问题
I am a neural-network beginner. I'd like to learn the basics of neural networks by teaching computers to play checkers. Actually, the games I want to learn are Domineering and Hex.
These games are pretty easy to store and the rules are much simpler than chess, but there aren't too many people who play. If I can get this idea off the ground it would be great for experimenting Combinatorial Game Theory.
PyBrain seems to be the clear winner for Python neural networks, but who can walk me through how to set up a neural net for my game-playing task? A google search turned up Blondie24 in 2001 but it uses some genetic algorithms - I don't want to complicate things.
回答1:
Once you replace "neural networks" by machine learning (or even artificial intelligence, rather, imho) as the comments rightly suggest, I think you're better off starting with Alpha-beta pruning, the Minimax algorithm, and Branch and bound ideas.
Basically :
- At each step, you build the tree of all possible futures, and evaluate leaf positions with an evaluation function (e.g. board domination, connectivity, material, etc.)
- Propagate the results up in the tree, choosing the best play you can make, and the worse your opponent can (the best for him), until you know what move to play in the position you're at.
- Rinse, repeat. Branch and bound saves you a lot of computation if you have a few good heuristics, and the level of your programm will basically be how deep it'll be able to search the game tree.
This will most probably be the basic framework in which anyone would introduce new ideas, so if you're not familiar with it, go for it :-)
来源：https://stackoverflow.com/questions/12592857/how-to-build-game-playing-neural-network-in-python