{"id":"W2765574662","doi":"10.1109/tac.2017.2765501","title":"The Multi-Armed Bandit With Stochastic Plays","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Regret; Sublinear function; Mathematical optimization; Upper and lower bounds; Stochastic process; Process (computing); Computer science; Power (physics); Work (physics); Demand response; Mathematics; Engineering; Machine learning; Statistics; Discrete mathematics","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":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001710889,0.0002544609,0.0004063328,0.0002194427,0.003404996,0.001225967,0.001817469,0.00008415945,0.0004748273],"category_scores_gemma":[0.0009812792,0.0001336353,0.0001687967,0.0002357018,0.0007191563,0.0004882001,0.000004387056,0.0003700063,0.0009688386],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001034005,"about_ca_system_score_gemma":0.0001830385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003571733,"about_ca_topic_score_gemma":0.0005827101,"domain_scores_codex":[0.9961112,0.0002251318,0.0005733356,0.0005214115,0.001988671,0.0005802649],"domain_scores_gemma":[0.99166,0.005304889,0.0003740148,0.002092493,0.000339423,0.0002291778],"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":[0.0005177029,0.0003900393,0.0000350734,0.000008361273,0.0002829702,0.00006204664,0.0005293963,0.1877837,0.0003151348,0.00004222424,0.000526569,0.8095068],"study_design_scores_gemma":[0.004811674,0.0002558654,0.002668387,0.00003940271,0.00004813846,0.00002983502,0.0002749565,0.9897996,0.0004376928,0.0008836203,0.0005328387,0.0002179513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004968781,0.00002796298,0.9908764,0.002203481,0.0006589338,0.000916195,0.00005994089,0.0001302131,0.000158103],"genre_scores_gemma":[0.9935341,0.000004937705,0.001850661,0.00008175645,0.00005732627,0.0003046178,2.733474e-7,0.00002956554,0.004136695],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9890257,"threshold_uncertainty_score":0.9998109,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07040009105956221,"score_gpt":0.3874683501386741,"score_spread":0.3170682590791118,"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."}}