Abstract
Language Augmented Prediction
Highlights
Imagine the simple task of pointing to a red box to get a reward, while ignoring the blue box
Humans can succeed without any training at all, by being told what to do!1 We often take this ability for granted, but without it, all human learning would require direct experience with the domain
If all brains are surprisal-reducing machines, what is it about human brains that allows them to be guided so effectively, often foregoing laborious trial-and-error tweaking?
Summary
Imagine the simple task of pointing to a red box to get a reward, while ignoring the blue box. The problem here is not communication, but that of flexibly activating task-relevant mappings.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have