Improving game-tree search with evolutionary neural networks

Abstract

Neural networks were evolved to constrain minimax search in the game of Othello. At each level of the search tree, such focus networks decide which moves are to be explored. Based on the evolved knowledge of the minimax algorithm's advantages and limitations the networks hide problem nodes from minimax. Focus networks were encoded in marker-based chromosomes and evolved against a full-width minimax opponent using the same heuristic board evaluation function. The focus network was able to guide the minimax search away from poor information, resulting in stronger play while examining far fewer nodes.<>