An Improved Parametrization and Analysis of the EXP3++ Algorithm for Stochastic and Adversarial Bandits

[edit]

Yevgeny Seldin, Gábor Lugosi ;
Proceedings of the 2017 Conference on Learning Theory, PMLR 65:1743-1759, 2017.

Abstract

We present a new strategy for gap estimation in randomized algorithms for multiarmed bandits and combine it with the EXP3++ algorithm of Seldin and Slivkins (2014). In the stochastic regime the strategy reduces dependence of regret on a time horizon from $(\ln t)^3$ to $(\ln t)^2$ and eliminates an additive factor of order $∆e^1/∆^2$, where $∆$ is the minimal gap of a problem instance. In the adversarial regime regret guarantee remains unchanged.

Related Material