Presentation on YouTube.

The talk will start with a general overview of mean field games (MFGs) approach to decision making in multi-agent dynamical systems in both model-based and model-free settings and discuss connections to finite-population games. Following this general introduction, the talk will focus on the structured setting of discrete-time infinite-horizon linear-quadratic-Gaussian dynamic games, where the players are partitioned into finitely-many populations with an underlying graph topology---a framework motivated by paradigms where consensus and dissensus co-exist. MFGs approach will be employed to arrive at approximate Nash equilibria, and learning algorithms will be presented for the model-free setting, along with sample complexity analysis.