Move Ordering Using Neural Networks

Authors:
Levente Kocsis;Jos W. H. M. Uiterwijk;H. Jaap van den Herik
Affiliations:
-;-;-
Venue:
Proceedings of the 14th International conference on Industrial and engineering applications of artificial intelligence and expert systems: engineering of intelligent systems
Year:
2001

Citing 2
Cited 3

Computer chess move-ordering schemes using move influence

Artificial Intelligence
Learning Time Allocation Using Neural Networks

CG '00 Revised Papers from the Second International Conference on Computers and Games

An effective two-level proof-number search algorithm

Theoretical Computer Science - Algorithmic combinatorial game theory
Enhanced forward pruning

Information Sciences: an International Journal
The relative history heuristic

CG'04 Proceedings of the 4th international conference on Computers and Games

Quantified Score

Hi-index	0.01

Visualization

Abstract

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 network. 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.