... and are inherently next to impossible to hand tune after the fact -- a requirement for most game design applications.

Alvaro: When I'm hitting data for the first time I always build an OLS model first. It's rare that it's ever the top contender, though it does happen. The only model type that seems to consistently reign supreme is a boosted ensemble of trees.

Regardless, in many stats packages (mine included) there is no hand tuning necessary. Provide data, click go, and you have a model which has been validated etc... Even the choice of activation function at each layer can be automated these days. If you had to write everything from scratch then it definately would be more challenging than multivariate OLS.

Dave: I really can't argue with you as I've never put any form of regression model in a game. You are right that it's pretty much impossible to hand tune after the fact. A decision tree would be better suited for what you want, but only if you have a bunch of data and don't know what it means before hand. .

I rarely run across a video game where I think "this needs some machine learning", but it does happen. Many board games have terrible AI and they get boring really fast. Some "sandbox" games, like MineCraft, could definately use some novel approaches to NPCs. These sorts of games don't have a specific win condition and players don't want scripted or repetitive things happening.

It's still early days for video games. I'm not ready to call "case closed" on statistical inference just yet.

You can easily get non-scripted and non-repetitive out of traditional AI techniques. It's actually not hard at all just through things like parametric noise, weighted random decisions, etc. Then just let chaos theory kick in.