The Robot Brains Podcast cover image

Noam Brown: from Open AI on solving Poker and Diplomacy with AI

The Robot Brains Podcast

00:00

How to Do Search in Poker

It took 20 years after deep blue beating Gary Kasparov for us to be humans in poker. figuring out how to do search in poker ended up being trickier than people expected. One way is using your self-play techniques where you've had the bot play against itself for trillions of iterations. Obviously the game is too big to store the exact strategy. And so you have to rely on this neural network generalization to store the policy for the entire game.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app