Pilot AI

Jp Calderone (exarkun@flashmail.DONT-SPAM.com)
Mon, 16 Aug 1999 19:41:43 +0200 (MET DST)

I'm currently working on a game that will (at a much later date)
incorperate AI piloted space craft. The system is flexible, in
that the stats of a ship can change due to newly installed equipment,
battle damage, repairs to damaged components, and stress-damage over
time. My main goal for the AI is to have them capable enough to fly
against human opponents in a combat situation and do moderately well.
While I'd rather have them fly brilliantly *grin* I not opposed to
offsetting a slight inferiority in skill with a superiority in numbers/
firepower/etc. There is no code written for the AI module yet, and
the space module is still very open to change in terms of data structures
and overall framework. My question is is this is something attainable
without an immense amount of work and what mechanisms are best suited
for this. Learning algorithms are of course a plus, serializability
is a necessity, lower CPU usage is also more important than memory or
disk space.

Also, I've had some ideas about using genetic algorithms to guide the
AI's movements by setting up a language of alleles for basic manuveurs
and letting them evolve against each other and against players. Does
this sound feasable?

Thanks in advance for any help.

PS - I really only have experience in genetic algorithms, I don't know
much about NNs or fuzzy logic, so simple terms and newbie links in
those areas would be much appreciated :)

-- 
No, `Eureka' is Greek for `This bath is too hot.'
                -- Dr. Who

############################################################################ This message was posted through the fuzzy mailing list. (1) To subscribe to this mailing list, send a message body of "SUB FUZZY-MAIL myFirstName mySurname" to listproc@dbai.tuwien.ac.at (2) To unsubscribe from this mailing list, send a message body of "UNSUB FUZZY-MAIL" or "UNSUB FUZZY-MAIL yoursubscription@email.address.com" to listproc@dbai.tuwien.ac.at (3) To reach the human who maintains the list, send mail to fuzzy-owner@dbai.tuwien.ac.at (4) WWW access and other information on Fuzzy Sets and Logic see http://www.dbai.tuwien.ac.at/ftp/mlowner/fuzzy-mail.info (5) WWW archive: http://www.dbai.tuwien.ac.at/marchives/fuzzy-mail/index.html