I'm sorry, did I miss soemthing here?
On Friday, October 27, 2017, 5:46:19 AM EDT, Gian-Carlo Pascutto
<[email protected]> wrote:
On 27-10-17 00:33, Shawn Ligocki wrote:
> But the data should be different for different komi values, right?
> Iteratively producing self-play games and training with the goal of
> optimizing for komi 7 should converge to a different optimal player
> than optimizing for komi 5.
"For the policy (head) network, yes, definitely. It makes no difference
to the value (head) network."
The value network indicates whether the board leads to a win or not. This would
certainly depend on komi, especially in the half-point games which seem to be
the natural end result of how it selects moves?
_______________________________________________
Computer-go mailing list
[email protected]
http://computer-go.org/mailman/listinfo/computer-go
_______________________________________________
Computer-go mailing list
[email protected]
http://computer-go.org/mailman/listinfo/computer-go
