/papers/
../
An optimal high probability algorithm for the contextual bandit problem, 2010.pdf
Aueur, Cesa, Freund, Schapire - The nonstochastic multiarmed bandit problem, 2002.pdf
Cesa, Lugosi - Prediction, learning and games, 2006.pdf
NIPS2003_AA44.pdf
coursbandit.pdf
rapport.pdf