[computer-go] producing a good probability distribution over legal moves

[David Doshay]

On 17, May 2007, at 8:17 AM, Brian Slesinsky wrote:

> A weakness of this approach is that sometimes the best move depends on
> how you plan to follow it up; a program that plays the theoretically
> best move but doesn't know how to follow it up is weaker than a
> program that plays safer moves.

I have often said that when SlugGo makes what looks to me to be a
really good move, my joyful surprise quickly turns to worry about
what is about to happen. It is exactly this inability to make the proper
continuing followup moves that is the problem.



Cheers,
David