{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001936808,0.0004509304,0.0006297451,0.0008156704,0.0006148466,0.001022125,0.001843667,0.0005378354,0.000517222],"category_scores_gemma":[0.001212386,0.0004430922,0.0006015454,0.00129202,0.00043351,0.0005187471,0.002608434,0.001400939,0.001241071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006907702,"about_ca_system_score_gemma":0.000642009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008161943,"about_ca_topic_score_gemma":0.00008811442,"domain_scores_codex":[0.9955472,0.0002364886,0.0005242514,0.002265206,0.0006818373,0.0007450564],"domain_scores_gemma":[0.9957111,0.001278645,0.0003612091,0.001471557,0.000863384,0.0003140391],"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":[0.0004796717,0.00009695974,0.0006135456,0.0001966229,0.0002412208,0.0004137665,0.0005244391,0.9633,0.00008992613,0.006794721,0.01171859,0.01553054],"study_design_scores_gemma":[0.0005339085,0.0001351553,0.0003529891,0.0001034753,0.00009292433,0.00001152453,0.0005594807,0.7641208,0.0001990799,0.1922486,0.04111055,0.0005314866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.325005,0.000297674,0.6680576,0.0003938386,0.002943968,0.0009167823,0.0002579395,0.000280935,0.001846302],"genre_scores_gemma":[0.9666891,0.0001371719,0.003191523,0.00003948243,0.0005445229,0.000008730726,0.00005982267,0.00006772307,0.02926198],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.664866,"threshold_uncertainty_score":0.9998021,"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."}}