Quote: Original post by wild_pointer
Thanks for the ideas guys. I think I'm going to run life by him. I'm afriad a chatbot wouldn't be acceptable. Speaking of classical conditioning though, could anyone think of anything I could do with genetic algorithms aside from the standard ants simulation? We did discuss evolution quite a bit and I think that might go over well.

There was a thread in this forum on my old uni project on genetic programming for pacman AI.

It's a bit too much to implement in "weeks" (unless you're a good coder - *I* could do it but that's because I code graphics + logic + input + etc every day and I'm "in practice", and already know everything I need to about evolutionary programming - but I wouldn't recommend it!). But you could go for something slightly simpler - e.g. tetris - since you really need somethign non ground-breaking yet also non-trivial.

Another one (probably better than tetris, which is pretty damn hard if you go down the wrong path) would be breakout *with multiple balls*. (with only one it's trivial...). This is a very good problem for simple-yet-interesting EP.

If you want help I could be a supplementary advisor for you (I do private tuition of undergrads etc and have a good idea what academic projects like this need) if you're allowed them (depends on your course; sometimes yes, sometimes no). Email me at ceo @ grexengine.com (not my personal address; stick "redmilamber" in the subject ot make sure it gets to me) if you want to and have OK'd it with your prof.

redmilamber