Not sure if I am allowed to put this in finished products, so I'll stick this here...
So I was bored last week and put together a dynamic AI system and made it for a Tic-Tac-Toe game. All it does is hold a large population of reproducing, competing programs who's goal is to win. This is achieved through random mutation and natural selection. I also made a 'Trainer' for it that pits random programs against each other in order to speed up the training process (Just look at the basic script in the DATA folder (AI.SRC)
) etc. If you play it right away you'll notice that the programs have figured out several winning patterns already. How most of them achieve this; I have no idea, and I wrote the scripting language that they use
Seriously, the code is really messy, but works, apparently.
Download it here:
http://www.filefront.com/14913979/T-T-T%20v32.rar
Please tell me what you think, or at least let me know it if crashes on you
EDIT: Fix'd link for lazy people
"I have faith, that I shall win the race, even though I have no legs, and am tied to a tree." ~Mark75
