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
Using Language Models to Build Robotic Robotic Systems
Robotic systems that understand Visio motor control, basically how to manipulate the world and how to change things in the environment. We can build those kinds of systems and then we can hook them up to an interface that humans can talk to by using these visual language models. "I do know what a really interesting potential is forward to have it be a bidirectional thing," he says.
Transcript
Play full episode
