Gaming research has contributed significantly to the development of artificial intelligence over the last few decades. Now the Computer Poker Research Group at the University of Alberta in Canada has reached a new milestone: solving heads-up limit hold’em poker.
“Poker has been a challenge problem for artificial intelligence going back over 40 years, and until now, heads-up limit Texas hold’em poker was unsolved,” says Michael Bowling, lead author of the gaming research which was published January 9 in Science.
Poker is a family of games that exhibit imperfect information, where players do not have full knowledge of past events. These games are more challenging, with theory, computational algorithms, and instances of solved games lagging behind results in the perfect information setting. And, while perfect information may be a common property of parlor games, it is far less common in real-world decision making settings.
Many perfect information games have already been solved, but the researchers say this is the first time a nontrivial imperfect information game that is played competitively by humans has been solved.
“The breakthroughs behind this result are general algorithmic advances that make game-theoretic reasoning in large-scale models of any sort more tractable,” says Bowling.
With real-life decision-making settings almost always involving uncertainty and missing information, algorithmic advances, such as those needed to solve poker, are needed to drive future applications. Ultimately, the algorithmic advances outlined in the research could have significant implications for other arenas in which artificial intelligence is used, including the development of thoughtful robots.