Superhuman AI for multiplayer poker

  • Noam Brown
    Computer Science Department, Carnegie Mellon University, Pittsburgh, PA 15213, USA.
  • Tuomas Sandholm
    Computer Science Department, Carnegie Mellon University, Pittsburgh, PA 15213, USA.

説明

<jats:title>AI now masters six-player poker</jats:title> <jats:p>Computer programs have shown superiority over humans in two-player games such as chess, Go, and heads-up, no-limit Texas hold'em poker. However, poker games usually include six players—a much trickier challenge for artificial intelligence than the two-player variant. Brown and Sandholm developed a program, dubbed Pluribus, that learned how to play six-player no-limit Texas hold'em by playing against five copies of itself (see the Perspective by Blair and Saffidine). When pitted against five elite professional poker players, or with five copies of Pluribus playing against one professional, the computer performed significantly better than humans over the course of 10,000 hands of poker.</jats:p> <jats:p> <jats:italic>Science</jats:italic> , this issue p. <jats:related-article xmlns:xlink="http://www.w3.org/1999/xlink" ext-link-type="doi" issue="6456" page="885" related-article-type="in-this-issue" vol="365" xlink:href="10.1126/science.aay2400">885</jats:related-article> ; see also p. <jats:related-article xmlns:xlink="http://www.w3.org/1999/xlink" ext-link-type="doi" issue="6456" page="864" related-article-type="in-this-issue" vol="365" xlink:href="10.1126/science.aay7774">864</jats:related-article> </jats:p>

収録刊行物

  • Science

    Science 365 (6456), 885-890, 2019-08-30

    American Association for the Advancement of Science (AAAS)

被引用文献 (2)*注記

もっと見る

問題の指摘

ページトップへ