It would be very difficult to put 1000 computers to work on a big
network to produce a single instance of a strong player.   There are way
too many interactions - it's difficult to split the work up in a
reasonable fashion.

It's probably possible, but would require a lot of study.   There are
certain compromises that effect the playing strength of a single
processor program but might be very good trade-offs for a such a beast.

- Don


Jason House wrote:
>
>
> On 10/30/07, [EMAIL PROTECTED]
> <mailto:[EMAIL PROTECTED]>* <[EMAIL PROTECTED]
> <mailto:[EMAIL PROTECTED]>> wrote:
>
>
>     > -----Original Message-----
>     > From: Jason House <[EMAIL PROTECTED]
>     <mailto:[EMAIL PROTECTED]>>
>     > To: computer-go <[email protected]
>     <mailto:[email protected]>>
>     > Sent: Mon, 29 Oct 2007 3:00 pm
>     > Subject: Re: [computer-go] BOINC
>
>
>
>     > On 10/29/07, [EMAIL PROTECTED]
>     <mailto:[EMAIL PROTECTED]>* <[EMAIL PROTECTED]
>     <mailto:[EMAIL PROTECTED]>> wrote:
>
>         >
>         > milestone 1: All network-nodes compute pure Monte-Carlo (no
>         search tree) scores for the possible moves, the > > > scores
>         are combined centrally to pick the move. It's easy, it will
>         wring out the system, and the bandwidth is low. > > The
>         playing performance will always be poor because this algorithm
>         doesn't scale well. 
>
>
>
>     > It scales, reasonably, but there's a maximum total work to do
>     before any extra becomes useless.
>
>
>     Both of our statements are so vague that I can't tell if we agree
>     or disagree. :) Here's what I meant. The consensus is that
>     Monte-Carlo with UCT converges in the limit, as time and memory
>     approach infinity, while Monte-Carlo by itself does not. In
>     practice, Monte-Carlo by itself plateaus out at around 5K
>     playouts/move. Don's scalability study tested Monte-Carlo with UCT
>     out past 1 Million playouts/move and found no sign of a plateau.
>     So if a network of 1000 computers played pure Monte-Carlo go, I
>     believe the playing strength would still be weak. Not so for UCT. 
>
>
>
> I think we're in agreement.  I didn't know about the 5k limit, but
> that's essentially what I was thinking.  Having 1 computer do 5k sims
> is pretty quick already.  Having 1000 computers doing 5 playouts each
> is just insanity.  The overhead would probably make it take as long
> (or longer) as 1 computer doing all of it.
>
> This is of course true only for pure monte carlo or other 1-ply variants.
>
>
> ------------------------------------------------------------------------
>
> _______________________________________________
> computer-go mailing list
> [email protected]
> http://www.computer-go.org/mailman/listinfo/computer-go/
_______________________________________________
computer-go mailing list
[email protected]
http://www.computer-go.org/mailman/listinfo/computer-go/

Reply via email to