News for hackers. Stuff that matters.
Re:Game AI vs Traditional AI by KVFinn on Wednesday September 05, 2012 @02:32PM (#4480707)
One approach that has been more successful and easier to integrate than machine learning is Monte Carlo based systems. That's what the latest Go AIs use and they are making big strides.

It's powers various card game AIs, here's the developer talking about it: http://hfog.blogspot.com/2010_01_01_archive.html

Though this absolutely brutal Race for the Galaxy AI was generated using machine learning: http://www.keldon.net/rftg/

He talks about it in this thread: http://www.boardgamegeek.com/thread/438698/race-for-the-gala...

[quote]Some of the AI neural nets for the Brink of War are only partially-trained; the AI performance in big games is way too slow and takes weeks to train. I'll need to fix that both so that players won't have to wait and to improve training speed.[/quote]

For "true" AI in games, check out Steve Grand's work:

http://grandroids.com/

http://www.youtube.com/watch?v=9XLJuDV03Mw&feature=youtu...

Re:Game AI vs Traditional AI by elemeno on Thursday September 06, 2012 @05:41AM (#4483474)
A hat-tip for mentioning Keldon's RFTG AI.

It's surprisingly brutal and even against good players it wins a good proportion of games. It does though show the downside of the machine learning and neural net approach (it uses a trained neural net) in that it can take a very long time to train the network and when it exhibits unexpected behavior it's almost impossible to tell why.

For those interested, all the source for the AI is on Keldon's website (linked above) - the only thing missing is the art for the cards at the publisher's request.