Here is a simple optimization if someone want to give it a serious try:
When all 10 playouts for a move in the Meta-Playout either wins or
loses one could terminate the search early. If one need to be more
conservative one could terminate when the score is 0% or 100% N times
in a row.
Magnus
Quoting Don Dailey <[email protected]>:
What I tried was not a tree based version, so it's a very poor substitute.
I observed in private testing that even 10 playouts crushes 1 playout in a
simple non-tree based bot. So what I tried was doing recursive playouts -
instead of playing move randomly in the playouts each move in the playouts
was decided by it's own set of playouts.
It was a quick and dirty experiment, and I did not stick with it long enough
to do it justice, so I probably only tried naive versions of it. What I
did try did not work well at all.
- Don
On Thu, Jun 11, 2009 at 3:21 PM, Michael Williams <
[email protected]> wrote:
I tried it in my previous engine, which while probably littered with bugs,
at least had the characteristic that more playouts lead to better play.
This test was extremely slow and produced a weaker bot. YYWV.
I'm 95% sure Don mentioned it on this list a couple of years ago, but I
don't know if he actually tried it.
Gian-Carlo Pascutto wrote:
On Wednesday 10 June 2009 18:48:55 Martin Mueller wrote:
Currently, we try to sidestep this fundamental problem by replacing
local search with local knowledge, such as patterns. But that does not
fully use the power of search.
So, has anyone tried recursive UCT (using UCT again in the playouts), and
what were the results? I saw some results for uninteresting games, but
nothing about Go.
_______________________________________________
computer-go mailing list
[email protected]
http://www.computer-go.org/mailman/listinfo/computer-go/
--
Magnus Persson
Berlin, Germany
_______________________________________________
computer-go mailing list
[email protected]
http://www.computer-go.org/mailman/listinfo/computer-go/
