
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 Future for Computer Animation?
I took a break from the computer graphics world for a while, but then over the last five years, there was actually a student in my lab. Jason Peng, now a professor at Simon Grayser University in Canada. He just graduated last year and he more or less in his P2D. I would say basically solved the problems that I had tried in my own PhD a decade prior. You can kind of think of it as like old motion capture data. We can get our hands on and brings a latent variable GAN on it that will generate human-like motion.
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.