Learning to Evaluate Chess Positions with Deep Neural Networks and Limited Lookahead

Matthia Sabatelli, Francesco Bidoia, Valeriu Codreanu, Marco Wiering

2018

Abstract

In this paper we propose a novel supervised learning approach for training Artificial Neural Networks (ANNs) to evaluate chess positions. The method that we present aims to train different ANN architectures to understand chess positions similarly to how highly rated human players do. We investigate the capabilities that ANNs have when it comes to pattern recognition, an ability that distinguishes chess grandmasters from more amateur players. We collect around 3,000,000 different chess positions played by highly skilled chess players and label them with the evaluation function of Stockfish, one of the strongest existing chess engines. We create 4 different datasets from scratch that are used for different classification and regression experiments. The results show how relatively simple Multilayer Perceptrons (MLPs) outperform Convolutional Neural Networks (CNNs) in all the experiments that we have performed. We also investigate two different board representations, the first one representing if a piece is present on the board or not, and the second one in which we assign a numerical value to the piece according to its strength. Our results show how the latter input representation influences the performances of the ANNs negatively in almost all experiments.

Paper Citation

in Harvard Style

Sabatelli M., Bidoia F., Codreanu V. and Wiering M. (2018). Learning to Evaluate Chess Positions with Deep Neural Networks and Limited Lookahead.In Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-276-9, pages 276-283. DOI: 10.5220/0006535502760283

in Bibtex Style

@conference{icpram18,
author={Matthia Sabatelli and Francesco Bidoia and Valeriu Codreanu and Marco Wiering},
title={Learning to Evaluate Chess Positions with Deep Neural Networks and Limited Lookahead},
booktitle={Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2018},
pages={276-283},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006535502760283},
isbn={978-989-758-276-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Learning to Evaluate Chess Positions with Deep Neural Networks and Limited Lookahead
SN - 978-989-758-276-9
AU - Sabatelli M.
AU - Bidoia F.
AU - Codreanu V.
AU - Wiering M.
PY - 2018
SP - 276
EP - 283
DO - 10.5220/0006535502760283