Kanji input on a pen stroke interface (3000 common characters you need a rather complex keyboard) was a well used NN application (20 years ago was it ??)

SO maybe a game that uses sweep input (mouse or finger interface) gestures which are recognized (have to be learned and then repeated back at the game ??)

Typical unit AI's are very irregular special case oriented - generalized patterns really arent there in most game mechanics (and scripting already handles quite well - you might have a few NN tools for certain analysis but it would only be a small piece.

The training thing for NNs really doesnt work without massive effort of creating training sets even for a very generalized game state set. (You also need a very explicit 'right or wrong' judgement metric so any forming NN can correct itself and more complicated games which have results happen in a delayed fashion are hard to gather/digest the judgement data for.)

So how would you design a game if you had to make the AI for the game a neural network?

I probably wouldn't.

Its unlikely that you'll find any type of game where a NN would be the superior choice in AI. thus any game using NN would be sub-par and not worth doing.

only if one could identify a good candidate game, and then PROVE that NN works better than other AI types (via rapid prototyping), would it be a viable option.

this assumes that its not simply undertaken as a learning exercise.

if undertaken as a learning exercise only, you'd want a game where what a human player does is similar to what your NN does. But even then, a non-NN AI would probably still beat your best attempt at NN AI.

I agree with everyone else that you are:

1. Doing it backwards by choosing a game to match the algo
2. Putting the word "good" in the wrong place... i.e. "a game that is good for a neural network". In theory, you could have a very, very simple game that NN could solve. However, it would likely be a pathetic game. It is very likely you will achieve the different goal of designing "a good game that a neural network can solve."

If you are just trying to learn how to do a NN, don't design a game. Use something standard.

When you are done, put NNs behind you and concentrate on doing AI with other algos that have far more application in game AI.

Or a standard NN task can be turned into a game.

For example, you can use a camera to play rock-paper-scissors in real time against a simulated character on the screen. A NN can

1. recognize when the player swings his hand to react with the bot's move, like real people do;
2. more importantly, cheat by recognizing patterns in how the human player moves fingers and adjusting the bot's choice of rock, paper or scissors on the fly..