No limit: AI poker bot is first to beat professionals at multiplayer game

Triumph over five human opponents at Texas hold’em brings bots closer to solving complicated real-world problems.

Go to the profile of Nature Research
Aug 05, 2019
0
0

Machines have raised the stakes once again. A superhuman poker-playing bot called Pluribus has beaten top human professionals at six-player no-limit Texas hold’em poker, the most popular variant of the game. It is the first time that an artificial-intelligence (AI) program has beaten elite human players at a game with more than two players.

The team behind Pluribus had already built an AI, called Libratus, that had beaten professionals at two-player poker. Other AIs that have mastered human games — such as Libratus and DeepMind’s Go-playing bots — have shown that they are unbeatable in two-player zero-sum matches. In these scenarios, there is always one winner and one loser, and game theory offers a well-defined best strategy.

But game theory is less helpful for situations involving multiple parties with competing interests and no clear win–lose conditions — which reflect most real-life challenges. By solving multiplayer poker, Pluribus lays the foundation for future AIs to tackle complex problems of this sort, says Noam Brown at Carnegie Mellon University in Pittsburgh, Philadelphia, and Facebook AI Research in New York, who developed Pluribus with his Carnegie colleague Tuomas Sandholm. 

He thinks that their success is a step towards applications such as automated negotiations, better fraud detection and self-driving cars.

By: Douglas Heaven/Nature News

No comments yet.