Robot defeats world's top poker players in breakthrough for Artificial Intelligence

Joanna Estrada
July 12, 2019

Chalk up another victory for machines.

An artificial intelligence (AI) program has defeated leading professionals in six-player Texas hold'em poker, making a superhuman AI milestone in a multi-party competition. But a game like poker, specifically six-player Texas Hold 'em, has been too tough for a machine to master - until now.

In poker, however, you can't know all the information that your opponent knows, so it's more hard to anticipate what moves they may make - and it only gets more hard the more players you have. He'd take on four tables full of them at a time, and he'd alert the computer scientists who designed the bot when it made a mistake. The system was trained by having the AI play the game against copies of itself, without knowing how to play the game and improving as it went.

"The bot wasn't just playing against some middle-of-the-road pros", said Elias in a Facebook blog post. Pluribus defeated the humans in games where five AIs and one human played, and in games involving Pluribus and five human players. And it won again.

The overall strategy led Pluribus to beat some of the best players of the game for the first time, the researchers announce Thursday in the journal Science.

The easiest way to quantify how well Pluribus did was by how much money it was winning.

In 10,000 hands of poker, Pluribus played against five copies of itself versus one top-class professional player, as well as five top-class professional poker players versus one version of itself.

The program runs on two Intel Haswell processors and uses a modest 128GB during play. Previous groundbreaking poker bots focused on a few different kinds of two-player poker. "No other popular recreational game captures the challenges of hidden information as effectively and as elegantly as poker". From that point on, Pluribus does a more detailed search of possible moves in a finer-grained abstraction of game.

As a result, it's a lot more efficient than many other AI game-playing bots. But even though there's no fail-safe strategy to win, Brown says, Pluribus still outperforms the best humans. The cards are hidden.

"Its major strength is its ability to use mixed strategies", Elias said last week as he prepared for the 2019 World Series of Poker main event.

Scientists have developed AI that can beat top human poker players in a six-player tournament. "Which is something that humans could probably do a little more".

Pluribus also confirmed something that many poker pros already suspected - "limping" is nearly never a good strategy.

"Pluribus is a very hard opponent to play against", Ferguson said. He clarified that the code created in collaboration with Facebook for Pluribus can only be used in poker, and therefore has no military applications. "Most people just can't". "The bots will always be better than us".

"It's the first time AI has achieved superhuman performance in a multiplayer game", said Tuomas Sandholm, who developed Pluribus with his PhD student Noam Brown at Carnegie Mellon University in Pittsburgh. "It was incredibly fascinating getting to play against the poker bot and seeing some of the strategies it chose", Michael Gagliano said. A successful bluff can dramatically change a poker game in your favor, but do it too much and your deception becomes predictable. Brown says their AI technology could eventually be useful in other situations where there are multiple people involved and a lot of unknown variables, like getting a self-driving auto through traffic.

Other reports by Click Lancashire

Discuss This Article