A Tutorial on Thompson Sampling

TL;DR

This tutorial explains Thompson sampling, an efficient algorithm for sequential decision-making that balances exploration and exploitation across various complex problems, with insights into its effectiveness and applications.

Contribution

It provides a comprehensive overview of Thompson sampling, illustrating its application across diverse problems and discussing its advantages, limitations, and relation to other algorithms.

Findings

Thompson sampling effectively balances exploration and exploitation.

The algorithm performs well in complex information structures.

It is computationally efficient and widely applicable.

Abstract

Thompson sampling is an algorithm for online decision problems where actions are taken sequentially in a manner that must balance between exploiting what is known to maximize immediate performance and investing to accumulate new information that may improve future performance. The algorithm addresses a broad range of problems in a computationally efficient manner and is therefore enjoying wide use. This tutorial covers the algorithm and its application, illustrating concepts through a range of examples, including Bernoulli bandit problems, shortest path problems, product recommendation, assortment, active learning with neural networks, and reinforcement learning in Markov decision processes. Most of these problems involve complex information structures, where information revealed by taking an action informs beliefs about other actions. We will also discuss when and why Thompson sampling is or is not effective and relations to alternative algorithms.