[edit]
An Improved Parametrization and Analysis of the EXP3++ Algorithm for Stochastic and Adversarial Bandits
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 (lnt)3 to (lnt)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.