[MUD-Dev] Efficient AI?

[Brian Lindahl]

Ola wrote:

> I just thought about how to implement efficient markov chain based
> AI for a MUD. Maybe this implementation strategy is unworkable, or
> maybe it is well known, but it might be worth a discussion.

Another good way to generate a good hash function would be to feed
inputs and 'perfect' outputs through a neural net. After training it
properly, a good hash function would result. However, you could also
use a neural net instead of a hash function, so that it could be
trained over time. For this sort of solution to AI, I think a neural
net would work better than genetic algorithms, since genetic
algorithms have usually significant overhead associated with them,
and, therefore, could only be used in preprocessing the hash
function.

I've planned on using neural nets to implement a similiar scheme for
locality-based reputations, see:

  http://www.mudconnect.com/discuss/discuss.cgi?mode=MSG&area=adv_code&message=11022
_______________________________________________
MUD-Dev mailing list
MUD-Dev at kanga.nu
https://kanga.nu/lists/listinfo/mud-dev