Systematic N-tuple Networks for Position Evaluation: Exceeding 90% in the Othello League
This work addresses the challenge of improving AI performance in board games for researchers and practitioners, though it is incremental as it builds on existing n-tuple network methods.
The authors tackled the problem of designing effective n-tuple networks for position evaluation in board games like Othello by proposing a systematic placement of many short, straight n-tuples instead of random long ones, resulting in a network with only 288 weights achieving nearly 96% performance in the Othello League.
N-tuple networks have been successfully used as position evaluation functions for board games such as Othello or Connect Four. The effectiveness of such networks depends on their architecture, which is determined by the placement of constituent n-tuples, sequences of board locations, providing input to the network. The most popular method of placing n-tuples consists in randomly generating a small number of long, snake-shaped board location sequences. In comparison, we show that learning n-tuple networks is significantly more effective if they involve a large number of systematically placed, short, straight n-tuples. Moreover, we demonstrate that in order to obtain the best performance and the steepest learning curve for Othello it is enough to use n-tuples of size just 2, yielding a network consisting of only 288 weights. The best such network evolved in this study has been evaluated in the online Othello League, obtaining the performance of nearly 96% --- more than any other player to date.