It depends on how you see it.  Deep Blue is nothing more than a
Knowledge-Based expert system.  Netrek is more compicated and  the
game-space for Netrek is much more than chess.

I am thinking that the easiest way to do it would to be able to assign
"roles" to various bots.  These "roles" would alter their behavior.  If a
bot had enough kills and the central AI, or human caption, told it to take
a planet.  It would switch roles to planet-taker and cause nearby bots to
switch roles to escort if necessary.  The different "roles" could be
individually programmed or better yet, they could be evolved using
something like Genetic Programming.

The purpose of robot soccer is also to evolve an AI team.  The difference
with Netrek is that it is closer to real life.  You have to control space,
coordinate attacks on the enemy, assault planets, and force the enemy
back.  This is much closer to a military campaign then soccer is. If you
look at Huber's and Hadley's paper, some of their research was sponsored
by the NSF and DARPA.  Who knows maybe someone could use the research for
a master's topic for AI.

Chess is slightly different then Netrek.  In chess you can loose space,
you can even loose pieces, but if you can attack and defeat one peace you
win.  It is not the same in Netrek, if you loose most of your planets then
you go and take your enemy's homeworld, you just wasted armies.  Now if
you focus on first gaining and maintaining control of space then taking
planets behind the front, you don't have to worry about the planettaker
switching modes between attack/defending/ogg-avoidance/planettake, but
maybe even this won't be a problem.  If the bots were better at fighting,
playing a more ship-to-ship type defense would probably work.  As long as
the sides are even in a conflict the bots would win out let's say 60% of
the time.  To win the game, is different from saying that you have to geno
the team.  If the strategy works to just be 1 or 2 planets ahead for most
of the game, that is enough.

Darryl




-----Original Message-----
From: vanilla-list-admin at us.netrek.org
[mailto:vanilla-list-admin at us.netrek.org]On Behalf Of Karthik Arumugham
Sent: Wednesday, December 05, 2001 11:41 PM
To: vanilla-list at us.netrek.org
Subject: Re: [Vanilla List] Growing Netrek - Measures


I'm not sure what plocking cloakers has to do with actual clue. That
intangible "clue" is what is hard to code. Coding bots to take planets as
well as humans do, making team plays to accomplish their goals, and so on
would be quite difficult in my opinion. Not to mention, the difficulty of
figuring out exactly what the other team is up to.

Winning the game takes a whole lot more than creating a bunch of robots
that
may be tactically superior to the other team. I think Netrek is a much
more
complex game than many people realize (especially those who haven't played
higher level clue games). Someone compared it to computers playing chess
in
a previous post. While I don't know much about chess past the basic rules,
it's basically a very simple game with a small, fixed number of variables
(with a very, very large number of permutations of these variables of
course, which is what makes it a complex and interesting game). Netrek has
far, far more variables at work in determining exactly what's going on,
and
exactly what course of action to take.
-------------- next part --------------
A non-text attachment was scrubbed...
Name: smime.p7s
Type: application/x-pkcs7-signature
Size: 3043 bytes
Desc: not available
Url : http://shadowknight.real-time.com/pipermail/netrek-dev/attachments/20011206/edfe3320/smime.bin