[quote name='IADaveMark' timestamp='1337086862' post='4940385']
I'm not sure why you would need a book or paper to analyze the fact that you can't easily tweak a "learned" algorithm without going back and retraining it. There are no well-labeled knobs to turn, no branch points to edit, no triggers to massage... it's a black box. You have to hope for the best.
Its an academic thing, the marking scheme's tick boxes must be filled, else the lecturers give a lower mark.
[/quote]
That's like needing to cite a book or paper to verify that your car will not run when it is out of gas.
"that's like needing to cite a paper to verify that your cr will not run when it's out of gas". LOL. Mind if I borrow that?
Dave, he wants an online learning algorithm. NNs are well suited to the task. It takes a trivial amount of time to train/retrain an ANN and the whole thing can be automated. You're always complaining that NNs have no use in games, and now this gentleman has a plan to use one with legitimate reasons.
Blessman: you can cite this website and the post. It is peer reviewed, as everything gets reviewed and commented on by people who have some experience working within the field. There is a video on YouTube of reinforcement learning being used to teach an opponent to play the game "golden spaceships". If you look you can find it-- it's not an ANN, but the idea is the same.
Dave makes a good point about the use of ML techniques in general. For video games they are almost never the right choice. Hand coded rules are easier to adjust to produce the desired behavior and most games require simple agents.
I wasn't saying don't use one. I was just pointing out the caveats.
What I was fascinated with is that he wanted a paper or source to support the notion that you can't edit them after the fact. If one doesn't know that, then one has no idea how they work in the first place. *shrug*
