While MCTS works "better" in games with a forward direction, it eventually converges to the same answer as alpha-beta in any game. The general architecture is to set a maximum depth, and use a suitable evaluator at the leaf nodes.
I haven't done detailed studies, but there is definitely a space where (for example) a 30 second MCTS with a depth limit of 20 ply will outperform a progressive-deepening alpha-beta that is allowed 30 seconds. Another advantage of MCTS is that it's easy to run multiple threads, which is not true of alpha-beta. _______________________________________________ Computer-go mailing list Computer-go@computer-go.org http://computer-go.org/mailman/listinfo/computer-go
