
Episode 21: Chelsea Finn, Stanford, on the biggest bottlenecks in robotics and reinforcement learning
Generally Intelligent
00:00
The Main Blocker to Working With Real Data?
The main blocker is that there's a big ramp up time and the big learning curve in terms of working with real hardware. We have a current project right now where everything works perfectly in simulation and it's not working at all on the real robot. I personally think it's really important to touch real things. It keeps you honest, but it also can be frustrating at times as well.
Transcript
Play full episode