This talk aims to introduce the basics of reinforcement learning (RL) and review its financial applications. In an RL framework, an intelligent agent learns to make and improve her decisions by interacting with the unknown environment, and by observing her state trajectories and a sequence of reward signals. RL provides a natural setting for decision-making problems where there are fewer assumptions needed on the underlying models. This talk starts with an introduction to Markov decision processes (MDP) which is the setting for many of the commonly used algorithms. Several popular RL algorithms will then be covered in detail. Finally, we discuss the applications of these RL approaches in a variety of decision-making problems in finance including optimal execution, portfolio optimization, market making, and robo-advising.

This talk is based on a survey paper with Ben Hambly (U of Oxford) and Huining Yang (Princeton U) (https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3971071)