Abstract
We review two previous simulations in which opponent modelling was performed within the computer game of pong. These results suggested that sums of local models were better than a single global model on this data set. We compare two supervised methods, the multilayered perceptron, which is global, and the radial basis function network which is a sum of local models on this data and again find that the latter gives better performance. Finally we introduce a new topology preserving network which can give very local or more global estimates of results and show that, while the local estimates are more accurate, they result in game play which is less human-like in behaviour.
An erratum to this chapter can be found at http://dx.doi.org/10.1007/11550907_163 .
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
Bishop, C.M., Svensen, M., Williams, C.K.I.: Gtm: The generative topographic mapping. Neural Computation (1997)
Fyfe, C.: Topographic product of experts. In: International Conference on Artificial Neural Networks. In: ICANN 2005 (2005)
Haykin, S.: Neural Networks- A Comprehensive Foundation. Macmillan, Basingstoke (1994)
Kohonen, T.: Self-Organising Maps. Springer, Heidelberg (1995)
Leen, G., Fyfe, C.: Training an ai player to play pong using the gtm. In: IEEE Symposium on Computational Intelligence and Games (2005)
McGlinchey, S.: Learning of ai players from game observation data. In: Proceedings of Fourth International Conference on Intelligent games and Simulation, pp. 106–110 (2003); ISBN: 90-77381-05-8
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fyfe, C. (2005). Local vs Global Models in Pong. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds) Artificial Neural Networks: Formal Models and Their Applications – ICANN 2005. ICANN 2005. Lecture Notes in Computer Science, vol 3697. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11550907_154
Download citation
DOI: https://doi.org/10.1007/11550907_154
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28755-1
Online ISBN: 978-3-540-28756-8
eBook Packages: Computer ScienceComputer Science (R0)