Solving Heads-Up Limit Texas Hold'em
Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 645-651.
Abstract
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+.
@inproceedings{ijcai2015p97,
title = {Solving Heads-Up Limit Texas Hold'em},
author = {Tammelin, Oskari and Burch, Neil and Johanson, Michael and Bowling, Michael H.},
booktitle = {Proceedings of the Twenty-Fourth International Joint Conference on
Artificial Intelligence, {IJCAI-15}},
publisher = {International Joint Conferences on Artificial Intelligence},
editor = {Qiang Yang and Michael Wooldridge},
pages = {645--651},
year = {2015},
month = {7},
note = {Main Track},
url = {https://ijcai.org/proceedings/2015/97},
}
TY - CPAPER TI - Solving Heads-Up Limit Texas Hold'em AU - Tammelin, Oskari AU - Burch, Neil AU - Johanson, Michael AU - Bowling, Michael H. T2 - Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-15 PB - International Joint Conferences on Artificial Intelligence PY - 2015 SP - 645 EP - 651 UR - https://ijcai.org/proceedings/2015/97 ER -Copied
Machine-readable versions of this paper, for tools and AI agents: