TalkRL: The Reinforcement Learning Podcast cover image

John Schulman

TalkRL: The Reinforcement Learning Podcast

CHAPTER

Uh, Is the Standard RL Framing Problematic?

I saw Stuart Russell was on your PhD committee and I really enjoyed his book Human Compatible. He mentioned that the standard RL framing with this fixed reward signal is problematic. Do you have any thoughts on that idea? "Yeah, yeah, I totally agree with, with that idea," he says.

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