ML Anthology

Approximating Game-Theoretic Optimal Strategies for Full-Scale Poker

Darse Billings, Neil Burch, Aaron Davidson, Robert C. Holte, Jonathan Schaeffer, Terence Schauenberg, Duane Szafron
IJCAI 2003 pp. 661-668
/ijcai/2003/billings2003ijcai-approximating/

Abstract

The computation of the first complete approximations of game-theoretic optimal strategies for fullscale poker is addressed. Several abstraction techniques are combined to represent the game of 2player Texas Hold’em, having sizeÇ �, using closely related models each having sizeÇ�. Despite the reduction in size by a factor of 100 billion, the resulting models retain the key properties and structure of the real game. Linear programming solutions to the abstracted game are used to create substantially improved poker-playing programs, able to defeat strong human players and be competitive against world-class opponents. 1

PDF Semantic Scholar

Cite

Text

Billings et al. "Approximating Game-Theoretic Optimal Strategies for Full-Scale Poker." International Joint Conference on Artificial Intelligence, 2003.

Markdown

[Billings et al. "Approximating Game-Theoretic Optimal Strategies for Full-Scale Poker." International Joint Conference on Artificial Intelligence, 2003.](https://mlanthology.org/ijcai/2003/billings2003ijcai-approximating/)

BibTeX

@inproceedings{billings2003ijcai-approximating,
  title     = {{Approximating Game-Theoretic Optimal Strategies for Full-Scale Poker}},
  author    = {Billings, Darse and Burch, Neil and Davidson, Aaron and Holte, Robert C. and Schaeffer, Jonathan and Schauenberg, Terence and Szafron, Duane},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2003},
  pages     = {661-668},
  url       = {https://mlanthology.org/ijcai/2003/billings2003ijcai-approximating/}
}