Consensus and Dissensus in Multi-population Multi-agent Systems
Explore a seminar on dynamic games and applications that delves into consensus and dissensus in multi-population multi-agent systems. Learn about mean field games (MFGs) approach to decision making in multi-agent dynamical systems, covering both model-based and model-free settings. Discover the connections between MFGs and finite-population games. Focus on discrete-time infinite-horizon linear-quadratic-Gaussian dynamic games, where players are divided into finitely-many populations with an underlying graph topology. Understand how this framework relates to scenarios where consensus and dissensus coexist. Examine the use of MFGs to achieve approximate Nash equilibria and explore learning algorithms for model-free settings, including sample complexity analysis.