LEADER 01456nam  2200313 i 4500
001 991004402927907536
005 20251022111406.0
008 251016s2020    -uka   e    b 001 0 eng d
020   $a9781108486828$qhardcopy
024 7 $a10.1017/9781108571401$2doi
040   $aBibl. Dip.le Aggr. Matematica e Fisica - Sez. Matematica$beng
082 04$a518.1
084   $aAMS 68Q-xx
084   $aLC QA402
100 1 $aLattimore, Tor$01854713
245 10$aBandit algorithms /$cTor Lattimore, Csaba Szepesvári
260   $aCambridge ;$aNew York, NY :$bCambridge University Press,$c2020
300   $axviii, 518 p. :$bill. ;$c26 cm
504   $aIncludes bibliographical references (p. [484]-511) and index
520   $aDecision-making in the face of uncertainty is a challenge in machine learning, and the multi-armed bandit model is a common framework to address it. This comprehensive introduction is an excellent reference for established researchers and a resource for graduate students interested in exploring stochastic, adversarial and Bayesian frameworks
650 24$aResource allocation$xMathematical models
650 24$aDecision making$xMathematical models
650 14$aAlgorithms
650 14$aProbabilities
650 14$aMathematical optimization
700 1 $aSzepesvári, Csaba$eauthor$4http://id.loc.gov/vocabulary/relators/aut$01854714
912   $a991004402927907536
996   $aBandit algorithms$94452332
997   $aUNISALENTO