Thompson Sampling : an asymptotically optimal finite time analysis - Télécom Paris Access content directly
Conference Papers Year : 2012

Thompson Sampling : an asymptotically optimal finite time analysis

Abstract

The question of the optimality of Thompson Sampling for solving the stochastic multi-armed bandit problem had been open since 1933. In this paper we answer it positively for the case of Bernoulli rewards by providing the first finite-time analysis that matches the asymptotic rate given in the Lai and Robbins lower bound for the cumulative regret. The proof is accompanied by a numerical comparison with other optimal policies, experiments that have been lacking in the literature until now for the Bernoulli case.
Not file

Dates and versions

hal-02286442 , version 1 (13-09-2019)

Identifiers

  • HAL Id : hal-02286442 , version 1

Cite

Emilie Kaufmann, Nathaniel Korda, Rémi Munos. Thompson Sampling : an asymptotically optimal finite time analysis. International Conference on Algorithmic Learning Theory, Nov 2012, Lyon, France. pp.199-213. ⟨hal-02286442⟩
33 View
0 Download

Share

Gmail Facebook Twitter LinkedIn More