Computer Science Department, Carnegie Mellon University, Pittsburgh, PA 15213, USA.
Facebook AI Research, New York, NY 10003, USA.
Science. 2019 Aug 30;365(6456):885-890. doi: 10.1126/science.aay2400. Epub 2019 Jul 11.
In recent years there have been great strides in artificial intelligence (AI), with games often serving as challenge problems, benchmarks, and milestones for progress. Poker has served for decades as such a challenge problem. Past successes in such benchmarks, including poker, have been limited to two-player games. However, poker in particular is traditionally played with more than two players. Multiplayer games present fundamental additional issues beyond those in two-player games, and multiplayer poker is a recognized AI milestone. In this paper we present Pluribus, an AI that we show is stronger than top human professionals in six-player no-limit Texas hold'em poker, the most popular form of poker played by humans.
近年来,人工智能(AI)取得了巨大的进展,游戏通常作为挑战问题、基准和进展的里程碑。扑克几十年来一直是这样的挑战问题。在这些基准测试中取得的过去的成功,包括扑克,仅限于两人游戏。然而,扑克传统上是由两个以上的玩家进行的。多人游戏除了在两人游戏中存在的问题之外,还存在基本的额外问题,而多人扑克是人工智能的一个公认的里程碑。在本文中,我们介绍了 Pluribus,一个在六人无限制德州扑克中比顶级人类专业人士更强的 AI,这是人类最常玩的扑克形式。