Carnegie Mellon’s AI system beats top poker players

A new AI system created by researchers at Carnegie Mellon beat four of the ''world's best professional poker players'' – Dong Kim, Jimmy Chou, Daniel McAulay and Jason Les. The AI played the humans in a 20-day 120,000-hand Heads-up No-Limit Texas Hold'em binge held live on a casino floor in Pittsburgh.

At the end of the experiment, the AI, called Libratus, was up $1,766,250 in chips when it finally beat the four pros in a competition at Rivers Casino. The play continued almost constantly with the players  conferring on strategy after each day of play.

The AI did not originally know how to play poker and was told by the researchers to try things at random until, after trillions of hands, it learned a winning strategy. The humans played Libratus for 11 hours a day, finishing at 10pm every night, for twenty days.

''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, techcrunch.com reported.

McAulay, one of the human players, said that ''Libratus was a tougher opponent than he expected.''

''Whenever you play a top player at poker, you learn from it,'' he said.

According to commentators, it was a crushing defeat for humans, but a major milestone for artificial intelligence.

Machines had already become smart enough to beat humans at other games such as chess and Go, but poker was more difficult due to the imperfect nature of the information.

With chess and Go, the entire board can be seen by the players, but with poker, players do not get to see each other's hands. Also the AI was required to bluff and correctly interpret misleading information in order to win.