{"id":"W3005661940","doi":"10.1609/aaai.v35i8.16901","title":"Regret Bounds for Batched Bandits","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Air Force Office of Scientific Research; Office of Naval Research; Institut de Valorisation des Données; Canada First Research Excellence Fund; National Science Foundation","keywords":"Regret; Logarithm; Mathematical optimization; Simple (philosophy); Computer science; Multi-armed bandit; Mathematics; Algorithm; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.01028647,0.004038423,0.003157027,0.001597801,0.001776554,0.005220371,0.00576809,0.003409448,0.01101953],"category_scores_gemma":[0.04718895,0.001427288,0.002570681,0.002461864,0.003366545,0.009119267,0.00453636,0.008738587,0.00296832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005417763,"about_ca_system_score_gemma":0.0035213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002956382,"about_ca_topic_score_gemma":0.003112965,"domain_scores_codex":[0.9926302,0.002223113,0.0003914096,0.001456441,0.00221725,0.001081489],"domain_scores_gemma":[0.9605368,0.02882966,0.002485752,0.004633632,0.002370235,0.001143882],"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":[0.001120757,0.0004227089,0.001111058,0.0004912103,0.000186638,0.0001376857,0.0001944715,0.7502117,0.004707093,0.1664146,0.01086735,0.06413471],"study_design_scores_gemma":[0.00006229535,0.00008062064,0.0002013281,0.00005590678,0.00004147023,0.00004380497,0.00001659528,0.9140266,0.001395998,0.08264568,0.001407049,0.00002262277],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01194131,0.002144476,0.9719155,0.001373356,0.0003166451,0.0001893313,0.0004713294,0.001266265,0.0103817],"genre_scores_gemma":[0.5310056,0.003835616,0.4412124,0.00181873,0.001223813,0.001245875,0.001369559,0.001442951,0.01684546],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01101953,"threshold_uncertainty_score":0.05440068,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.349858033997507,"score_gpt":0.4633447509370407,"score_spread":0.1134867169395337,"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."}}