Abstract
Within this paper we evaluate the components used to build a checkers playing system with no embedded expert knowledge. We found that Particle Swarm Optimisation (PSO) and Evolutionary Algorithms (EA) are suitable training methods for Artificial Neural Networks (ANN) acting as evaluation functions within minimax, when training on 2 and 4 plies. By playing the trained networks against one other the single best network was found, which was produced by 3000 iterations of PSO playing on 2 plies. We show that this network outperformed a piece differential evaluation function, both on a fixed number of plies, and when using iterative deepening search. We also show that the higher the amount of plies the better a system will perform, however it is the relative difference between the amount of plies that impacts the performance. External validation of the system shows it winning all 44 games it played against non-expert human players. It was also able to solve the hardest tasks on a checkers problem website. The system was also able to draw against Chinook, a checkers playing system with expert knowledge and state-of-the-art in the field.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Checker Cruncher. https://www.checkercruncher.com/
Go Ratings. https://www.goratings.org/en/
ItsYourTurn.com - Help Page. https://www.itsyourturn.com/t_helptopic2030.html
Boonzaaier, D.: Training neural networks for checkers. Ph.D. thesis (2017)
Campbell, M., Hoane, A.J., Hsu, F.H.: Deep Blue. Artif. Intell. 134(1–2), 57–83 (2002). https://doi.org/10.1016/S0004-3702(01)00129-1
Chellapilla, K., Fogel, D.B.: Evolving neural networks to play checkers without relying on expert knowledge. IEEE Trans. Neural Netw. 10(6), 1382–1391 (1999). https://doi.org/10.1109/72.809083
Franken, N., Engelbrecht, A.P.: Comparing PSO structures to learn the game of checkers from zero knowledge. In: 2003 Congress on Evolutionary Computation, CEC 2003 - Proceedings (2003). https://doi.org/10.1109/CEC.2003.1299580
Hsu, F.H., Campbell, M., Hoane, J.: Deep Blue system overview. In: Proceedings of the 9th International Conference on Supercomputing, ICS 1995, pp. 240–244 (1995). https://doi.org/10.1145/224538.224567
Kennedy, J., Eberhart, R.: Particle swarm optimization. In: Proceedings of ICNN 1995 - International Conference on Neural Networks, vol. 4, pp. 1942–1948 (November 1995). https://doi.org/10.1109/ICNN.1995.488968
Knuth, D.E., Moore, R.W.: An analysis of alpha-beta pruning. Artif. Intell. 6(4), 293–326 (1975). https://doi.org/10.1016/0004-3702(75)90019-3
Korf, R.E.: Depth-first iterative-deepening. An optimal admissible tree search. Artif. Intell. 27(1), 97–109 (1985). https://doi.org/10.1016/0004-3702(85)90084-0
Messerschmidt, L.: Using particle swarm optimization to evolve two-player game agents (2005)
Poli, R., Kennedy, J., Blackwell, T.: Particle swarm optimization. Swarm Intell. 1, 33–57 (2007). https://doi.org/10.1007/s11721-007-0002-0
Schaeffer, J., et al.: Checkers is solved. Science 317(5844), 1518–1522 (2007). https://doi.org/10.1126/science.1144079
Silver, D., et al.: Mastering the game of Go without human knowledge. Nature (2017). https://doi.org/10.1038/nature24270
Sousa-Ferreira, I., Sousa, D.: A review of velocity-type PSO variants. J. Algorithms Comput. Technol. (2017). https://doi.org/10.1177/1748301816665021
Taherdangkoo, M., Paziresh, M., Yazdi, M., Bagheri, M.H.: An efficient algorithm for function optimization: modified stem cells algorithm. Cent. Eur. J. Eng., pp. 36–50. (2013). https://doi.org/10.2478/s13531-012-0047-8
University of Alberta: Play Chinook. https://webdocs.cs.ualberta.ca/~chinook/play/
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Bunce, E., Keedwell, E. (2020). Optimisation of a Checkers Player Using Neural and Metaheuristic Approaches. In: Idoumghar, L., Legrand, P., Liefooghe, A., Lutton, E., Monmarché, N., Schoenauer, M. (eds) Artificial Evolution. EA 2019. Lecture Notes in Computer Science(), vol 12052. Springer, Cham. https://doi.org/10.1007/978-3-030-45715-0_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-45715-0_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-45714-3
Online ISBN: 978-3-030-45715-0
eBook Packages: Computer ScienceComputer Science (R0)