Comparison Training for Computer Chinese Chess
- 16 January 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 12 (2) , 169-176
Abstract
This paper describes the application of a modified comparison training for automatic feature weight tuning. The final objective is to improve the evaluation functions used in Chinese chess programs. First, we apply n-tuple networks to extract features. N-tuple networks require very little expert knowledge through its large numbers of features, while simultaneously allowing easy access. Second, we propose a modified comparison training into which tapered eval is incorporated. Experiments show that with the same features and the same Chinese chess program, the automatically tuned feature weights achieved a win rate of 86.58% against the hand-tuned ones. 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.Keywords
All Related Versions
Funding Information
- Ministry of Science and Technology, Taiwan (106-2221-E-009-139-MY2, 106-2221-E-305-017-MY2, 106-2221-E-009-140-MY2, 106-2221-E-305-016-MY2, 108-2634-F-009-011)
This publication has 23 references indexed in Scilit:
- Temporal difference learning of N-tuple networks for the game 20482014
- Comparison Training of Shogi Evaluation Functions with Self-Generated Training Positions and Moves2014
- The Global Landscape of Objective Functions for the Optimization of Shogi Piece Values with a Game-Tree SearchLecture Notes in Computer Science, 2012
- Analysis of Evaluation-Function Learning by Comparison of Sibling NodesLecture Notes in Computer Science, 2012
- Reinforcement Learning with N-tuples on the Game Connect-42012
- Computer shogiArtificial Intelligence, 2002
- Deep BlueArtificial Intelligence, 2002
- From Simple Features to Sophisticated Evaluation Functions1999
- A generalised quiescence search algorithmArtificial Intelligence, 1990
- An analysis of alpha-beta pruningArtificial Intelligence, 1975