- Zoom webinar
Mean-field game theory borrows ideas from statistical physics to provide a tractable approximation of very large multi-agent systems. Applications are ubiquitous in today's highly interconnected world, from crowd motion to macroeconomics and distributed robotics. Real-world problems often lead to models which are in high dimension or not fully specified, hence a recent surge of interest for the question of learning solutions with mesh-free and model-free methods. In this talk, we present several methods based on neural network approximation, stochastic optimization and reinforcement learning techniques. If time permits, we will also discuss the converse direction, namely a mean-field game perspective on some aspects of machine learning.