
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
Introduction
Sergei Levin is an assistant professor of EECS at UC Berkeley. His research focuses on developing general purpose algorithms for autonomous agents to be able to learn to solve any task. In this episode, we're interviewing him about his work in deep reinforcement learning.
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.