Abstract
Evolutionary multi-objective optimization (EMO) has gained popularity and it has been successfully applied in several research areas. Based on the literature review conducted, EMO approach has not been applied in any Go game application. In this study, artificial neural networks (ANNs) are evolved with an EMO algorithm, Pareto Archived Evolution Strategies (PAES) for computer player to learn and play the 7x7 board Go game against GNU Go. In this study, two conflicting objectives are investigated: first, maximize the ability of neural player to play the Go game and second, minimize the complexity of the ANN by reducing the hidden units. Several comparative empirical experiments were conducted that showed EMO which optimize two distinct and conflicting objectives outperformed the single-objective (SO) optimization which only optimized the first objective with no pressure selection on the second objective.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Bouzy, B., Cazenave, T.: Computer Go: an AI Oriented Survey. Artificial Intelligence Journal 132, 39–103 (2001)
Thu Bui, L., Alam, S.: Multi-Objective Optimization in Computational Intelligence: Theory and Practice. Information Science Reference, Hershey (2008)
Coello Coello, C.A., Pulido, G.T., Montes, E.M.: Current and Future Research Trends in Evolutionary Multiobjective Optimization. In: Grana, M., Duro, R., d’Anjou, A., Wang, P.P. (eds.) Information Processing with Evolutionary Algorithms: From Industrial Applications to Academic Speculations, pp. 213–231. Springer, London (2005)
Corne, D.W., Knowles, J.D.: Techniques for Highly Multiobjective Optimisation: Some Nondominated Points are Better than Others. Computing Research Repository (CoRR) abs/0908.3025 (2009)
Enzenberger, M.: Evaluation in Go by a Neural Network Using Soft Segmentation. In: 10th Advances in Computer Games Conference (ACG-10), Graz, Styria, Austria, pp. 97–108 (2003)
Gauci, J., Stanley, K.O.: Indirect Encoding of Neural Networks for Scalable Go. In: Schaefer, R., Cotta, C., Kołodziej, J., Rudolph, G. (eds.) PPSN XI, Part I. LNCS, vol. 6238, pp. 354–363. Springer, Heidelberg (2010)
GnuGo Documentation, http://www.gnu.org/software/gnugo/gnugo_toc.html (access on January 2012)
Lubberts, A., Miikkulainen, R.: Co-Evolving a Go-Playing Neural Network. In: Coevolution: Turning Adaptive Algorithms upon Themselves, Birds-of-a-Feather Workshop, Genetic and Evolutionary Computation Conference (GECCO), San Francisco, MA, USA (2001)
Lucas, S.M.: Computational Intelligence and Games: Challenges and Opportunities. International Journal of Automation and Computing 5(1), 45–57 (2008)
Mayer, H.A.: Board Representations for Neural Go Players Learning by Temporal Difference. In: IEEE Symposium on Computational Intelligence and Games (CIG), Honolulu, Hawaii, USA, pp. 183–188 (2007)
Mayer, H.A., Maier, P.: Coevolution of Neural Go Players in a Cultural Environment. In: Congress on Evolutionary Computation (CEC), Edinburgh, Scotland, pp. 1017–1024 (2005)
Runarsson, T.P., Lucas, S.M.: Coevolution Versus Self-Play Temporal Difference Learning for Acquiring Position Evaluation in Small-Board Go. IEEE Transactions on Evolutionary Computation 9(6), 628–640 (2005)
Stanley, K.O., Miikkulainen, R.: Evolving a Roving Eye for Go. In: Deb, K., Tari, Z. (eds.) GECCO 2004. LNCS, vol. 3103, pp. 1226–1238. Springer, Heidelberg (2004)
Teo, J., Abbass, H.A.: Elucidating the Benefits of A Self-Adaptive Pareto EMO Approach for Evolving Legged Locomotion in Artificial Creatures. In: IEEE Conference on Evolutionary Computation (CEC), vol. 2, pp. 755–762. IEEE Press, Canberra (2003)
Van der Werf, E.C.D., Winands, M.H.M.: Solving Go for Rectangular Boards. ICGA Journal 32(2), 77–88 (2009)
Van der Werf, E.C.D., Van den Herik, H.J., Uiterwijk, J.W.H.M.: Solving Go on Small Boards. International Computer Games Association (ICGA) Journal 26(2), 92–107 (2003)
Wu, L., Baldi, P.: Learning to Play Go Using Recursive Neural Networks. Neural Network 21(9), 1392–1400 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tan, K.B., Teo, J., Chin, K.O., Anthony, P. (2012). An Evolutionary Multi-objective Optimization Approach to Computer Go Controller Synthesis. In: Anthony, P., Ishizuka, M., Lukose, D. (eds) PRICAI 2012: Trends in Artificial Intelligence. PRICAI 2012. Lecture Notes in Computer Science(), vol 7458. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32695-0_76
Download citation
DOI: https://doi.org/10.1007/978-3-642-32695-0_76
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-32694-3
Online ISBN: 978-3-642-32695-0
eBook Packages: Computer ScienceComputer Science (R0)