Hi;

http://arxiv.org/PS_cache/math/pdf/0508/0508580v2.pdf
>>
>
The top of page 4 in this paper is very clear - yes, pure Monte-Carlo (no
tree search!)
is optimal for these random-turn games.

 Impressive... The proof is simple, but it is
so unexpected that one can work 20 years on such games without observing
this I guess :-)

Best regards,
Olivier
_______________________________________________
Computer-go mailing list
[email protected]
http://dvandva.org/cgi-bin/mailman/listinfo/computer-go

Reply via email to