Title: On Machine Learning Methods for Mean Field Games and Mean Field Control
Speaker: Mathieu Lauriere
Speaker Info: Princeton
Brief Description:
Special Note:
Abstract:
In today’s highly interconnected world, many situations involve a large number of agents taking decisions. Mean field games have been introduced to cope with the fact that individual interactions become intractable as the size of the population grows. The key idea is to replace the microscopic viewpoint by a macroscopic one, describing the interactions of a typical player with the population’s distribution. In this talk, we propose several stochastic numerical methods for mean field games which are are based on machine learning tools such as function approximation via neural networks and optimization relying on stochastic gradient descent. We investigate the numerical analysis of these methods and prove bounds on the error. Numerical tests will also be presented. This is joint work with Rene Carmona (Princeton University).Date: Tuesday, February 04, 2020