More Bad News for Gamblers – AI Wins…Again
AI-based poker playing programs have been upping the ante for lowly humans. Notably, several algorithms from Carnegie Mellon University (e.g. Libratus, Claudico, and Baby Tartanian8) have performed well. Writing in Science last week, researchers from the University of Alberta, Charles University in Prague and Czech Technical University report their poker algorithm – DeepStack – is the first computer program to beat professional players in Heads-up No-limit Texas Hold ’Em (HUNL).
Sorting through the “firsts” is tricky in the world of AI game playing programs. What sets DeepStack apart, say the researchers, is its more realistic approach, at least in games such as poker where all factors are never fully known – think bluffing, for example. HUNL is a two-player version of poker in which two cards are initially dealt face down to each player, and additional cards are dealt face-up in three subsequent rounds. No limit is placed on the size of the bets although there is an overall limit to the total amount wagered in each game.
“Poker has been a longstanding challenge problem in artificial intelligence,” says Michael Bowling, professor in the University of Alberta’s Faculty of Science and principal investigator on the study. “It is the quintessential game of imperfect information in the sense that the players don’t have the same information or share the same perspective while they’re playing.”
Using GTX 1080 GPUs and CUDA with the Torch deep learning framework, “we train our system to learn the value of situations,” says Bowling on an NVIDIA blog. “Each situation itself is a mini poker game. Instead of solving one big poker game, it solves millions of these little poker games, each one helping the system to refine its intuition of how the game of poker works. And this intuition is the fuel behind how DeepStack plays the full game.”
The entire article can be found on our sister site HPCwire.