The multi-armed bandit problem is a popular model for studying exploration/exploitation trade-off in sequential decision problems. Many algorithms are now available for this well-studied problem. One of the earliest algorithms, given by W. R. Thompson, dates back to 1933. This algorithm, referred to as Thompson Sampling, is a natural Bayesian algorithm. The basic idea is to choose an arm to play according to its probability of being the best arm. Thompson Sampling algorithm has experimentally been shown to be close to optimal. In addition, it is efficient to implement and exhibits several desirable properties such as small regret for delayed feedback. However, theoretical understanding of this algorithm was quite limited. In this paper, for the first time, we show that Thompson Sampling algorithm achieves logarithmic expected regret for the Bernoulli multi-armed bandit problem. More precisely, for the two-armed Bernoulli bandit problem, the expected regret in time $T$ is $O(\frac{\ln T}{\Delta} + \frac{1}{\Delta^3})$. And, for the $N$-armed Bernoulli bandit problem, the expected regret in time $T$ is $O([(\sum_{i=2}^N \frac{1}{\Delta_i^2})^2] \ln T)$. Our bounds are optimal but for the dependence on $\Delta_i$ and the constant factors in big-Oh.

本文介绍了使用贝叶斯算法的 Thompson Sampling 原则，旨在在序贯决策问题中研究探索/开发权衡。该算法在实验证明接近最优，并展现了一些理想的特性，但对该算法的理论认识相当有限。本文第一次展示了 Thompson Sampling 算法在多臂赌博机问题中实现了对数级别的预期遗憾。

多臂赌博问题中汤普森采样的分析