RLAI Reinforcement Learning and Artificial Intelligence (RLAI)
The predictive representations hypothesis

The ambition of this web page is to state, refine, clarify and, most of all, promote discussion of, the following scientific hypothesis:

Representations of the state of the world that are in terms predictions of upcoming experience will generalize particularly well

return to hypotheses

Extend this Page   How to edit   Style   Subscribe   Notify   Suggest   Help   This open web page hosted at the University of Alberta.   Terms of use