An AI system called DeepStack has beaten professional human players at no-limit Texas hold ’em Poker for the first time in history making its landmark in artificial intelligence research. This achievement was recently published in Science magazine by a team of researchers led by Michael Bowling from University of Alberta’s Computer Poker Research Group. This ten-man team also included three Czech Scientists – Matej Moravčík, Martin Schmid and Viliam Lisý from Charles University and Czech Technical University in Prague.
DeepStack bridges the gap between approaches used for games of perfect information—like those used in checkers, chess, and Go where both 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.
More information in the news post at University of Alberta website.