Solving Heads-Up Limit Texas Hold'em
- Oskari Tammelin
- Neil Burch, Department of Computing Science, University of Alberta
- Michael Johanson, University of Alberta
- Michael Bowling, University of Alberta
Cepheus is the first computer program to essentially solve a game of imperfect information that is played competitively by humans. The game it plays is heads-up limit Texas hold'em poker, a game with over 10^14 information sets, and a challenge problem for artificial intelligence for over 10 years. Cepheus was trained using a new variant of Counterfactual Regret Minimization (CFR), called CFR+, using 4800 CPUs running for 68 days. In this paper we describe in detail the engineering details required to make this computation a reality. We also prove the theoretical soundness of CFR+ and its component algorithm, regret-matching+. We further give a hint towards understanding the success of CFR+ by proving a tracking regret bound for this new regret matching algorithm. We present results showing the role of the algorithmic components and the engineering choices to the success of CFR+.
Citation
O. Tammelin, N. Burch, M. Johanson, M. Bowling. "Solving Heads-Up Limit Texas Hold'em". International Joint Conference on Artificial Intelligence (IJCAI), (ed: Qiang Yang, Michael J. Wooldridge), pp 645-652, July 2015.| Keywords: | |
| Category: | In Conference |
| Web Links: | IJCAI |
BibTeX
@incollection{Tammelin+al:IJCAI15,
author = {Oskari Tammelin and Neil Burch and Michael Johanson and Michael
Bowling},
title = {Solving Heads-Up Limit Texas Hold'em},
Editor = {Qiang Yang, Michael J. Wooldridge},
Pages = {645-652},
booktitle = {International Joint Conference on Artificial Intelligence
(IJCAI)},
year = 2015,
}Last Updated: October 29, 2020Submitted by Sabina P
