Re: [NTLK] Newt artificial intelligence

From: Dylan Stewart (rxs015500_at_utdallas.edu)
Date: Tue Mar 25 2003 - 16:00:08 PST


Technically, it is AI. If it can learn, it probably involves some sort of
neural net. It probably weights the different spots based on how you play.
That way, after a little while, it starts picking the spots that will block
your tactics.

Of course, tic-tac-toe has a countable number of states. In fact, someone
could probably write a program for the Newt that would play perfect
tic-tac-toe. It's much more of an achievement if it is actually a form of
AI, rather than just brute force or chance. Also, I would be _very_
impressed if it could play naughts and crosses (tic-tac-toe with an infinite
board and requiring 5 symbols in a row).

What package was this? I would be interested in playing it myself to test
how quickly it learns.

 Dylan Stewart AC5ZH

-- 
This is the NewtonTalk list - http://www.newtontalk.net/ for all inquiries
List FAQ/Etiquette/Terms: http://www.newtontalk.net/faq.html
Official Newton FAQ: http://www.chuma.org/newton/faq/


This archive was generated by hypermail 2.1.5 : Tue Mar 25 2003 - 16:30:00 PST