Only recently Monte-Carlo Tree Search (MCTS) has substantially contributed to the field of computer Go. So far, in standard MCTS there is only one type of node: every node of the tree represents a single move. Instead of maintaining only this type of node, we propose a second type of node representing groups of moves. Thus, the tree may contain move nodes and group nodes. This article documents how such group nodes can be utilised for including domain knowledge in MCTS. Furthermore, we present a technique, called Alternating-Layer UCT, for managing move nodes and group nodes in a tree with alternating layers of move nodes and group nodes. A self-play experiment performed in the game of Go demonstrates that group nodes can be used effectively to integrate domain knowledge in a MCTS program and thereby improve its playing strength.
|Title of host publication||19th Belgian-Dutch Conference on Artificial Intelligence|
|Number of pages||8|
|Publication status||Published - 2007|