How AI Solved Poker
  • "So the AI starts by knowing nothing about the game, it plays totally randomly, and it plays itself, it plays a copy of itself, in that game for trillions of iterations."
  • "Then suddenly, the bot bets $20,000 into a $500 pot. The bot is basically saying, 'I'm either bluffing or I have the best hand'."
  • "In poker, it's very clear what actions you can take in any given situation. You win a certain amount of money at the end of the hand. But if you move to a negotiation for example, your actions are not as clearly defined. You can negotiate over all sorts of things."

Season 01 Episode 05

How AI Solved Poker

Featuring Noam Brown

How did Libratus AI beat some of the top heads-up poker pros in the world? Libratus co-creator Noam Brown joins Dirk and Jon to talk about how Libratus taught itself and devised innovative strategies to conquer this popular game.

Computer and research scientist Noam Brown joins Dirk and Jon to provide the inside story on Libratus, a poker playing AI that he co-created which defeated four top human heads-up poker pros. We discover how Libratus taught itself to prepare, how it adjusted its play overnight, and continually made plays that, in the words of a top poker pro, “is thinking two moves ahead of any human.”