🚀 go-pugleaf

dmb@rice-chex.ai.mit.edu (David Baggett) writes:

Rice Chex?  Did you get to name your machine, Dave, or did you inherit it?

>Yes, but what would be more interesting would be a computer opponent
>that looked at the board and thought to itself, "I dunno, both those
>paths look about three inches long.  But I bet he's trying to snag that
>pill over there, so I'll turn left."  Perhaps that's part of the recent
>fondness for GA's and NN's in this group.

Interesting, yes, but practical -- probably not.  It's neat to talk about
GAs and NNs and say, "When..." and "What if..." but I don't think you're
going to see them in games (or anywhere else) any time soon.  Even the
"sensory input" of Pac-Man would overload the machine.
	What I would like to see (and probabaly should do, with "Night
of the Brain-Sucking Undead Businessman From Beyond the Grame" if I ever
get off my butt and start working on it again...  Heh) is fuzzy logic.
I think it's much more realistic to attempt a program that keeps track
of the types of moves used by the player in a certain situation, recording
percentages.  The bad guys then use those percentages to counter-attack.
"Hey, he's moving under me.  Using Attack 1, I've died 80% of the time;
using Attack 2, I've died 40% of the time.  Attack 2 it is.  Yaaah!"
	You get realistic battles -- you're not going to get away with
the same thing nine times in a row -- and can still safely stay within
the bounds of a home computer's ability.  Plus, since the game constantly
changes stragety, maybe it says interesting longer...
--
 ------------------------------------------------------------------------------
 Greg "Maddog" Knauss               "Aieee!"              greg@duke.quotron.com
 ------------------------------------------------------------------------------