[MUD-Dev] Metrics for assessing game design

[ceo]

Paul Schwanz wrote:
> ceo wrote:

>> I was actually trying to evaluate games to use whilst
>> experimenting with evolutionary-AI (i.e. automatically evolving
>> better and better AI's). At one point, I sat down with a long
>> list of pre-existing computer games and ranked them according to
>> how well they were likely to work with EP.

> Would it be possible to expand on this a bit?  For example, could
> you walk us through how you determined exactly that Tetris should
> get a high ranking for being likely to work with EP, or that
> Warcraft should get a low ranking?  Or perhaps you could explain
> what steps you use to evaluate your test game to find that it
> requires adjustment.  If you can find the time, that sort of thing
> could be very helpful.

I'm not quite sure what you're asking here. What I had initially was
just boring metrics that are used for judging EP suitability already
by people in that field. What I refined from that was the bits that
seemed most relevant for games (which is what I posted about).

Do you want to know how people evaluate problems for EP? I can try
and dig out a load of citations if you want, but you may be best off
just looking at the main stopping off points for EP research
resources online (e.g. Koza's genetic-programming.com, and one of
the FAQ's - the most general of which is huge but excellent, and
covers all forms of EP, but I can't recall the domain off teh top of
my head).

Adam M
_______________________________________________
MUD-Dev mailing list
MUD-Dev at kanga.nu
https://www.kanga.nu/lists/listinfo/mud-dev