Olivier: You paper at http://hal.inria.fr/inria-00512854/ has a black stone missing in Fig 4. at o19
-------------+ B . O X O . | O O O X O . | X O X X X X | Fig 4 the stone marked as B is missing. (Otherwise, Fuego's move would not be bad, as 4 would merely be a threat an the black corner group could not be saved.) I got the right position from Nick Wedd's report. See how in-depth we revise your papers. ;-) PD. Interesting paper, not just about parallelization but contains many nice ideas. Jacques. *Olivier Teytaud wrote:*
In MoGo it's not root parallelization. We share the statistics in the tree, e.g. once per second (depending on the time settings); more precisely, we average - the number of wins, - the number of losses, - the number of amaf-wins - the number of amaf-losses in all nodes in the tree with more than e.g. 5% of the number of simulations at the root.
This is not so different from averaging just at the root, but there's a slight improvement. (the difference is probably much higher when building strategies, as in opening book building, instead of just choosing one move) It is, on the other hand, much better than averaging just before taking the decision (i.e., roughly speaking, voting) as proposed in some papers. More details in http://hal.inria.fr/inria-00512854/. <http://hal.inria.fr/inria-00512854/> Best regards, Olivier
_______________________________________________ Computer-go mailing list [email protected] http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
