Posts: 650 Location: Adelaide, South Australia Liked others: 219 Was liked: 281
Rank: Australian 3 dan
GD Posts: 200
Getting KataGo to solve tsumego is an interesting game! Often, if you put a life and death problem in a corner and leave the rest of the board empty, KataGo will just tell you that the first move in an empty corner is bigger. The challenge is to construct a whole-board position where the tsumego is hotter than anything else. But it's worse than that. Even if you can persuade it to pick the "right" corner, KataGo will suggest different moves depending on the whole-board context.
[go]$$B Black to play and kill $$ -------------------- $$ | . . . . . . X . . . $$ | O O . . . O O X . . $$ | X X O . . O X O X . $$ | . X O O O X X . . , $$ | . . X . X . . . . . $$ | . X . . X . . . . . $$ | . . . . . . . . . .[/go]
[go]$$B Black to play and kill $$ -------------------- $$ | . . . . . . X 3 . . $$ | O O 2 1 . O O X . . $$ | X X O . . O X O X . $$ | . X O O O X X . . , $$ | . . X . X . . . . . $$ | . X . . X . . . . . $$ | . . . . . . . . . .[/go]
On a first look, I missed -- and indeed this is where KataGo also gets stuck.
[go]$$B failure $$ -------------------- $$ | . . . . 3 4 X 6 . . $$ | O O 2 1 . O O X . . $$ | X X O . 5 O X W X . $$ | . X O O O X X . . , $$ | . . X . X . . . . . $$ | . X . . X . . . . . $$ | . . . . . . . . . .[/go]
This choice of feels more intuitive, but fails because is atari. This is where comes into play.
[go]$$B Black cuts off the tail $$ -------------------- $$ | . . . 6 . 5 X . . . $$ | O O . 2 1 O O X . . $$ | X X O 4 3 O X O X . $$ | . X O O O X X . . , $$ | . . X . X . . . . . $$ | . X . . X . . . . . $$ | . . . . . . . . . .[/go]
In some contexts, KataGo quite likes this choice of , capturing three stones. Often it will suggest that white should tenuki, but there's the option of living later on.
I've constructed three full-board positions:
Balanced: black can win if and only if black kills the top left group.
Ahead: black can win without killing (but killing is still presumably the best move)
Behind: killing makes the game close, and is still the best option, but white is ahead
In the first situation, KataGo solves it quickly. But in the others, it has a surprising amount of trouble finding the key move, and prefers the alternative variation.
Note: I'm still on KataGo 1.3.2 with a 20-block network, too lazy to upgrade at the moment! Please post here if you get different results with newer versions.
If you use a GUI, most of them support this in some way.
If you analyze a board with your corner stones only and restrict the analysis for 20 moves to the smallest rectangle that includes all stones, KataGo will quickly find the right move and continuation (with a 40b network, 20b doesn't get it right).
Users browsing this forum: No registered users and 1 guest
You cannot post new topics in this forum You cannot reply to topics in this forum You cannot edit your posts in this forum You cannot delete your posts in this forum You cannot post attachments in this forum