Course Meeting Times
Lectures: 2 sessions/week, 1.5 hours/session
Prerequisites
Students are expected to understand discrete mathematics and algorithms at the advanced undergraduate level and display mathematical maturity.
Course Description
While machine learning techniques have had significant success in single-agent settings, an increasingly large body of literature has been studying settings involving several learning agents with different objectives. In these settings, standard training methods such as gradient descent are less successful and the simultaneous learning of the agents commonly leads to nonstationary and even chaotic system dynamics.
Motivated by these challenges, this course presents the foundations of multi-agent systems from a combined game-theoretic, optimization, and learning-theoretic perspective. We start with basic matrix games, such as rock-paper-scissors, and advance to more complex forms including imperfect information games and structured games like combinatorial games, polymatrix games, and stochastic games.
Topics will cover various equilibrium concepts, aspects of equilibrium computation and learning, as well as the computational complexity of finding equilibria. Additionally, we will examine how these models and methods have driven recent breakthroughs in AI, producing human- and superhuman-level agents for well known games such as Go, poker, Diplomacy, and Stratego.
Grading
Problem Sets 50%
Project 50%
Collaboration Policy
We encourage working together whenever possible: in the coding exercises, problem sets, and general discussion of the material and assignments. Keep in mind, however, that for the problem sets the solutions you hand in should reflect your own understanding of the class material, and should be written solely by you. It is not acceptable to copy a solution that somebody else has written.
