Newsgroups: comp.ai.genetic,comp.ai.alife
Path: cantaloupe.srv.cs.cmu.edu!das-news2.harvard.edu!news2.near.net!howland.reston.ans.net!news.sprintlink.net!news.indirect.com!s68.phxslip3.indirect.com!enigma
From: enigma@indirect.com (Andy Sherwood)
Subject: Re: GA For Starfleet Battles? or How To Kill Each Other (Efficiently)
Message-ID: <enigma.4.001420E4@indirect.com>
Sender: usenet@indirect.com (System Operator)
Organization: Nothing, Inc.
Date: Thu, 3 Nov 1994 03:07:34 GMT
References: <enigma.2.00166BC7@indirect.com> <3988eb$q0j@calvin.st-and.ac.uk> <398dbt$g6n@panix.com>
X-Newsreader: Trumpet for Windows [Version 1.0 Rev A]
Lines: 21
Xref: glinda.oz.cs.cmu.edu comp.ai.genetic:4160 comp.ai.alife:1225

In article <398dbt$g6n@panix.com> dcl@panix.com (David Lambert) writes:
>From: dcl@panix.com (David Lambert)
>Subject: Re: GA For Starfleet Battles? or How To Kill Each Other (Efficiently)
>Date: 2 Nov 1994 11:05:17 -0500

>>> paraphrased problem: getting fleets of starships of varying types to 
>>> kill each other effectively.
>>

>If the original poster is not wedded to genetic techniques, some
>approach based on reinforcement learning might be interesting also.

Actually, the entire system will be written in Windows (for those of you 
booing, knock it off.. ;)  and I plan to use DLLs for the AI itself.  That way 
I can easily drop in other forms of AI and watch them compete.  I was planning 
on dropping in a canned AI (search, kill, retreat), as well as one that would 
allow the user to define certain genes and pit his own intelligence against an 
artificial one.  :)



