On Wednesday, July 16, 2003, at 10:42 AM, Markus Enzenberger wrote:
This raises another question: is there a good cheap criterion for quiescence in Go?not a full search, only the quiescence search, which is much cheaper.
Presumably the evaluation function has learned some intuitions about life, influence, and territory.I don't think that it is a bad idea to use an evaluation function that was trained with TD and 1-ply look-ahead later in deeper searches. I am doing this with NeuroGo on the 9x9 board and doing a 3-ply full-board search makes it significantly stronger.