
Episode 28: Sergey Levine, UC Berkeley, on the bottlenecks to generalization in reinforcement learning, why simulation is doomed to succeed, and how to pick good research problems
Generally Intelligent
Is There a Higher Level Goal?
There's a lot of active research in this area. I think it's possible to kind of take these goal condition things a little further and really conditional in any notion of a task. So there's some really interesting work that I've seen out of fair. This is by a fellow named Ahmed Tuadi and Jan Olivier to researchers at the meta.
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.