Thompson sampling (TS) and its variants are popular algorithms for reinforcement learning and multi-armed bandits. In this tutorial, we will briefly review the basic concepts of reinforcement learning, bandits, and TS. We will also discuss several practical considerations when applying TS to real-world problems, as well as the high-level insights on how to analyze TS. Preliminary experiment results will also be discussed.
December 25th, 2018
14:00 ~ 15:00
Jingwei Liang, University of Cambridge
Room 102, School of Information Management & Engineering, Shanghai University of Finance & Economics