Deep Learning and the Game of Checkers

Jan Popic; Borko Boskovic; Janez Brest

doi:10.13164/mendel.2021.2.001

Jan Popic Institute of Computer Science, Faculty of Electrical Engineering and Computer Science, University of Maribor, Maribor, Slovenia
Borko Boskovic Institute of Computer Science, Faculty of Electrical Engineering and Computer Science, University of Maribor, Maribor, Slovenia
Janez Brest Institute of Computer Science, Faculty of Electrical Engineering and Computer Science, University of Maribor, Maribor, Slovenia

DOI: https://doi.org/10.13164/mendel.2021.2.001

Keywords: Artificial Intelligence, Deep Learning, Convolutional Neural Network, Reinforcement Learning, Checkers

Abstract

In this paper we present an approach which given only a set of rules is able to learn to play the game of Checkers. We utilize neural networks and reinforced learning combined with Monte Carlo Tree Search and alpha-beta pruning. Any human influence or knowledge is removed by generating needed data, for training neural network, using self-play. After a certain number of finished games, we initialize the training and transfer better neural network version to next iteration. We compare different obtained versions of neural networks and their progress in playing the game of Checkers. Every new version of neural network represented a better player.

References

Baek, M., DiMaio, F., Anishchenko, I., Dauparas, J., Ovchinnikov, S., et al. Accurate prediction of protein structures and interactions using a three-track neural network. Science 373, 6557 (2021), 871-876.

Foster, D. Deep reinforcement learning. Available at https://github.com/AppliedDataSciencePartners/DeepReinforcementLearning, 2018.

Ioffe, S., and Szegedy, C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proceedings of the 32Nd International Conference on Machine Learning - Volume 37 (2015), ICML'15, JMLR.org, pp. 448-456.

Samuel, A. L. Some studies in machine learning using the game of checkers. IBM Journal of research and development 3, 3 (1959), 210-229.

Schaeffer, J., Burch, N., Bjornsson, Y., Kishimoto, A., Muller, M., Lake, R., Lu, P., and Sutphen, S. Checkers is solved. Science 317, 5844 (2007), 1518-1522.

Schmidhuber, J. Deep learning in neural networks: An overview. Neural networks 61 (2015), 85-117.

Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., et al. Mastering the game of go with deep neural networks and tree search. Nature 529 (Jan 2016), 484 EP.

Silver, D., Hubert, T., Schrittwieser, J., Antonoglou, I., Lai, M., et al. A general reinforcement learning algorithm that masters chess, shogi, and go through self-play. Science 362, 6419 (2018), 1140-1144.

Silver, D., Schrittwieser, J., Simonyan, K., Antonoglou, I., Huang, A., et al. Mastering the game of go without human knowledge. Nature 550 (Oct 2017), 354 EP.

Srinidhi, C. L., Ciga, O., and Martel, A. L. Deep neural network models for computational histopathology: A survey. Medical Image Analysis 67 (2021), 101813.