{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001932964,0.0001809425,0.0003070276,0.0003181619,0.0002098499,0.00008932203,0.001040187,0.0001025172,0.002551286],"category_scores_gemma":[0.004526408,0.0001198385,0.0001614839,0.0006372106,0.0001600539,0.0004457079,0.0002048121,0.0001665843,0.000764601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003965834,"about_ca_system_score_gemma":0.000109089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004168634,"about_ca_topic_score_gemma":0.00002456806,"domain_scores_codex":[0.9970291,0.00006059357,0.0005644316,0.00068245,0.0010678,0.0005955708],"domain_scores_gemma":[0.9966971,0.001339869,0.000131581,0.0007262835,0.0008402856,0.0002649202],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000953062,0.0007006625,0.000228387,0.00002160733,0.0001360175,0.00003247132,0.00264001,0.001536715,0.002509969,0.003806965,0.02698158,0.9604526],"study_design_scores_gemma":[0.002185194,0.0008867707,0.001163585,0.000008604841,0.00001447417,0.00001868349,0.0007438004,0.8639171,0.01231539,0.1043812,0.01384855,0.0005166981],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000894949,0.00003705011,0.9950824,0.000125253,0.0005562847,0.0006984963,0.00004483985,0.00009861482,0.002462146],"genre_scores_gemma":[0.4156465,0.000006764012,0.5122555,0.0003400656,0.0009702462,0.0004079075,0.00001623683,0.00008791894,0.07026884],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9599358,"threshold_uncertainty_score":0.9983605,"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."}}