AI program beats pros in six-player poker -- a first

Remigio Civitarese
Luglio 14, 2019

As announced via a press release, the AI system named Pluribus was able to defeat 12 of the best Poker players in the popular six-player no-limit Texas Hold'em poker format. The list of professionals included four-time World Poker Tour champion Darren Elias and 14 other players who have won world championships or taken home more than $1 million in prizes. Then, when playing against humanopponents, Pluribus improves the blueprint strategy by searching in real time for a strategy that better suits the circumstances of the current game.

It is the latest milestone marking the superior powers of machines over people and the first time a computer has beaten more than one opponent in a complex game of strategy and calculation.

There were two different experiments conducted by Pluribus' creators, Noam Brown and Tuomas Sandholm of Carnegie Mellon University.

Pluribus is the world's most evolved Poker AI developed by Carnegie Mellon University and Facebook AI research scientists.

A research paper describing the way Pluribus was made, has been published today by the journal Science.

That didn't work in six-player poker games like no-limit Texas Hold 'em, Brown says.

Computers have been surpassing humans in one game after another, with checkers, chess, go and some competitive video games like Starcraft 2 already conquered.

Pluribus' algorithms created some surprising features in its strategy.

One surprise was that Pluribus used "donk betting" - ending one round with a call and starting the next with a bet - far more than would the pros, who traditionally see the move as a weak one. It used wildly differing bet sizes, a strategy humans seem to find hard to do. "It was incredibly fascinating getting to play against the poker bot and seeing some of the strategies it chose", Michael Gagliano said.

Why it matters: Yet again, artificial intelligence has shown its superiority over us mere mortals when it comes to humanity's favorite games.

The easiest way to quantify how well Pluribus did was by how much money it was winning. Each player was given an anonymous screen name so that the players did not know who the actual human was behind the names and thus have an advantage based on the knowledge of a human player's lifetime tendencies.

Michael "Gags" Gagliano, who has earned almost $2 million in career earnings, also competed against Pluribus. Pluribus needed just 20 hours to learn to play to the level of a poker professional, according to the report. "There were several plays that humans simply are not making at all, especially relating to its bet sizing. Bots/AI are an important part in the evolution of poker, and it was unbelievable to have first-hand experience in this large step toward the future".

Over the past 16 years, Sandholm has been researching poker as an insight into AI strategy at his lab.

The AI, called Pluribus, defeated Darren Elias, the holder of the record for most World Poker Tour titles, and Chris "Jesus" Ferguson, victor of six World Series of Poker events. Often, games serve as challenge problems, benchmarks, and milestones for this progress.

In the likes of chess and Go, everything is laid out in the open.

A computer has beaten five of the world's champion players at poker - a game once thought too hard for machines to master. That makes it both a tougher AI challenge and more relevant to many real-world problems involving multiple parties and missing information. Multi-player games present fundamental additional issues for AI beyond those in two-player games.

Take, for example, Nash equilibrium: so long as your opponent's strategy remains the same, you won't benefit from changing yours.

AI in two-player games tends to approximate a Nash equilibrium, guaranteeing that only a result no worse than a tie, and AI emerges victorious once its opponent errs and can not maintain the equilibrium. Pluribus also uses less than 128 GB of memory.

Pluribus learned poker by playing copies of itself. For a start, Pluribus has an online search algorithm to look for ahead for options.

Pluribus registered a solid win, and Mr Elias said 'The bot wasn't just playing against some middle of the road pros.

Pluribus also thrives on unpredictability. Limping means making the smallest bet possible to stay in the hand, instead of raising or folding.

Altre relazioniGrafFiotech

Discuti questo articolo

Segui i nostri GIORNALE