[computer-go] Test position set for MC programs

[Don Dailey]

Yamato wrote:
> Don Dailey wrote:
>   
>> Go problems don't work for MC programs unless you can arrange them so
>> that finding the right move wins, and anything else loses.   I found you
>> can modify some problems by manipulating the komi to make this true.  
>>     
>
> I intend to have adjusted all of them like that (only 1 move = win).
> Do you mean you found some problems are wrong?
>
>   
No, I don't know if any are wrong (I didn't look at the set yet.)

If you have adjusted these so that one and only one move wins the game,
then it should be a usable set.

You should be able to study scalability with a good properly constructed
test set.  

- Don


> --
> Yamato
> _______________________________________________
> computer-go mailing list
> computer-go at computer-go.org
> http://www.computer-go.org/mailman/listinfo/computer-go/
>
>