{"id":"W2119738618","doi":"","title":"Improved Algorithms for Linear Stochastic Bandits","year":2011,"lang":"en","type":"article","venue":"","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":916,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Logarithm; Computer science; Constant (computer programming); Simple (philosophy); Algorithm; Mathematical optimization; Multi-armed bandit; Mathematics; Machine learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008746492,0.002299319,0.002995717,0.002032754,0.0009861181,0.003264652,0.004659482,0.003298637,0.008169985],"category_scores_gemma":[0.04489249,0.001170912,0.001900964,0.002924328,0.002438478,0.005900263,0.004277546,0.006200713,0.003284171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002812113,"about_ca_system_score_gemma":0.002999307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003043824,"about_ca_topic_score_gemma":0.002925608,"domain_scores_codex":[0.9920875,0.003554884,0.0004014049,0.001103707,0.002134805,0.000717635],"domain_scores_gemma":[0.9774994,0.01567248,0.001422823,0.002937819,0.001998257,0.0004692464],"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":[0.0004438064,0.0002952042,0.001232905,0.0003538644,0.0001571091,0.0001126171,0.0002191129,0.5721544,0.002765167,0.2561734,0.009038774,0.1570536],"study_design_scores_gemma":[0.00003933125,0.00003787705,0.0001130125,0.00002958227,0.0000139385,0.00003229071,0.000006844414,0.9459243,0.0005808895,0.05186597,0.001342466,0.0000134817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00468228,0.0006533609,0.9902884,0.0004119279,0.00009552488,0.0000800382,0.000101554,0.0007733071,0.0029136],"genre_scores_gemma":[0.2585602,0.001282696,0.7272025,0.001005207,0.0006581399,0.0006956131,0.0007621157,0.0008566319,0.008976917],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008746492,"threshold_uncertainty_score":0.04625642,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3179026584292263,"score_gpt":0.4621502314159748,"score_spread":0.1442475729867485,"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."}}