By Thor Olavsrud
In the battle of man vs. machine, heads-up no-limit Texas hold’em may be the next new frontier. Artificial intelligence (AI), developed by a Carnegie Mellon University professor and a PhD student, is taking on four of the top pros in the world to show that AI can master games of imperfect information.
Thor Olavsrud writes, “For decades, researchers have been pitting [AI] against the top game players in the world. The heads-up no-limit Texas hold’em variant of poker may be the final frontier in the battle of man vs. machine over games. And it may be about to fall.
“In 1997, IBM chess computer Deep Blue defeated world chess champion Garry Kasparov. In 2011, IBM Watson defeated Ken Jennings and Brad Ruttner, the two winningest Jeopardy players in that game show’s history. In 2015, Google DeepMind’s AlphaGo defeated South Korean professional Go player Lee Sedol, considered one of the best players in the world.
“But as games go, heads-up no-limit Texas hold’em is an entirely different beast. Unlike the others, it is a game of imperfect information—the players know only some of the cards in play, and they can bluff and use other ploys to mislead their opponents. Tuomas Sandholm, computer science professor at Carnegie Mellon University, says the game features 10161 information sets, significantly more than all the atoms in the universe. Limit hold’em, which restricts bets and raises to a predetermined amount, has 1013 information sets.
“‘For a given game size, incomplete information games are much harder to solve than complete information games,’ Sandholm says. ‘In complete information games, it’s basically decomposable. You can solve what’s best to do just by looking at the end game. But if I’m in an end game where I have four aces, I can’t just bet aggressively. And I can’t just bet weakly when I have a weak hand. That would be too transparent. You have to balance across the subgames and therefore the problem is not decomposable.’”
Also, in case you hadn’t heard, the AI won. Read all about it.