On Wed, Jun 16, 2010 at 07:48:46PM +0800, Fuming Wang wrote:
> We are able to run 167 games in parallel. Unfortunately, it is not easy to
> incorporate FPGA based simulation into UCT based MCTS scheme. So, we are
> trying the traditional alpha-beta type tree search method to try to evaluate
> the usefulness of our FPGA based MC simulation.
Do all the games have to start synchonously?
I think it would still be much better than alpha-beta with MC to do a
UCT search with m * n playouts where you run m parallel descends with
n playouts evaluated in the leaf. It is probably good idea to spread
the descends using virtual loss, not sure if adding 1 or n losses would
be better, perhaps a depth-dependent fraction rounded up would be
best... Of course, having strongly pre-biased node values would help
a lot here, I guess.
m would be tuned so that you could pre-descend m times for next set of
playouts while FPGA would walk the first m. The disadvantage of course
is that you are descending on a tree that is missing (2*m-1)*n samples
(you are doing basically 2*m samples in parallel). If the FPGA supports
asynchronous game queuing, it would be of course much better as you
could queue next set of games right after the descent, so the
obsolescence factor would be just m*n (m+1 samples in parallel).
Well, maybe this was all obvious to you, but it is not possible for you
to easily do this in your framework?
--
Petr "Pasky" Baudis
The true meaning of life is to plant a tree under whose shade
you will never sit.
_______________________________________________
Computer-go mailing list
[email protected]
http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
