Many problems of optimal control, popular in economics for more than forty years, can be expressed in the reinforcement learning framework, and recent advances in computational science, provided in particular by deep learning algorithms, can be used by economists in order to solve complex behavioral problems.

In this article, we propose state-of-the-art of reinforcement learning techniques, and present applications in economics, game theory, operation research and finance.

• There is large intersection between the economics field and RL; many classical economics problems can be written as RL problems as well. Examples in this talk include: inventory problem, oligopoly games, risk management…
• Many economics topics such as game theory, or optimization (going back to the 1970s or further back) inspired or overlap with modern RL, such as multi-armed bandits, sub-game perfect Nash equilibrium…