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
Machine Learning Systems That Emulate Humans Through Imitation Learning Through Supervised Learning
There has been a lot of advances in machine learning systems, both in robotics and in other areas like vision and language. But I think that ultimately we really need machine learning systems that do a good job of going beyond the best that people can do. And that's really the promise of reinforcement learning.
Transcript
Play full episode
