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
00:00
Deep Learning
In science, it is a really good idea to sometimes see how extreme of a design can still work. The full power of learning is really only realized once you have very large amounts of data that can enable broad generalization. So kind of do the hardest thing first. Do the most extreme thing first.
Transcript
Play full episode
