On Fri, Feb 29, 2008 at 1:37 PM, Abram Demski <[EMAIL PROTECTED]> wrote:
> However, Solomonoff induction needs infinite computational resources, so > this clearly isn't a justification. see http://www.hutter1.net/ai/paixi.htm "The major drawback of the AIXI model is that it is uncomputable. To overcome this problem, we construct a modified algorithm AIXI^tl, which is still superior to any other time t and space l bounded agent. The computation time of AIXI^tl is of the order t x 2^l." In any case, whether or not Solomnoff in induction can actually be used to make an AI is beside the point. Analogous to a point made by Eliezer Yudkowsky (http://www.overcomingbias.com/2008/01/beautiful-proba.html), Solomnoff Induction is the precise definition of the right answer: the *law*. It is not the definition of how you go about getting that answer. An abstract definition of an algorithm should not include, e.g., register assignments. > My thinking is that a more-universal theoretical prior would be a prior > over logically definable models, some of which will be incomputable. I'm not exactly sure what you're talking about, but I assume that these logically definable models would be defined in some formal language, which means that they would be caught by Solomnoff. Daniel ------------------------------------------- agi Archives: http://www.listbox.com/member/archive/303/=now RSS Feed: http://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: http://www.listbox.com/member/?member_id=8660244&id_secret=95818715-a78a9b Powered by Listbox: http://www.listbox.com