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
via Google News
The Latest on: Artificial intelligence
- Wolters Kluwer Partners with Clifford Chance Paris to Host Artificial Intelligence and International Arbitration Webinaron December 2, 2020 at 8:04 am
Panelists from Wolters Kluwer Legal & Regulatory U.S., Google and Clifford Chance Paris will participate in an exciting digital discussion on artificial intelligence (AI) and international arbitration ...
- Artificial Intelligence in Healthcare Market 2021 Global Industry Size, Demand, Growth Analysis, Share, Revenue and Forecast 2029on December 2, 2020 at 6:42 am
The research study on Global Artificial Intelligence in Healthcare market 2019 presents an extensive analysis of ...
- Artificial Intelligence: Leadership’s Friend Or Foe?on December 2, 2020 at 5:20 am
Leaders should not see artificial intelligence as a threat to organizational purpose, but rather a support for leaders to have the time and space to engage with aspects of their higher purpose.
- Preparing Leaders For The Artificial Intelligence Ageon December 2, 2020 at 4:50 am
The power and promise of AI to augment decision-making is impressive, but there are a few things leaders need to keep in mind in order to leverage the tech successfully.
- How Artificial Intelligence Can Aid Inventors To Prevent Idea Thefton December 2, 2020 at 2:40 am
AI can be used to compare your idea against competitors' products and it can automate the patent process by decreasing cost and increasing access.
- O3 Mining Identifies New Targets Confirming Validity of Artificial Intelligence Targetingon December 2, 2020 at 2:00 am
PRNewswire/ - O3 Mining Inc. (TSXV: OIII) ("O3 Mining" or the "Corporation") is pleased to provide results from its completed summer channel sampling ...
- EPM partners with the Artificial Intelligence Group to improve its cloud-based Ai solutionson December 1, 2020 at 9:01 pm
EPM UAE, in an official statement, announced that the company has entered into a partnership with the Artificial Intelligence group and shall now act as their official product distributor within the ...
- Artificial Intelligence Risk Is Topic Of Great Valley Researchon December 1, 2020 at 6:38 pm
Four professors at Penn State Great Valley are researching risks and vulnerabilities in artificial intelligence.
- Global Artificial Intelligence Market 2020 Scope of the Report, Challenges and Trends, Key Regions and Key Players Analysis by 2025on December 1, 2020 at 2:47 pm
MarketQuest.biz has recently published Global Artificial Intelligence Market 2020 by Company, Regions, Type and Application, Forecast to 2025, assuming the historical data of the market to forecasts ...
- iHealthScreen’s Artificial Intelligence (AI) Based Tool Can Accurately Diagnose Age-Related Macular Degeneration (AMD) and Help Prevent Blindnesson November 30, 2020 at 10:39 pm
AMD, with no early signs or symptoms, is a leading cause of adult blindness in the developed world. Early detection can enable preventative measures in time and stop AMD incident. Currently, AMD ...
via Bing News