Abstract
© Springer-Verlag Berlin Heidelberg 2001. The efficiency of alpha-beta search algorithms heavily depends on the order in which the moves are examined. This paper focuses on using neural networks to estimate the likelihood of a move being the best in a certain position. The moves considered more likely to be the best are examined first. We selected Lines of Action as a testing ground. We investigated several schemes to encode the moves in a neural net- work. In the experiments, the best performance was obtained by using one output unit for each possible move of the game. The results indicate that our move-ordering approach can speed up the search with 20 to 50 percent compared with one of the best current alternatives, the history heuristic.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 14th International conference on Industrial and engineering applications of artificial intelligence and expert systems: engineering of intelligent systems |
| Publisher | Springer Verlag |
| Pages | 45-50 |
| Number of pages | 6 |
| Volume | 2070 |
| ISBN (Print) | 9783540422198 |
| Publication status | Published - 2001 |
Cite this
Kocsis, L., Uiterwijk, J., & Van Den Herik, J. (2001). Move Ordering using Neural Networks. In Proceedings of the 14th International conference on Industrial and engineering applications of artificial intelligence and expert systems: engineering of intelligent systems (Vol. 2070, pp. 45-50). Springer Verlag. http://www.mendeley.com/research/move-ordering-using-neural-networks