Abstract
The Pareto-based Differential Evolution (PDE) algorithm is one of the current state-of-the-art Multi-objective Evolutionary Algorithms (MOEAs). This paper describes a series of experiments using PDE for evolving artificial neural networks (ANNs) that act as game-playing agents. Three systems are compared: (i) a canonical PDE system, (ii) a co-evolving PDE system (PCDE) with 3 different setups, and (iii) a co-evolving PDE system that uses an archive (PCDE-A) with 3 different setups. The aim of this study is to provide insights on the effects of including co-evolutionary techniques on a well-known MOEA by investigating and comparing these 3 different approaches in evolving intelligent agents as both first and second players in a deterministic zero-sum board game. The results indicate that the canonical PDE system outperformed both co-evolutionary PDE systems as it was able to evolve ANN agents with higher quality game-playing performance as both first and second game players. Hence, this study shows that a canonical MOEA without co-evolution is desirable for the synthesis of cognitive game AI agents.
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
Preview
Unable to display preview. Download preview PDF.
References
Davis, J., Kendall, G.: An investigation, using coevolution, to evolve an awari player, 2002. In: Proc. of the IEEE CEC ’02, pp. 1408–1413. IEEE Computer Society Press, Los Alamitos (2002)
Monroy, G.A., Stanley, K.O., Miikkulainen, R.: Coevolution of neural networks using a layered pareto archive. In: Proc. of GECCO ’06, pp. 329–336. ACM Press, New York (2006)
Panait, L., Luke, S.: A comparison of two competitive fitness functions. In: W. B. L., et al. (eds.) Proc. of GECCO ’02, pp. 503–511 (2002)
Mayer, H.A., Maier, P.: Coevolution of neural Go players in a cultural environment. In: Proc. of the IEEE CEC ’05, vol. 2, pp. 1017–1024. IEEE, Los Alamitos (2005)
Lubberts, A., Miikkulainen, R.: Co-evolving a go-playing neural network. In: Belew, R.K., Juillè, H. (eds.) Coevolution: Turning Adaptive Algorithms upon Themselves, San Francisco, California, USA, pp. 14–19 (2001)
Chellapilla, K., Fogel, D.B.: Evolution, neural networks, games, and intelligence. Proceedings of IEEE 87(9), 1471–1496 (1999)
Yau, Y.J., Teo, J.: An empirical comparison of non-adaptive, adaptive and self-adaptive co-evolution for evolving artificial neural network game players. In: Proc. IEEE CIS ’06, pp. 405–410. IEEE, Los Alamitos (2006)
Yau, Y.J., Teo, J.: Co-evolving Neural Agents for Game AI: From Single-objective to Pareto Multi-objective Evolution. In: The 22nd ACM Symposium on Applied Computing (SAC’07), Seoul, Korea, ACM Press, New York (Submitted, 2007)
Abbass, H.A., Sarker, R.: The Pareto Differential Evolution Algorithm. International Journal on Artificial Intelligence Tools 11(4), 531–552 (2002)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Yau, Y.J., Teo, J., Anthony, P. (2007). Pareto Evolution and Co-evolution in Cognitive Game AI Synthesis. In: Obayashi, S., Deb, K., Poloni, C., Hiroyasu, T., Murata, T. (eds) Evolutionary Multi-Criterion Optimization. EMO 2007. Lecture Notes in Computer Science, vol 4403. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-70928-2_20
Download citation
DOI: https://doi.org/10.1007/978-3-540-70928-2_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-70927-5
Online ISBN: 978-3-540-70928-2
eBook Packages: Computer ScienceComputer Science (R0)