Lex Fridman Podcast cover image

#344 – Noam Brown: AI vs Humans in Poker and Games of Strategic Negotiation

Lex Fridman Podcast

00:00

Self-Play Algorithm Learns How to Play Poker

There is a process called self play that can be used to find a Nash equilibrium./nThe process starts by playing randomly and then learning from its mistakes./nThis allows the algorithm to find actions that have the highest regret with the highest probability.

Play episode from 18:27
Transcript

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