Abstract
|
Abstract
Mean field games have been introduced to study Nash equilibria in large populations of strategic agents, while mean field control problems aim at modeling social optima in large groups of cooperative agents. These frameworks have found a wide range of applications, from economics and finance to social sciences and biology. In the past few years, the question of learning equilibria and social optima in a mean field setting has attracted a growing interest. In this talk, I will discuss several model-free methods based on reinforcement learning (RL). We will first discuss RL for mean field Nash equilibria and mean field Social optima, and we will then discuss mixed situations, with a combination of cooperative and non-cooperative scenarios. Numerical experiments on stylized examples of financial models will be presented. This is based on joint works with Andrea Angiuli, Rene Carmona, Nils Detering, Jean Pierre Fouque, Jimin Lin and Zongjun Tan. |