CS 364 A : Algorithmic Game

This lecture continues to study the questions introduced last time. Do strategic players reach an equilibrium of a game? How quickly? By what learning processes? Positive results on these questions justify equilibrium analysis, including bounds on the price of anarchy. Last lecture focused on best-response dynamics. These dynamics are most relevant for potential games, which cover many but not all interesting applications. This lecture, we study a second fundamental class of learning dynamics — no-regret dynamics. An attractive feature of these dynamics is their rapid convergence to an approximate equilibrium — a coarse correlated equilibrium (Lecture 13), not generally a Nash equilibrium — in arbitrary games.