AXRP - the AI X-risk Research Podcast cover image

7 - Side Effects with Victoria Krakovna

AXRP - the AI X-risk Research Podcast

CHAPTER

How to Set the Impact Penalty Weight?

So, one question i have about this kind of measure. Basically, the way, you, the way gets implemented, is your reward function is whatever your reward function would otherwise be,. And there's this meter of am, how how strong the regularization is, and how it trades off. How do i know how to set that parameter? Is there some like guide er? Is it just a guess and check? So think the kind of te falt answer to this er is to kind of start out with a high value of  the regularization perometer...and then kind of keep reducing it until the agent starts doing something.

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.
App store bannerPlay store banner