Abstract
Robustness has long been recognised as a critical issue for co-evolutionary learning. It has been achieved in a number of cases, though usually in domains which involve some form of non-determinism. We examine a deterministic domain — a pseudo real-time two-player game called Tron - and evolve a neural network player using a simple hill-climbing algorithm. The results call into question the importance of determinism as a requirement for successful co-evolutionary learning, and provide a good opportunity to examine the relative importance of other factors.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Blair, A. and Sklar, E. (1998). The evolution of subtle manoeuvres in simulated hockey. In Proc. of SAB-5.
Blair, A. D. and Pollack, J. (1997). What makes a good co-evolutionary learning environment? Australian Journal of Intelligent Information Processing Systems, 4(3/4):166–175.
Ficici, S. and Pollack, J. (1998). Challenges in coevolution-ary learning: Arms-race dynamics, open-endedness, and mediocre stable states. In Proc. of ALIFE-6.
Funes, P., Sklar, E., Juillé, H., and Pollack, J. (1997). The inter-net as a virtual ecology: Coevolutionary arms races between human and artificial populations. Computer Science Technical Report CS-97-197, Brandeis University.
Funes, P., Sklar, E., Juillé, H., and Pollack, J. (1998). Animal-animat coevolution: Using the animal population as fitness function. In Proc. of SAB-5.
Hillis, W. D. (1992). Co-evolving parasites improve simulated evolution as an optimization procedure. In et al., L., editor, Proc. of ALIFE-2, pages 313–324. Addison Wesley.
Juillé, H. and Pollack, J. B. (1996). Dynamics of co-evolutionary learning. In Proc. of SAB-4, pages 526–534. MIT Press.
Koza, J. (1992). Genetic Programming: On the Programming of Computers by Means of Natural Selection. MIT Press, Cambridge, MA.
Pollack, J. B. and Blair, A. D. (1998). Co-evolution in the successful learning of backgammon strategy. Machine Learning (to appear).
Sims, K. (1995). Evolving 3d morphology and behavior by competition. In Proc. of ALIFE-4. MIT Press.
Tesauro, G. (1995). Temporal difference learning and td-gammon. Commun. of the ACM 39(3).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Blair, A.D., Sklar, E., Funes, P. (1999). Co-evolution, Determinism and Robustness. In: McKay, B., Yao, X., Newton, C.S., Kim, JH., Furuhashi, T. (eds) Simulated Evolution and Learning. SEAL 1998. Lecture Notes in Computer Science(), vol 1585. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48873-1_50
Download citation
DOI: https://doi.org/10.1007/3-540-48873-1_50
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65907-5
Online ISBN: 978-3-540-48873-6
eBook Packages: Springer Book Archive