Episode 21: Chelsea Finn, Stanford, on the biggest bottlenecks in robotics and reinforcement learning
Generally Intelligent
00:00
Robotics
In robotics, I imagine you do a lot of work in simulation. And there was an interesting recent paper on more high fidelity simulation is worse. Did that sort of fit with your intuition? Was it surprising? How do you react to that?Yeah, in some ways I don't think it's too surprising. Any simulation, especially for object manipulation, is not very accurate.
Transcript
Play full episode
