From: Eliezer S. Yudkowsky (sentience@pobox.com)
Date: Fri Dec 13 2002 - 05:06:50 MST
Ben Goertzel wrote:
>
> Here is my view on the relationship btw planning & reinforcement learning...
>
> Firstly, I think that reinforcement learning, if given enough time & space
> to work in, would eventually emergently give rise to planning. (This could
> probably be shown mathematically, actually, though estimates on the time &
> space required would be hideously exponential. This relates to Hutter and
> Schmidhuber's work on algorithm information theory based AGI)
In a sense, of course, reinforcement learning has already been
demonstrated to give rise to planning; what else is evolution but
reinforcement learning on the space of DNA strings and phenotypes? But in
this case it was reinforcement learning on DNA that gave rise to planning
in the phenotype; planning never did come about within the DNA.
-- Eliezer S. Yudkowsky http://intelligence.org/ Research Fellow, Singularity Institute for Artificial Intelligence
This archive was generated by hypermail 2.1.5 : Wed Jul 17 2013 - 04:00:41 MDT