Re: [Fwd: Re: Strong players only?]

[Darren Cook <darren@xxxxxxxxxxxxxx>]

>Computer go is definitely not like computer chess because we do know very
well
>that brute force will *never* be an issue in computer go : a good go programm

If brute force means doing lots and lots of simple tasks - tedious and
stupid by human standards - then I think when very strong go programs
appear they will be doing brute force. Of course it is likely to be a
different kind of brute force from that used in chess (exhaustive search to
10-20 ply).

>-what is a good judgement of a situation ? (I do not mean an evaluation
fonction
>because I'm quite sure that you cannot summarize a (statically) complex
position
>in a single number  : so what ?

This is possible in the end game. Though I think a multi-valued evaluation
function (even just returning territory and influence estimates) might be
the best way to go for the middle-game.  How this would work in an minimax
tree is a very interesting research project, and useful in other AI fields,
but strangely no-one seems to be working on it (at least I've not seen any
papers).

Darren