L\'evy bandits under Poissonian decision times

Abstract

We consider a version of the continuous-time multi-armed bandit problem where decision opportunities arrive at Poisson arrival times, and study its Gittins index policy. When driven by spectrally one-sided L\'evy processes, the Gittins index can be written explicitly in terms of the scale function, and is shown to converge to that in the classical L\'evy bandit of Kaspi and Mandelbaum (1995).