CMU’s Libratus wins the Poker Tournament Against the Humans
Mellon University Artificial Intelligence Libratus has won the Heads-up
No-Limit Texas Hold’em tournament against the best “world’s best professional
poker players” – Dong Kim, Jimmy Chou, Daniel McAulay and Jason Les. “The best
AI’s ability to do strategic reasoning with imperfect information has now
surpassed that of the best humans,” said Tuomas Sandholm, professor of Computer
Science and co-creator of the AI.
The tournament took
place at Rivers Casino in Pittsburgh and streamed live in the Twitch online
platform for 20 days, from January 11 to 31, 2017. After 120,000-hands, Libratus
beat the four pros, with $1,766,250 in chips.
The humans played
the AI for 11 hours a day at a nearly constant pace, gathering to talk strategy
after each day. But the AI didn’t originally know how to play poker. It was
instructed to try things at random until, after trillions of hands, it learned
a winning strategy.
can’t win at poker if it can’t bluff,” said Frank Pfenning, head of the CMU
Computer Science Department and Carnegie Mellon Portugal PI and Ph.D. advisor.
“Developing an AI that can do that successfully is a tremendous step forward
scientifically and has numerous applications. Imagine that your smartphone will
someday be able to negotiate the best price on a new car for you. That’s just
Portuguese article at Pokerpt.com (January 31, 2017), Rádio Renascença Online, Sapo Tek Online (February 2, 2017), and Jornal de Negócios Online (February 4, 2017). The
article is also available in English at TechCrunch
and Carnegie Mellon University News (January 31, 2017).