For almost three weeks, Dong Kim sat at a casino in Pittsburgh and played poker against a machine. But Kim wasn’t just any poker player. This wasn’t just any machine. And it wasn’t just any game of poker.
Kim, 28, is among the best players in the world. The machine, built by two computer science researchers at Carnegie Mellon, is an artificially intelligent system that runs on a Pittsburg supercomputer. And for twenty straight days, they played no-limit Texas Hold ‘Em, an especially complex form of poker in which betting strategies play out over dozens of hands.
During the competition, the creators of Libratus were coy about how the system worked—how it managed to be so successful, how it mimicked human intuition in a way no other machine ever had. But as it turns out, this AI reached such heights because it wasn’t just one AI. Libratus relied on three different systems that worked together, a reminder that modern AI is driven not by one technology but many.
Libratus relied on a form of AI called reinforcement learning, which is driven by a process of extreme trial and error: The machine basically plays game after game against itself, learning from every outcome. “We give the AI a description of the game. We don’t tell it how to play,” Noam Brown, a CMU grad student who built the system alongside his professor, Tuomas Sandholm, told Wired. “It develops a strategy completely independently from human play, and it can be very different from the way humans play the game.” Some believe Libratus’s breed of AI could play a major role in everything from Wall Street trading to cybersecurity to auctions and political negotiations.