[MUD-Dev] Neural Networks as the AI system for a MUD?

[Hans-Henrik Staerfeldt]

On Thu, 2 Dec 1999 PartyG2816 at aol.com wrote:

> The subject says it all.  I'm out researching various AI tools and i hi=
t upon=20
> NN's. From the bit I have read, they seem rather interesting, and very =
well=20
> suited to a MUD's needs for AI.. But I still haven't read far enough to=
=20
> really /know/ if you know what I mean... I thought maybe some of you mo=
re=20
> experienced people on here might have used em or know ab it about them.=
.=20

Artifical Neural Networks are a bit simplistic for anything i would use
for AI in a mud. Perhaps the neural net could be used as a tool for a=20
rulebased AI, where the NN is used to try and identify 'situations' where
a given ruleset would apply, but i cannot see how NN could be accounting=20
for AI by its own.

Specifically you need to 'display' the events in the mud intelligently to
the neural net. The better you port your event into the 'problem domain',
that the network is trying to solve, the better you probably will get the=
=20
network to perform.

Another problem is CPU power, as someone else also commented on, training
or using (which is less demanding than training) the networks of thoustan=
ds
of NPC NN's would be very demanding, even on today's hardware.

What you perhaps should think very hard about, is where in your AI you wa=
nt=20
to use NN for in your AI. Remember you do not get 'problem solving abilit=
y'
just because you interconnect a few thousand neurons.

As before, you could try using the neural nets for guessing wants/needs o=
r
threat/non threat, friend/enemy and other hard-definable feature, and use=
=20
these ovservations later on.

Then of course you need to train the network, you need a set of situation=
s
that you can display to the network, and then tell it if it performed
correctly or not. This may be, if possible, to train the network on-line,=
=20
that the network at one time may predict some situation, and then at a la=
ter=20
time be able to definitively tell if it predicted right or not, and that =
way=20
learn from its mistake/success. However, you can also set up a set of cas=
es=20
offline and start by training on them first.

> And=20
> if that fails, if you can also provide a few other ideas for me to look=
 up=20
> after I  get done digging into NN's :)
>=20
> JD

Another idea (which better deal with time-sequences) is hidden markov mod=
els.
Although they are at-least as demanding to use as NN's.=20


My background; I work with biological sequence analysis, where we use the
NN's/HMM's, to match patterns in biological sequences (i.e. DNA and prote=
ins).

Hans Henrik St=E6rfeldt   |    bombman at diku.dk    | work:  hhs at cbs.dtu.dk=
      |
address:                |___  +45 40383492    __|__       +45 45252425   =
  __|
 Dybendalsvej 74 2. th, | Scientific programmer at Center for Biological =
    |
 2720 Vanl=F8se, Danmark. |  Sequence Analysis, Technical University of D=
enmark|




_______________________________________________
MUD-Dev maillist  -  MUD-Dev at kanga.nu
http://www.kanga.nu/lists/listinfo/mud-dev