2016 Poster Sessions : General Game Playing

Student Name : Bertrand Decoster
Advisor : Mike Genesereth
Research Areas: Artificial Intelligence
Abstract:
General Game Players are computer systems able to play games based solely on formal game descriptions supplied at "runtime". In other words, they don't know the rules until the game starts. Unlike specialized game players, such as Deep Blue or AlphaGo, general game players cannot be trained in advance for specific games; they must discover the relevant strategies themselves. General game playing expertise depends on intelligence on the part of the game player and not just intelligence of the programmer of the game player.

GGP is an interesting application in its own right. It is intellectually engaging and really fun. But it is much more than that. It provides a theoretical framework for modeling discrete dynamic systems and for defining rationality in a way that takes into account problem representation and complexities like incompleteness of information and resource bounds. It has practical applications in areas where these features are important, e.g. in business and law. More fundamentally, it raises questions about the nature of intelligence and serves as a laboratory in which to evaluate competing approaches to artificial intelligence.

Bio:
Bertrand Decoster did his master in the Ecole Polytechnique, France, before starting his PhD in Stanford's ICME program. His work for his advisor, Michael Genesereth, focuses on General Game Playing (GGP). The goal is to have the machine understand set of rules rather than blindly manipulating them. He is interested notably in knowledge representation, artificial intelligence and machine learning.