The State of the Art in Computer Poker
Martin Zinkevich
Yahoo! Research
Wednesday, February 6, 2008
4:30 - 5:30 PM
Terman Engineering Center, Room 453
Abstract:
Poker is an incredibly popular game, especially Texas Hold'Em.
Moreover, there has been a recent surge of research in attempting to
solve this game, at the University of Alberta, Carnegie Mellon,
SEQUEL, and a host of other places. What has been accomplished? What
is left to be done? In this talk, I will try to give a description of
the problems which are nearly solved and the problems which appear
wide open in this domain. I will focus on some of the techniques
developed at the University of Alberta for abstraction
and for equilibrium computation, and how regret minimization can solve a
problem normally handled with a linear program.
Operations Research Colloquia: http://or.stanford.edu/oras_seminars.html