From: Bill Hibbard (
Date: Fri Dec 13 2002 - 10:56:19 MST

Hi Ben,

> Bill says this will be solved by solving the temporal credit assignment
> problem, and I say the solution to that may involve *explicit* use of
> planning and inference, as well as the emergence of *further* aspects of
> planning and inference.

No argument. A robust solution to the temporal credit assignment
problem does require planning.

> Bill, I think that computationally-plausible temporal credit assignment is a
> bigger can of worms than you're realizing ;-)

Well, in my book I say it will be 100 years before we can solve it
(including having machines with sufficient computing power). Do you
think its a bigger can of worms than that?


This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:41 MDT