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
The Importance of Robotics Versus Not?
The more modern architectures do become tremendously useful as the problem becomes more realistic. So it's really just with relation to the problem. The more the larger networks start to pay off quite a bit. Although I guess the interesting thing about the Atari thing was like, as you made these larger, they seem to help anyway. Yes.
Transcript
Play full episode
