Libratus: The Superhuman AI for No-Limit Poker
Abstract
No-limit Texas Hold'em is the most popular variant of poker in the world. Heads-up no-limit Texas Hold'em is the main benchmark challenge for AI in imperfect-information games. We present Libratus, the first - and so far only - AI to defeat top human professionals in that game. Libratus's architecture features three main modules, each of which has new algorithms: pre-computing a solution to an abstraction of the game which provides a high-level blueprint for the strategy of the AI, a new nested subgame-solving algorithm which repeatedly calculates a more detailed strategy as play progresses, and a self-improving module which augments the pre-computed blueprint over time.
Cite
Text
Brown and Sandholm. "Libratus: The Superhuman AI for No-Limit Poker." International Joint Conference on Artificial Intelligence, 2017. doi:10.24963/IJCAI.2017/772Markdown
[Brown and Sandholm. "Libratus: The Superhuman AI for No-Limit Poker." International Joint Conference on Artificial Intelligence, 2017.](https://mlanthology.org/ijcai/2017/brown2017ijcai-libratus/) doi:10.24963/IJCAI.2017/772BibTeX
@inproceedings{brown2017ijcai-libratus,
title = {{Libratus: The Superhuman AI for No-Limit Poker}},
author = {Brown, Noam and Sandholm, Tuomas},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2017},
pages = {5226-5228},
doi = {10.24963/IJCAI.2017/772},
url = {https://mlanthology.org/ijcai/2017/brown2017ijcai-libratus/}
}