quote:
Originally posted by Shyrka:
The idea is very good, not only for modders but also to MM. Why not "train" the AI to improve it just as neural nets, decision trees or other algorithms? (In these structures engineers run a situation and lets the system deal with it, so they learn from them errors. With time the systems take better and better decisions).
Hey Shyrka, do you know "Fritz", my favorite chess program ? It has a self-optimizing engine which does not make the same error for a second time.
For SEIV this would be future music, but what a potential ! EDIT: "dreams of the future", of course. I am still thinking too much in german.
Regards from a dreaming PTF...
[ 15 February 2002: Message edited by: PsychoTechFreak ]
Re: AI longtime simulation feature
Threaded Mode