TalkRL: The Reinforcement Learning Podcast cover image

Jakob Foerster

TalkRL: The Reinforcement Learning Podcast

00:00

The Importance of Language Models in Deep Learning

OBL is the policies that OBL comes up with do not entangle everything in the same way that traditional deep learning would. What this prevents is secret protocols, emerging protocols between the different agents in the same environment. And I think here is something like of belief learning could be used down the line to make sure that the messages that are being passed between language models are being used in the literal sense as opposed to scheming a plot to take over the world.

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