Computational Game Theory Spring Semester , 2009 / 10 Lecture 7 : April 28 , 2010

1 Regret Minimization In this lecture, our goal is to build a strategy with good performance when dealing with repeated games. Let us start with a simple model of regret. In this model a player performs a partial optimization on his actions. Following each action he updates his belief and selects the next actions, dependent on the outcome. We will also show that for a familty of games, socially concave games, if all the players play a strategy to minimize the regret, the game converges to a Nash equilibrium.