01035nam0M2200361--I450 99000350616020331620200703062912.0000350616USA01000350616(ALEPH)000350616USA0100035061620110301f2009----|||||itac50 baitaIT||||||||001yy<<La >> via latteaPiergiorgio Odifreddi e Sergio Valzaniacon la partecipazione di Franco CardiniMilanoMondolibri2009314 p.ill.21 cm20012001001-------2001Santiago de CompostelaPellegrinaggiBNCF263.042ODIFREDDI,Piergiorgio28537VALZANIA,Sergio281668CARDINI,Franco<1940- >ITsalbcISBD990003506160203316XVII A.A. 18489296 DLASXVII A.A.00157470BKCASVia lattea778553UNISA01456nam 2200313 i 450099100440292790753620251022111406.0251016s2020 -uka e b 001 0 eng d9781108486828hardcopy10.1017/9781108571401doiBibl. Dip.le Aggr. Matematica e Fisica - Sez. Matematicaeng518.1AMS 68Q-xxLC QA402Lattimore, Tor1854713Bandit algorithms /Tor Lattimore, Csaba SzepesváriCambridge ;New York, NY :Cambridge University Press,2020xviii, 518 p. :ill. ;26 cmIncludes bibliographical references (p. [484]-511) and indexDecision-making in the face of uncertainty is a challenge in machine learning, and the multi-armed bandit model is a common framework to address it. This comprehensive introduction is an excellent reference for established researchers and a resource for graduate students interested in exploring stochastic, adversarial and Bayesian frameworksResource allocationMathematical modelsDecision makingMathematical modelsAlgorithmsProbabilitiesMathematical optimizationSzepesvári, Csabaauthorhttp://id.loc.gov/vocabulary/relators/aut1854714991004402927907536Bandit algorithms4452332UNISALENTO