
Episode 27: Noam Brown, FAIR, on achieving human-level performance in poker and Diplomacy, and the power of spending compute at inference time
Generally Intelligent
Do You Have Any Controversial Opinions in the Multi-Agents RL Community?
I think in the multi-agents RL community my controversial opinion is that I think in order to achieve human AI cooperation you need to incorporate human data. So basically I know self-play evolution all the way and like that's not going to get us there. In order to do well it's really more about modeling the human behavior rather than trying to compute an equilibrium. That really resonates with me actually to given some of the stuff that I saw at Noreps this year. Yeah and I'm hoping that the Cicero work kind of pushes people in themulti-agent RL community more in this direction.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.