Generally Intelligent cover image

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

CHAPTER

I Think Jason Pang's Robotics Demo Is the Work

The history of robotic technology is one of building abstractions, taking those abstractions as far as we can take them. And the really difficult wall that robotics generally hits with this kind of approach has to do with situations that are not as fully and cleanly structured as a rigid body. In 2012, Alice Kshavski had a solution to the ImageNet challenge that didn't use any of that stuff whatsoever and just used the giant neural net. So kind of suspect that like the robotics world is kind of just getting to that point, like right around in the last half years or so.

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