4.8 Article

Superhuman AI for heads-up no-limit poker: Libratus beats top professionals

期刊

SCIENCE
卷 359, 期 6374, 页码 418-+

出版社

AMER ASSOC ADVANCEMENT SCIENCE
DOI: 10.1126/science.aao1733

关键词

-

资金

  1. NSF [IIS-1718457, IIS-1617590, CCF-1733556]
  2. U.S. Army Research Office [W911NF-17-1-0082]
  3. Carnegie Mellon University
  4. Rivers Casino
  5. GreatPoint Ventures
  6. Avenue4Analytics
  7. TNG Technology Consulting
  8. Artificial Intelligence
  9. Intel
  10. Optimized Markets, Inc.
  11. Direct For Computer & Info Scie & Enginr [1445606] Funding Source: National Science Foundation

向作者/读者索取更多资源

No-limit Texas hold'em is the most popular form of poker. Despite artificial intelligence (AI) successes in perfect-information games, the private information and massive game tree have made no-limit poker difficult to tackle. We present Libratus, an AI that, in a 120,000-hand competition, defeated four top human specialist professionals in heads-up no-limit Texas hold'em, the leading benchmark and long-standing challenge problem in imperfect-information game solving. Our game-theoretic approach features application-independent techniques: an algorithm for computing a blueprint for the overall strategy, an algorithm that fleshes out the details of the strategy for subgames that are reached during play, and a self-improver algorithm that fixes potential weaknesses that opponents have identified in the blueprint strategy.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.8
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据