Preview Mode Links will not work in preview mode

Technical AI Safety Podcast

May 15, 2021

with Joel Z. Leibo

Feedback form

Request an episode

Multi-agent Reinforcement Learning in Sequential Social Dilemmas

Joel Z. Leibo, Vinicius Zambaldi, Marc Lanctot, Janusz Marecki, Thore Graepel
Matrix games like Prisoner's Dilemma have guided research on social dilemmas for decades. However, they necessarily treat the...