131 citations · 143 across the 3 of their papers we have counts for
3 papers
cs.LG2012★ 5 cited
Regret in Online Combinatorial Optimization
Jean-Yves Audibert, Sébastien Bubeck, Gábor Lugosi
We address online linear optimization problems when the possible actions of the decision maker are represented by binary vectors. The regret of the decision maker is the difference…
cs.LG2012★ 131 cited
The best of both worlds: stochastic and adversarial bandits
Sebastien Bubeck, Aleksandrs Slivkins
We present a new bandit algorithm, SAO (Stochastic and Adversarial Optimal), whose regret is, essentially, optimal both for adversarial rewards and for stochastic rewards. Specific…
math.ST2008★ 7 cited
Pure Exploration for Multi-Armed Bandit Problems
Sébastien Bubeck, Rémi Munos, Gilles Stoltz
We consider the framework of stochastic multi-armed bandit problems and study the possibilities and limitations of forecasters that perform an on-line exploration of the arms. Thes…