On Fri, Feb 21, 2014 at 1:55 PM, Piaget Modeler <[email protected]> wrote: > > > So it looks to me like the principle is to > > choose the action that maximizes expected future computation. > > -- Matt Mahoney > > In other words, choose the action that best ensures survival.
It's not that simple. The examples given in the paper and video are simple programs that have no concept of death, and yet produce useful behavior. -- -- Matt Mahoney, [email protected] ------------------------------------------- AGI Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657 Powered by Listbox: http://www.listbox.com
