Top Two Algorithms Revisited

Abstract

Top Two algorithms arose as an adaptation of Thompson sampling to best arm identification in multi-armed bandit models (Russo, 2016), for parametric families of arms. They select the next arm to sample from by randomizing among two candidate arms, a leader and a challenger. Despite their good empirical performance, theoretical guarantees for fixed-confidence best arm identification have only been obtained when the arms are Gaussian with known variances. In this paper, we provide a general analysis of Top Two methods, which identifies desirable properties of the leader, the challenger, and the (possibly non-parametric) distributions of the arms. As a result, we obtain theoretically supported Top Two algorithms for best arm identification with bounded distributions. Our proof method demonstrates in particular that the sampling step used to select the leader inherited from Thompson sampling can be replaced by other choices, like selecting the empirical best arm.

Publication
Conference on Neural Information Processing Systems
Marc Jourdan
Marc Jourdan
PhD Student

PhD student at Scool (Inria), I study identification problems in Multi-Armed Bandits.

Rémy Degenne
Rémy Degenne
INRIA researcher
Dorian Baudry
Dorian Baudry
Post-Doctoral Researcher
Rianne de Heide
Rianne de Heide
Assistant professor
Emilie Kaufmann
Emilie Kaufmann
CNRS researcher

Related