Generally Intelligent cover image

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

00:00

Counterfactual Regret Minimization

Counterfactual regret minimization was developed in 2007. It's really an extension of regular regret minimization that's been around since the 50s. The basic idea is you have a regret value for each of your actions. And then any algorithm that minimizes regret, the average over all the iterations is proven to converge to an action.

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