Nav: Home

At last, an AI that outperforms humans in six-player poker

July 11, 2019

Achieving a milestone in artificial intelligence (AI) by moving beyond settings involving only two players, researchers present an AI that can outperform top human professionals in six-player no-limit Texas hold'em poker, the most popular form of poker played today. This system is the only AI to have bettered professional poker players at this multi-player game. In recent years, researchers have reported great strides in artificial intelligence. Often, games serve as challenge problems, benchmarks, and milestones for this progress. Past successes in such benchmarks, including in poker, have largely been limited to two-player games, however - even as poker in particular is traditionally played with more than two players. Multi-player games present fundamental additional issues for AI beyond those in two-player games. Here, applying approaches including "action abstraction" and "information abstraction" to overcome some of these issues, and in particular to reduce the number of different actions the AI needs to consider, Noam Brown and Tuomas Sandholm developed a program - dubbed Pluribus - that learned how to play six-player no-limit Texas hold'em by playing against five copies of itself. When pitted against five elite professional poker players, or with five copies of Pluribus playing against one professional, the computer performed significantly better over 10,000 hands of poker. Pluribus confirms the conventional human wisdom, say the authors, that limping (calling the "big blind" rather than folding or raising) is suboptimal for any player except the "small blind" player who already has half the big blind in the pot by the rules, and thus has to invest only half as much as the other players to call. The findings will be published during the week the 50th Edition of the World Series of Poker Main Event begins.
-end-


American Association for the Advancement of Science

Related Artificial Intelligence Articles:

Predicting molecular bond energy by artificial intelligence
Theoretical prediction of molecular bond energy is of key importance for understanding molecular properties.
Artificial intelligence: Towards a better understanding of the underlying mechanisms
The automatic identification of complex features in images has already become reality thanks to artificial neural networks.
Using artificial intelligence to analyze placentas
A team of researchers has developed a novel solution that could produce accurate, automated and near-immediate placental diagnostic reports through computerized photographic image analysis.
Using artificial intelligence to determine whether immunotherapy is working
Currently, only about 20% of all cancer patients will actually benefit from costly immunotherapy.
Artificial intelligence to run the chemical factories of the future
A new proof-of-concept study details how an automated system driven by artificial intelligence can design, build, test and learn complex biochemical pathways to efficiently produce lycopene, a red pigment found in tomatoes and commonly used as a food coloring, opening the door to a wide range of biosynthetic applications, researchers report.
How artificial intelligence can transform psychiatry
Scientists have developed a new mobile app that categorizes mental health status based on speech patterns.
Artificial intelligence system gives fashion advice
A University of Texas at Austin-led computer science team has developed an artificial intelligence system that can look at a photo of an outfit and suggest helpful tips to make it more fashionable.
Do we trust artificial intelligence agents to mediate conflict? Not entirely
We may listen to facts from Siri or Alexa, or directions from Google Maps or Waze, but would we let a virtual agent enabled by artificial intelligence help mediate conflict among team members?
Artificial intelligence improves biomedical imaging
ETH researchers use artificial intelligence to improve quality of images recorded by a relatively new biomedical imaging method.
Evolution of learning is key to better artificial intelligence
Researchers at Michigan State University say that true, human-level intelligence remains a long way off, but their new paper published in The American Naturalist explores how computers could begin to evolve learning in the same way as natural organisms did -- with implications for many fields, including artificial intelligence.
More Artificial Intelligence News and Artificial Intelligence Current Events

Top Science Podcasts

We have hand picked the top science podcasts of 2019.
Now Playing: TED Radio Hour

In & Out Of Love
We think of love as a mysterious, unknowable force. Something that happens to us. But what if we could control it? This hour, TED speakers on whether we can decide to fall in — and out of — love. Guests include writer Mandy Len Catron, biological anthropologist Helen Fisher, musician Dessa, One Love CEO Katie Hood, and psychologist Guy Winch.
Now Playing: Science for the People

#543 Give a Nerd a Gift
Yup, you guessed it... it's Science for the People's annual holiday episode that helps you figure out what sciency books and gifts to get that special nerd on your list. Or maybe you're looking to build up your reading list for the holiday break and a geeky Christmas sweater to wear to an upcoming party. Returning are pop-science power-readers John Dupuis and Joanne Manaster to dish on the best science books they read this past year. And Rachelle Saunders and Bethany Brookshire squee in delight over some truly delightful science-themed non-book objects for those whose bookshelves are already full. Since...
Now Playing: Radiolab

An Announcement from Radiolab