I am currently trying to implement my own neural-network library, and I would like to test it by letting it (and networks made with other librarys) play a 2D game. The problem is I can't really find a good game for a neural network to play.
Requirements for the game:
It should not involve skills like reaction time, precision. It should instead require some tactical skills.
It should be easily scorable, in order to create an efficient evolutional algorithm.
It should be relatively simple.
It does not have to be a game that already exists, you can come up with one if you have an idea.
It may be a single-player game (like mario) or a 1v1 game (like pong).
- It must not be any kind of MMO, RPG etc. I am looking for a small kind of mini-game.
The game should be well playable by a neural network. This means it should have a fixed amount of inputs somehow normalizable between 0 and 1. Inputs can be sensors, angles to closest objects etc. inputs should NOT be the pixels of the screen because 3*1920*1080 is just too much. Up to about 100 inputs are manageable (because I am a beginner and can't afford to let my computer calculate for hours just to get one generation evolved or so). Also the game should definitely be a 2D game since i am going to use a AWT JPanel to draw on.