Jérémy Scheurer

For instance, in the hospital example, you can just try to figure out what is the spurious correlation and then try to kind of, like, discorrelate these 2 features. But with the rewards, this just doesn't work because this just kind of obviously is the thing the model is trained to to maximize with reinforcement learning.

“For instance, in the hospital example, you can just try to figure out what is the spurious correlation and then try to kind of, like, discorrelate these 2 features. But with the rewards, this just doesn't work because this just kind of obviously is the thing the model is trained to to maximize with reinforcement learning.”

Speaker

Jérémy Scheurer

Episode

How Researchers Test AI for Hidden Goals — Apollo Research

Publisher

Machine Learning Street Talk