Strategies Anticipating a Difference in Search Depth using Opponent-Model Search

In this contribution we propose a class of strategies which focus on the game as well as on the opponent. Preference is given to the thoughts of the opponent, so that the strategy under investigation might be speculative. We describe a generalization of OM search, called (D, d)-OM search, where D stands for the depth of search by the player and D stands for the opponent's depth of search. A known difference in search depth can be exploited by purposely choosing a suboptimal variation with the aim to gain a larger advantage than when playing the objectively best move. The difference in search depth may have the result that the opponent does not see the variation in sufficiently deep detail. We then give a pruning alternative for (D,d)-OM search, denoted by alpha-beta (2) pruning. A best-case analysis shows that alpha-beta (2) prunes very efficiently, comparable to the efficiency of alpha-beta with regard to minimax. The effectiveness of the proposed strategy is confirmed by simulations using a game-tree model including an opponent model and by experiments in the domain of Othello.