Episode 21: Chelsea Finn, Stanford, on the biggest bottlenecks in robotics and reinforcement learning
Generally Intelligent
00:00
Is There a Benchmark for Distribution Shifts in Machine Learning?
One big thing that I've been doing a lot of work on recently is handling distribution shifts. So the train distribution and the test distribution are not always the same. The real world changes over time. This is true in robotic settings, because you train it in a lab maybe and then want to deploy it in the world. And trying to also think about practical tools for allowing us to handle these kinds of problems.
Transcript
Play full episode
