
John Schulman
TalkRL: The Reinforcement Learning Podcast
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.