Complete.Org: Mailing Lists: Archives: freeciv-ai: June 2003:
[freeciv-ai] learning from experience

[freeciv-ai] learning from experience

[Top] [All Lists]

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index] [Thread Index]
To: freeciv-ai@xxxxxxxxxxx
Subject: [freeciv-ai] learning from experience
From: "Alexander L. Vasserman" <avasserm@xxxxxxxxxxxxxxxxxxxxxx>
Date: Fri, 6 Jun 2003 20:50:08 -0400 (EDT)

Hi guys,
I was wondering if anyone has excercised/implemented the idea of AI
learning from experience. For eample, for the science selection could
assign a weight to each technology, which would be combined with current
game factors (want?) to figure out which technology is the most valuable.
The weights then can be adjusted deppending on wether the game was won or
lost. For a lost game technologies that have been researched early would
be penalised, for a won game they would be encouraged. This is just
one possible way of doing it. I am sure I could come up with more
interesting strategies. My question is more about the concept itself. Some
randomization of these decisions would be required, but I think this
would be a good thing. In addtion to hopefully improving the AI it would
also descourage a single winning strategy. If a strategy used too often
the AI would adjust to it, and at least will make you look for a new one.
Right now even very simple strategies work very well. For example, while I
am not such a great player, I can bit the AI every time under any
configuration I could come up with (except maybe landmass = 100) by
developing fleet thechnologies early. By the time I research magnetism AI
has no defence from frigates and I can capture all the port cities fairly
easily. And that gives me enough advantage to win every time. AI should be
able to adjust to stategies that simple.

What do you think?

Alex Vasserman

[Prev in Thread] Current Thread [Next in Thread]