Wednesday, February 12, 2003, 12:00:56 AM, Shane Legg wrote:

SL> Yes, if the universe is not "somehow predicatble" in the sense of
SL> being "compressible" then the AI will be screwed.  It doesn't have
SL> to be prefectly predictable; it just can't be random noise.

Thanks for your responses.

Some more questions:

So "Solomonoff induction", whatever that precisely is, depends on a
somehow compressible universe.  Do the AIXI theorems *prove* something
along those lines about our universe, or do they *assume* a
compressible universe (i.e. do they state "IF the universe is somehow
compressible, these algorithms (given infinite resources) can figure
out how)?

Assuming the latter, does that mean that there is a "mathematical
definition of 'pattern'"?  As I stated I'm not a math head, but with
what little knowledge I have I find it hard to imagine "pattern" as a
definable entity, somehow.

To get down to cases:

>> I should add, the example you gave is what raised my questions: it
>> seems to me an essentially untrainable case because it presents a
>> *non-repeatable* scenario.

SL> In what sense is it untrainable?  The system learns to win at chess.
SL> It then start getting punished for winning and switches to losing.
SL> I don't see what the problem is.

OK, let's say you reward it for winning during the first 100 games,
then punish it for winning / reward it for losing during the next 100,
reward it for winning the next 100, etc.  Can it perceive that pattern?

Given infinite resources, could it determine that I am deciding to
punish or reward a win based on a pseudo-random (65536-cyclic or
whatever it's called) random number generator?

And if the "compressibility of the Universe" is an assumption, is
there a way we might want to clarify such an assumption, i.e., aren't
there numerical values that attach to the *likelihood* of gravity
suddenly reversing direction; numerical values attaching to the
likelihood of physical phenomena which spontaneously negate like the
chess-reward pattern; etc.?

In fact -- would the chess-reward pattern's unpredictability *itself*
be an indication of life?  I.e., doesn't Ockham's razor fail in the
case of, and possibly *only* in the case of, conscious beings*?


--
Cliff

*I can elaborate on this if necessary.

-------
To unsubscribe, change your address, or temporarily deactivate your subscription, 
please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]

Reply via email to