Superhuman AI for heads-up no-limit poker: Libratus beats top professionals
Superhuman AI for heads-up no-limit poker: Libratus beats top professionals
复制标题
DOI：
10.1126/science.aao1733
复制
发表时间：
2018-01-26
期刊：
影响因子：
56.9
通讯作者：
Sandholm, Tuomas
中科院分区：
文献类型：
--
作者：
Brown, Noam;Sandholm, Tuomas
无限制的德克萨斯州Hold'em是最受欢迎的扑克形式。尽管人工智能（AI）在完美的信息游戏中取得了成功，但私人信息和大量游戏树还是很难解决限制扑克。我们提出了Libratus，这是一个AI，在一项120,000个手竞争中，在不限于Texas Holdem中击败了四名顶级人类专业专业人员，这是不完美的信息求解中领先的基准和长期存在的挑战问题。我们的游戏理论方法具有与应用程序无关的技术：一种用于计算整体策略蓝图的算法，一种算法充实了游戏过程中所达到的子游戏策略的细节，以及一种自我冲击算法，可以解决潜在的弱点对手在蓝图策略中已经确定了。
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.