A New Algorithm for Generating Equilibria in Massive Zero-Sum Games

In normal scenarios, computer scientists often consider the number of states in a game to capture the difficulty of learning an equilibrium. However, players do not see games in the same light: most consider Go or Chess to be more complex than Monopoly. In this paper, we discuss a new measure of game complexity that links existing state-of-the-art algorithms for computing approximate equilibria to a more human measure. In particular, we consider the range of skill in a game, i.e.how many different skill levels exist. We then modify existing techniques to design a new algorithm to compute approximate equilibria whose performance can be captured by this new measure. We use it to develop the first near ilibrium for a four round abstraction of poker, and show that it would have been able to win handily the bankroll competition from last year’s AAAI poker competition.

• Type: Conference
• Year: 2007
• Where: AAAI
• Authors: Martin Zinkevich, Michael H. Bowling, Neil Burch
• Keywords: AAAI 2007, Approximate Equilibria, Intelligent Agents, Normal Scenarios, Year’s Aaai Poker