[Computer-go] CGT endgame solver

Hideki Kato hideki_katoh at ybb.ne.jp
Mon Jul 13 18:21:21 PDT 2015


>> yose-moves and play such moves in random orders.  Assuming there are 7, 
>> 3, 1 pts moves left at a end position, for example.  Correct order is 
>> obviously 7, 3 and 1 (sente gets +5 pts) but all combinations are played 
>> at the same probability in MC simulations now.  The average of the 
>> scores has, thus, a big error.  
>
>Does the MCTS program just play bad moves, or does it ever play
>game-losing moves? (E.g. at the point in the game where 2pt gote is the
>biggest move, which is still before CGT kicks in, isn't it?)

I can say just "heavily depends on the position", maybe, mainly due to 
maximizing not score but winning rate.  Another reason for high level 
games: playing correct moves at endgames requires correct solutions of 
L&D problems on a position.

>(I'm quite curious how many playouts are needed for correct play on
>http://senseis.xmp.net/diagrams/44/bc3b65c106c9db92bec3a13d0e713718.sgf
>- or do all the strong programs get it wrong and lose the game?)

Anyway, number of playouts does not help (or, at least help a little if 
using adaptive simulations) playing correct yose.  Number of playouts 
only reduces statistical errors.  If the average is wrong, quantity 
makes no sense.

Hideki
-- 
Hideki Kato <mailto:hideki_katoh at ybb.ne.jp>



More information about the Computer-go mailing list