I would very much like an AI that doesn't cheat at all. I think the main reason so many players can hand a can of whoopass to the AI is that they read forums such as Apolyton. Before reading the apolyton forums I won about half the games on the Thinker level in SMAC. These days I pretty much don't lose a game. (Lost a couple of rounds to ZsoZso's Ultimate Builder Challenge and similar "impossible" settings though.)
The AI needs to learn! Something that I have been pondering for a long time is a slight expansion on the rules+neural net idea above. A rules+neural net+"apolyton for AI" where AI's can turn in good rules, and check new good rules out.
Another way is to do it like crisium is planning to do it for stars supernova. (www.crisium.com) They plan to let you set a time limit for AI pondering of problems: (Like, spend the night on it boy.) And their AI is going to learn from actual playing. (They are trying it out in the beta to see if it learns "the right stuff" or not.)
But I am too much of a cynic to think that there will be anything really new in the AI from firaxis.
The AI needs to learn! Something that I have been pondering for a long time is a slight expansion on the rules+neural net idea above. A rules+neural net+"apolyton for AI" where AI's can turn in good rules, and check new good rules out.
Another way is to do it like crisium is planning to do it for stars supernova. (www.crisium.com) They plan to let you set a time limit for AI pondering of problems: (Like, spend the night on it boy.) And their AI is going to learn from actual playing. (They are trying it out in the beta to see if it learns "the right stuff" or not.)
But I am too much of a cynic to think that there will be anything really new in the AI from firaxis.
Comment