Skip to main content


Poker AI: Libratus and an Introduction to Counterfactual Regret Minimization

In 2017, a poker playing AI developed by researchers at Carnegie Mellon defeated 4 top heads up no limit hold 'em players in a 120,000 hand challenge. In this video, Wade introduces counterfactual regret minimization, one of the algorithms that Libratus was built on, along with a simple CFR example for rock, paper, scissors.

Project Members: Wade Gong