DeepStack, created by researchers at the University of Alberta in Canada, bridges the gap between approaches used for games of perfect information – such as chess and Go where players can see everything on the board – with those used for imperfect information games by reasoning while it plays, using “intuition” honed through deep learning to reassess its strategy with each decision.

“Poker has been a long-standing challenge problem in artificial intelligence,” said Michael Bowling, professor at the University of Alberta.

“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,” said Bowling.

AI researchers have long used parlour games to test their theories because the games are mathematical models that describe how decision-makers interact.

DeepStack extends the ability to think about each situation during play to imperfect information games using a technique called continual re-solving.

This allows DeepStack to determine the correct strategy for a particular poker situation by using its “intuition” to evaluate how the game might play out in the near future without thinking about the entire game.

“We train our system to learn the value of situations. Each situation itself is a mini poker game,” said Bowling.

“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,” he said.

Thinking about each situation as it arises is important for complex problems like heads-up no-limit hold’em, which has vastly more unique situations than there are atoms in the universe, largely due to players’ ability to wager different amounts including the dramatic “all-in.”

Despite the game’s complexity, DeepStack takes action at human speed with an average of only three seconds of “thinking” time – and runs on a simple gaming laptop.

To test the approach, DeepStack played last December against a pool of professional poker players recruited by the International Federation of Poker.

Thirty-three players from 17 countries were asked to play a 3,000-hand match over a period of four weeks. DeepStack beat each of the 11 players who finished their match, with only one outside the margin of statistical significance.

It is a historic result in artificial intelligence (AI) that has implications far beyond the poker table, from helping make more robust medical treatment recommendations to developing better strategic defence planning.