-optimal Per-Action Regret Bounds for Sleeping Bandits","year":2024,"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":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regret; Action (physics); Mathematical economics; Economics; Computer science; Mathematics; Econometrics; Statistics; Physics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006882458,0.003324169,0.002734007,0.001153193,0.001191394,0.003043843,0.004707307,0.002344487,0.008786416],"category_scores_gemma":[0.03440579,0.001150287,0.002708954,0.001700089,0.003086101,0.006187913,0.003848369,0.008328317,0.002190097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003446425,"about_ca_system_score_gemma":0.003166799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002139895,"about_ca_topic_score_gemma":0.002850469,"domain_scores_codex":[0.9956493,0.001293033,0.0002107387,0.0009078751,0.001189842,0.0007492049],"domain_scores_gemma":[0.9776111,0.01530312,0.001464822,0.00349346,0.001278206,0.0008493562],"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":[0.0007914223,0.0003616487,0.001902088,0.0005465625,0.0001893191,0.0001668397,0.0003059789,0.7701762,0.005531938,0.1394727,0.008605613,0.07194965],"study_design_scores_gemma":[0.00004510587,0.0001188947,0.0004122584,0.00007574717,0.00005058719,0.00007386164,0.00003213737,0.916202,0.002065983,0.07947505,0.001422129,0.00002622457],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02526744,0.0021819,0.954648,0.001146442,0.0001957871,0.0001409065,0.0003655465,0.001220755,0.01483327],"genre_scores_gemma":[0.6576823,0.002686055,0.3224206,0.001714271,0.0006133237,0.0007364406,0.0009494792,0.001283005,0.01191452],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008786416,"threshold_uncertainty_score":0.03639835,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3503616559239939,"score_gpt":0.3551522520268063,"score_spread":0.004790596102812406,"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."}}