
#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


