>Intuition tells us that transpositions are a good thing, and they certainly
>work very well in >alphabeta search. However, they do seem to interfere with
>the dynamics of the current >MC search algorithms. So I don't think there is a
>clear recipe for doing transpositions well >in MCTS yet. I hope this will
>change.
When assigning the credit value for a node which is a transposition, are *all*
parents which point to that node credited, or just the particular one which led
to that transposition in the current continuation? If the former case, that's
seems like the TT would lead to more efficient learning (a bit "RAVE like"
since a single trial results in multiple updates) although wouldn't it
be unwieldy for a node to have a list of pointers back to its multiple parents?
-- Greg
_______________________________________________
Computer-go mailing list
[email protected]
http://dvandva.org/cgi-bin/mailman/listinfo/computer-go
