Search Results for author:
Found 3 papers, 0 papers with code
Efficient Change-Point Detection for Tackling Piecewise-Stationary Bandits
We introduce GLR-klUCB, a novel algorithm for the piecewise iid non-stationary bandit problem with bounded rewards.
What Doubling Tricks Can and Can't Do for Multi-Armed Bandits
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 $R\_T = O(\log T)$.
Multi-Player Bandits Revisited
Multi-player Multi-Armed Bandits (MAB) have been extensively studied in the literature, motivated by applications to Cognitive Radio systems.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
