Comparison Training for Computer Chinese Chess

TL;DR

This paper introduces a comparison training approach with n-tuple networks and tapered evaluation for tuning Chinese chess evaluation functions, achieving high win rates against hand-tuned weights.

Contribution

It proposes a novel combination of n-tuple networks and tapered evaluation within comparison training for automatic feature weight tuning in Chinese chess.

Findings

Comparison training with n-tuple networks outperforms hand-tuned weights.

Adding n-tuple features further improves performance.

Achieved 86.58% win rate against hand-tuned weights.

Abstract

This paper describes the application of comparison training (CT) for automatic feature weight tuning, with the final objective of improving the evaluation functions used in Chinese chess programs. First, we propose an n-tuple network to extract features, since n-tuple networks require very little expert knowledge through its large numbers of features, while simulta-neously allowing easy access. Second, we propose a novel evalua-tion method that incorporates tapered eval into CT. Experiments show that with the same features and the same Chinese chess program, the automatically tuned comparison training feature weights achieved a win rate of 86.58% against the weights that were hand-tuned. The above trained version was then improved by adding additional features, most importantly n-tuple features. This improved version achieved a win rate of 81.65% against the trained version without additional features.