Superhuman AI for multiplayer poker

被引:522
作者
Brown, Noam [1 ,2 ]
Sandholm, Tuomas [1 ,3 ,4 ,5 ]
机构
[1] Carnegie Mellon Univ, Dept Comp Sci, Pittsburgh, PA 15213 USA
[2] Facebook AI Res, New York, NY 10003 USA
[3] Strateg Machine Inc, Pittsburgh, PA 15213 USA
[4] Strategy Robot Inc, Pittsburgh, PA 15213 USA
[5] Optimized Mkt Inc, Pittsburgh, PA 15213 USA
基金
美国国家科学基金会;
关键词
GAME; GO;
D O I
10.1126/science.aay2400
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
070301 [无机化学]; 070403 [天体物理学]; 070507 [自然资源与国土空间规划学]; 090105 [作物生产系统与生态工程];
摘要
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.
引用
收藏
页码:885 / +
页数:36
相关论文
共 48 条
[1]
[Anonymous], 2016, AAAI C ART INT
[2]
[Anonymous], 2017, P ADV NEUR INF PROC
[3]
[Anonymous], INT C AUT AG MULT SY
[4]
[Anonymous], NEURAL INFORM PROCES
[5]
[Anonymous], INT C AUT AG MULT SY
[6]
[Anonymous], INT JOINT C ART INT
[7]
[Anonymous], AAAI C ART INT AAAI
[8]
[Anonymous], ACM T EC COMP TEAC
[9]
[Anonymous], 2017, WORKSH 31 AAAI C ART
[10]
[Anonymous], P AAAI C ART INT AAA