Premium
This is an archive article published on February 3, 2017

AI programme named Libratus beats 4 professional human players in poker marathon

A computer system has successfully beaten four human players in a poker marathon match lasting 20 days.

AI, Libratus, Carnegie Mellon AI, Texas Hold em Poker, Pro Poker player, Head up no limit Texas hold' em, landmark in AI gameplay,  video games, Gaming, gambling, Science, Science news This provs the ability of AI to do strategy and reasoning, there are many potential applications in the future. (Source: Youtube)

In a significant milestone for artificial intelligence, a computer system has successfully beaten four human players in a poker marathon match lasting 20 days, winning more than USD 1.5 millions worth of chips.

Libratus, an AI programme developed at Carnegie Mellon University in the US, was trained to play a variant of the game known as no-limit heads-up Texas hold ’em.

Watch all our videos from Express Technology

“Heads-up no limit Texas hold ’em is in a way the last frontier of all the games,” said Tuomas Sandholm, professor at Carnegie Mellon University. “Othello, Chess, Go, Jeopardy have all been conquered, but this remained elusive: this is a landmark in AI game-play,” said Sandholm.

Story continues below this ad

The algorithm used in the system could be transferred to a range of other uses including negotiations, finance, medical treatment and cybersecurity, he added. “Now we have proven the ability of AI to do strategy and reasoning, there are many potential applications in future,” Sandholm was quoted as saying by ‘BBC News’.

One of the professional poker players, Jimmy Chou, admitted that the AI was proving a tough opponent. “The bot gets better and better every day. It’s like a tougher version of us,” he said.

Also Read: New AI system can understand, see like humans

“The first couple of days, we had high hopes. But every time we find a weakness, it learns from us and the weakness disappears the next day,” Chou said.

Latest Comment
Post Comment
Read Comments
Advertisement
Loading Taboola...
Advertisement