AI-driven bot beats professionals in 6-player poker

Poker players, get set to lose millions to a bot! In a first, an Artificial Intelligence (AI) programme developed by Carnegie Mellon University in collaboration with Facebook AI has defeated leading professionals in a six-player poker The AI, called "Pluribus", defeated poker professional Darren Elias who holds the record for most "World Poker Tour" titles, and Chris "Jesus" Ferguson, winner of six "World Series of Poker" events at "no-limit Texas hold'em" -- the world's most popular form of poker.

Each professional separately played 5,000 hands of poker against five copies of Pluribus.

In another experiment involving 13 pros, all of whom have won more than $1 million playing poker, Pluribus played five pros at a time for a total of 10,000 hands and again emerged victorious.

"Pluribus achieved super-human performance at multi-player poker, which is a recognized milestone in AI and in game theory that has been open for decades," said Tuomas Sandholm, Angel Jordan Professor of Computer Science, who developed Pluribus with Noam Brown, who is finishing his PhD at Carnegie Mellon as a research scientist at Facebook AI.

"Playing a six-player game rather than head-to-head requires fundamental changes in how the AI develops its playing strategy," said Brown, who joined Facebook AI last year.

Pluribus' algorithms created some surprising features into its strategy.

For instance, most human players avoid "donk betting" -- that is, ending one round with a call but then starting the next round with a bet. It's seen as a weak move that usually doesn't make strategic sense.

Pluribus, however, placed donk bets far more often than the professionals it defeated.

Pluribus registered a solid win with statistical significance, which is particularly impressive given its opposition.

"The bot wasn't just playing against some middle of the road pros. It was playing some of the best players in the world," said the researchers.

Michael "Gags" Gagliano, who has earned nearly $2 million in career earnings, also competed against Pluribus.

"It was incredibly fascinating getting to play against the poker bot and seeing some of the strategies it chose," said Gagliano.

Sandholm and Brown earlier developed Libratus, which two years ago decisively beat four poker pros playing a combined 120,000 hands of heads-up at two-player version of the game.

Though poker is an incredibly complicated game, Pluribus made efficient use of computation. Pluribus computed its blueprint strategy in eight days using only 12,400 core hours and used just 28 cores during live play.

"Thus far, superhuman AI milestones in strategic reasoning have been limited to two-party competition. 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," said Sandholm in a paper published in the journal Science.