UAlberta researchers solve heads-up limit Texas hold ‘em poker.
In a world first, researchers in the Computer Poker Research Group at the University of Alberta have essentially solved heads-up limit Texas hold ‘em poker with their program, called Cepheus.
“Poker has been a challenge problem for artificial intelligence going back over 40 years, and until now, heads-up limit Texas hold ‘em poker was unsolved,” says Michael Bowling, lead author and professor in the Faculty of Science, whose findings were published Jan. 9 in the journal Science.
For more than a half-century, games have been test beds for new ideas in artificial intelligence. The resulting successes have marked significant milestones, from IBM’s Deep Blue defeating world champion Garry Kasparov in chess and Watson beating top-earning Jeopardy! champs Ken Jennings and Brad Rutter.
But as Bowling points out, defeating top human players is not the same as actually solving a game—especially a game like poker.
The challenge of imperfect information
In poker, players have imperfect information—they don’t have full knowledge of past events, and they can’t see their opponents’ hands. The most popular variant of poker today is Texas hold ‘em. When it is played with just two players and with fixed bet sizes and a limited number of raises allowed, it is called heads-up limit hold ‘em.
The possible situations in this poker version are fewer than in checkers—which U of A computing science researchers solved in 2007, led by now dean of science Jonathan Schaeffer—but the imperfect-information nature of heads-up limit hold ‘em makes it a far more challenging game for computers to play or solve.
“We define a game to be essentially solved if a lifetime of play is unable to statistically differentiate it from being solved at 95% confidence,” explains Bowling. “Imagine someone playing 200 hands of poker an hour for 12 hours a day without missing a day for 70 years. Furthermore, imagine them employing the worst-case, maximally exploitive opponent strategy—and never making a mistake. They still cannot be certain they are actually winning.”
Read more: Poker-playing program knows when to fold ’em
The Latest on: Artificial intelligence
[google_news title=”” keyword=”Artificial intelligence” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Artificial intelligence
- Pope to bring his call for ethical artificial intelligence to G7 summit in June in southern Italyon April 26, 2024 at 10:26 am
Pope Francis is taking his call for artificial intelligence to be developed and used according to ethical lines to the Group of 7 industrialized nations
- Google parent Alphabet hits $2tn valuation as it announces first dividendon April 26, 2024 at 7:27 am
Tech company’s shares rise as it plans to reward investors after strong quarterly results
via Bing News