no code implementations • 5 Feb 2019 • Lilian Besson, Emilie Kaufmann, Odalric-Ambrym Maillard, Julien Seznec
We introduce GLR-klUCB, a novel algorithm for the piecewise iid non-stationary bandit problem with bounded rewards.
no code implementations • 19 Mar 2018 • Lilian Besson, Emilie Kaufmann
In a broad setting, we prove that a geometric doubling trick can be used to conserve (minimax) bounds in $R\_T = O(\sqrt{T})$ but cannot conserve (distribution-dependent) bounds in $R\_T = O(\log T)$.
no code implementations • 7 Nov 2017 • Lilian Besson, Emilie Kaufmann
Multi-player Multi-Armed Bandits (MAB) have been extensively studied in the literature, motivated by applications to Cognitive Radio systems.