I have measured whether you should speculatively ponder (i.e., guess your
opponent's play and then ponder, hoping that you will be right) versus
pondering your opponent's choice.

My measurements favored pondering your opponent's choice. The difference was
small, as you might expect.

I believe that the reason speculatively pondering works worse for Pebbles is
that when the opponent has no choice, (i.e., a forced reply) then Pebbles
ends up focusing entirely on that move anyway. That is, speculatively
pondering
does not gain much in that case. But when the opponent has a choice, then
the search spreads its attention, and picks up *some* gain on most moves.

Note that this result differs from chess, for example, where speculatively
pondering is definitely better.

Why chess works out differently: the move matching rate in chess is roughly
50%, so by speculatively pondering you can increase your thinking time by
50%.
When you ponder by thinking about the opponent's play, then you gain
according
to the inverse of the branching factor. (Because you are going to throw away
one layer of the tree.) Since the branching factor in chess trees is > 2,
you will gain less than 50%. A key point in this analysis is that the move
matching rate for an N ply search is not significantly better than the move
matching rate for an N+1 ply search.

Branching factors in a UCT/RAVE tree are nominally very large, but in effect
are extraordinarily narrow. Almost all attention concentrates on a handful
of choices.

Brian


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

Reply via email to