Showing stat.MLShow all
2 papers · 1 filter
stat.ML2019
Efficient Change-Point Detection for Tackling Piecewise-Stationary Bandits
Lilian Besson, Emilie Kaufmann, Odalric-Ambrym Maillard +1
We introduce GLR-klUCB, a novel algorithm for the piecewise iid non-stationary bandit problem with bounded rewards. This algorithm combines an efficient bandit algorithm, kl-UCB, w…
stat.ML2018
What Doubling Tricks Can and Can't Do for Multi-Armed Bandits
Lilian Besson, Emilie Kaufmann
An online reinforcement learning algorithm is anytime if it does not need to know in advance the horizon T of the experiment. A well-known technique to obtain an anytime algorithm…