Abstract
This paper presents a kernel-based online neuroevolutionary of augmenting topology (KO-NEAT) algorithm, which borrowing the selection mechanisms used in temporal difference (TD) algorithms and combining the kernel function approximator for individual fitness initiation. KO-NEAT can improve evolution’s online performance of NEAT and learns more quickly. Empirical results in keepaway soccer problem demonstrate that KO-NEAT can substantially improve the original algorithm.
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
Stone, P., Kuhlmann, G., Taylor, M.E., Liu, Y.: Keepaway Soccer: From Machine Learning Testbed to Benchmark. In: Bredenfeld, A., Jacoff, A., Noda, I., Takahashi, Y. (eds.) RoboCup 2005. LNCS (LNAI), vol. 4020, pp. 93–105. Springer, Heidelberg (2006)
Stanley, K.O., Miikkulainen, R.: Evolving Neural Networks through Augmenting Topolo- gies. Evolutionary Computation 10(2), 99–127 (2002)
Stanley, K.O., Miikkulainen, R.: Evolving a Roving Eye for Go. In: Proceeding of the genetic and evolutionary computation conference, pp. 1226–1238 (2004)
Stanley, K.O.: Competitive Coevolution through Complexification. Journal of artificial intelligence research 21, 63–100 (2004)
Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: a survey. Journal of artificial intelligence research, 237–285 (1996)
Tayor, M.E., Whiteson, S., Stone, P.: Comparing Evolutionary and Temporal Difference Methods in a Reinforcement Learning Domain. In: Proceeding of the genetic and evolutionary computation conference GECOO-2006, Seattle, Washington, USA, pp. 1321–1328 (2006)
Whiteson, S., Stone, P.: On-line Evolutionary Computation for Reinforcement Learning in Stochastic Domains. In: Proceeding of the genetic and evolutionary computation conference, pp. 1577–1584 (2006)
Sutton, R.S.: Learning to Predict by the Methods of Temporal Differences. Machine Learning, pp. 9–44. Kluwer Academic Publishers, Boston (1988)
Stone, P.: Layered Learning in Multiagent Systems: A Winning Approach to Robotic Soccer. MIT Press, Cambridge (2000)
Tong, L., Lu, J.: Overview of Robotsoccer Learning Methods. Computer Simulation 21(6), 1–5 (2004)
Zhang, R., Gu, G., Liu, Z., Wang, X.: Reinforcement Learning Theory, Algorithms and Its Application. Control Theory and Application 17(5), 637–642 (2000)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhao, Y., Cai, H., Chen, Q., Hu, W. (2007). Kernel-Based Online NEAT for Keepaway Soccer. In: Li, K., Fei, M., Irwin, G.W., Ma, S. (eds) Bio-Inspired Computational Intelligence and Applications. LSMS 2007. Lecture Notes in Computer Science, vol 4688. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74769-7_12
Download citation
DOI: https://doi.org/10.1007/978-3-540-74769-7_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74768-0
Online ISBN: 978-3-540-74769-7
eBook Packages: Computer ScienceComputer Science (R0)