
Noam Brown: from Open AI on solving Poker and Diplomacy with AI
The Robot Brains Podcast
00:00
The Nash Equilibrium in Poker
When your system is done learning, can you look at it and say, for example, when libratus or Cicero has pocket aces? I mean, doesn't even have a probability of possibly folding. Like, can you inspect that and get an intuition of what is the optimal way to play? Yeah, absolutely. And so what you'll end up with is, you know, you will end up with a strategy that's like the average over everything you've done. As you keep iterating, it will converge to the Nash equilibrium.
Transcript
Play full episode