Episode 19: Minqi Jiang, UCL, on environment and curriculum design for general RL agents
Generally Intelligent
00:00
On Line Supervised Learning
Supervised learning is like off line supervise learning. There's an outside process that devicts the aory and collected all the data, loputting it. We're busiy in supervise learning that there is an exploration problem. That's how you got your data, but we just assume it's already solved. I think that's the really interesting disconnect between supervisnin and r l.
Transcript
Play full episode
