AI program beats pros in six-player poker

Ceria Alfonso
Julio 14, 2019

"Pluribus is a very hard opponent to play against", Ferguson said. Poker sites are actively working to detect and root out possible bots. There is nothing to fear. While he typically takes on humans, he faced a daunting new opponent in June: a powerful bot developed by researchers at Carnegie Mellon University and Facebook AI Research to trounce the world's top players.

But the tables turned overnight as an algorithm trained by the might of Facebook AI and Carnegie Mellon University beat the poker professionals at the latest showdown in Texas.

Research co-author Noam Brown, of Facebook AI said: "We're elated with its performance and believe some of Pluribus" playing strategies might even change the way pros play the game'. So scientists tried a different experiment in which they put one bot up against a full table of pro players. As the AI plays, it figures out what actions lead to better outcomes. Think of it like sitting down in a live poker room with four complete strangers and a computer.

So that the poker pros would play seriously, $50,000 in prize money was divvied up.

Another thing worth noting is that Pluribus is a way cheaper AI bot compared to the many expensive ones out there, and this just adds onto its pile of achievement. Players were initially asked to play on four tables at a time, but the players themselves requested that be increased to six tables at a time. And it went against conventional poker wisdom by determining that a strategy known as "donk betting", where a player begins a round by betting after ending the previous round with a call, could be a good play.

According to Brown, the final major milestone for AI bots was progressing from a two-player poker game to multiple players. To translate, that is 48 big blinds per thousand hands, or 4.8 big blinds per hundred.

In a game with more than two players, playing a Nash equilibrium can be a losing strategy. Pluribus eventually stopped limping as it became a stronger player. They included Chris Ferguson, Greg Merson, Darren Elias and Jimmy Chou. They were paid $2,000 each and whichever did better than the other against the AI received an additional $2,000.

More news: Young Thug And Mason Ramsey Join The Old Town Road Remix

For one, it's a multiplayer game, not mano a mano like the others.

Not only did it call its opponent's bluff, it was brilliant at bluffing itself.

AI in gaming has come a long way since the IBM Deep Blue computer famously beat a professional player in a six-game chess match for the first time in 1997.

Computers have been surpassing humans in one game after another, with checkers, chess, go and some competitive video games like Starcraft 2 already conquered. There were options for Pluribus to veer from its bet restrictions if necessary.

Michael Wellman, a professor at the University of MI who focuses on game theory, said Pluribus's success against human players is a pretty big deal. A forerunner of Pluribus named Libratus made its name two years ago by trouncing top human players, but that program only played one-on-one.

'The ability to beat five other players in such a complicated game opens up new opportunities to use AI to solve a wide variety of real-world problems'.

The bot was excellent at varying its strategy even when dealt the exact same hand, Elias says, "which is pretty tough to play against because you can't really pick up a pattern". "And that's what makes it so hard to play against", said one of the humans, Jason Les.

Otros informes por

Discuta este artículo

SIGUE NUESTRO PERIÓDICO