{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002345155,0.0002457535,0.0004640393,0.0002076554,0.0003927544,0.0006097171,0.002219153,0.0001398997,0.0008648851],"category_scores_gemma":[0.01782167,0.0001644035,0.0002832372,0.001656431,0.0005583441,0.0004503532,0.0004687545,0.0003727381,0.0002470423],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007430318,"about_ca_system_score_gemma":0.0003718483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000960653,"about_ca_topic_score_gemma":0.00002940785,"domain_scores_codex":[0.9955533,0.00004313989,0.001008934,0.000864114,0.001977476,0.0005530899],"domain_scores_gemma":[0.9924282,0.001290812,0.000530731,0.000559453,0.00502735,0.0001633951],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005783451,0.0004005819,0.0005628177,0.0000616773,0.00005305604,0.000003949553,0.001859379,0.0002721842,0.1082446,0.5520921,0.007949475,0.3279218],"study_design_scores_gemma":[0.00004095534,0.0001220622,0.0001418722,0.00006603694,0.000007583715,0.000005285976,0.001701229,0.01244498,0.5155847,0.4669257,0.002815602,0.0001440194],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5126265,0.0004716068,0.3335667,0.0668943,0.006182012,0.004601665,0.0004012133,0.0003471127,0.07490888],"genre_scores_gemma":[0.9884676,0.00004071122,0.003575751,0.000203995,0.0002060923,0.00007118012,0.000002009242,0.00002293054,0.007409673],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4758411,"threshold_uncertainty_score":0.9904516,"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."}}