{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005229055,0.002256237,0.002777088,0.0007612366,0.001113143,0.002729262,0.002554866,0.002809446,0.005271066],"category_scores_gemma":[0.01636013,0.0009715182,0.001482054,0.001315009,0.002714704,0.003202527,0.002360121,0.004268637,0.001229114],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001634384,"about_ca_system_score_gemma":0.001881837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002676114,"about_ca_topic_score_gemma":0.00226759,"domain_scores_codex":[0.9961419,0.00231108,0.000150182,0.0005243262,0.0004818322,0.0003906861],"domain_scores_gemma":[0.9900815,0.007438758,0.0008540021,0.0007472025,0.0005374927,0.000340988],"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":[0.0003119796,0.0001272233,0.0008045924,0.0001643833,0.0001076508,0.000166841,0.0001102008,0.8359472,0.0007844983,0.134729,0.003285493,0.02346092],"study_design_scores_gemma":[0.000025549,0.00003843927,0.00006029282,0.00001437499,0.00001144374,0.000019607,0.000005923849,0.9675651,0.0002112766,0.03145288,0.0005862718,0.00000895626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01637777,0.0006979295,0.9742624,0.001366455,0.0001357154,0.00008893357,0.000132991,0.0003276378,0.006610127],"genre_scores_gemma":[0.8035842,0.001080734,0.1789841,0.0012057,0.0004501524,0.0005297626,0.0003262119,0.0002191652,0.01362006],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005271066,"threshold_uncertainty_score":0.02765423,"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."}}