Abstract
We propose a new neuroevolution technique that makes use of genetic algorithm to improve the task provided to a Radial Basis Function – NEAT algorithm. Normally, Radial Basis Function works best when the input- output mapping is smooth, that is, the dimensionality is high. However, if the input changes abruptly, for example, for fractured problems, efficient mapping cannot happen. Thus, the algorithm cannot solve such problems effectively. We make use of genetic algorithm to emulate the smoothing parameter in the Radial Basis function. In the proposed algorithm, the input- output mapping is done in a more efficient manner due to the ability of genetic algorithm to approximate almost any function. The technique has been successfully applied in the non- Markovian double pole balancing without velocity and the car racing strategy. It is shown that the proposed technique significantly outperforms classical neuroevolution techniques in both of the above benchmark problems.
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
Karpov, I., Sheblak, J., Miikkulainen, R.: OpenNERo; A game platform for AI research and education. In: Proceeding of the Fourth Artificial Intelligence and Interactive Digital Entertainment Conference (2008)
Shettleworth, S.J.: Evolution and Learning-The Baldwin effect reconsidered. MIT Press, Cambridge (2003)
Kull, K.: Adaptive Evolution Without Natural Selection-Baldwin effect. Cybernetics and Human Knowing 7(1), 45–55 (2000)
Baeck, T.: Evolutionary Algorithms in Theory and Practice. Oxford University Press, New-York (1996)
Beyer, H.G.: The Theory of Evolution Strategies. Springer, Heidelberg (2001)
Yao, X., Liu, Y.: A new Evolutionary System for Evolving Artificial Neural Networks 8(3), 694–713 (1997)
Floreano, D., Urzelai, J.: Evolutionary Robots with Self-Organization and Behavioral Fitness. Neural Networks 13, 431–443 (2000)
Niv, Y., Noel, D., Ruppin, E.: Evolution of reinforcement learning in Uncertain Environments; A Simple Explanation for Complex Foraging Behaviors. Adaptive Behavior 10(1), 5–24 (2002)
Soltoggio, A., Bulliaria, J.A., Mattiussi, C., Durr, P., Floreano, D.: Evolutionary Advantages of Neuromodulated Plasticity in Dynamics, Reward based Scenario. In: Artificial Life XI, pp. 569–576. MIT Press, Cambridge (2008)
Stanley, K.O., Miikkulainen, R.: Evolving Neural Networks through Augmenting Topologies. Evolutionary Computation 10(2) (2002)
Potter, M.A., De Jong, K.A.: Evolving Neural Networks with Collaborative Species. In: Proceedings of the 1995 Summer Computing Simulation Conference (1995)
Radcliff, N.J.: Genetic Set Recombination and its application to Neural Network Topology Optimization. Neural Computing and Applications 1(1), 67–90 (1992)
Wieland, A.: Evolving Neural Networks Controllers for unstable systems. In: Proceedings of the International Joint Conference on Neural Networks, Seattle, WA. IEEE (1991)
Saravanan, N., Fogel, D.B.: Evolving Neural Control Systems. IEEE Expert, 23–27 (1995)
Reisinger, J., Bahceci, E., Karpov, I., Miikkulainen, R.: Coevolving Strategies for general game playing. In: Proceedings of the IEEE Symposium on Computational Intelligence and Games (2007)
Stanley, K.O., Bryant, B.D., Miikkulainen, R.: Real-Time Neuroevolution in the NERO video game. IEEE Transactions on Evolutionary Computation 9(6), 653–668 (2007)
Stanley, K.O., Miikkulainen, R.: Competitive Coevolution through Evolutionary Complexification. Journal of Artificial Intelligence Research, 63–100 (2004)
Stanley, K.O., Miikkulainen, R.: Evolving a roving eye for go. In: Proceeding of the Genetic and Evolutionary Computation Conference (2004)
Lucas, S.M., Togelius, J.: Point-to-pointcar racing; an Initial Study of Evolution Versus Temporal Difference Learning. In: IEEE Symposium of Computational Intelligence and Games, pp. 260–267 (2007)
Li, J., Martinez-Maron, T., Lilienthal, A., Duckett, T.: Q-ran; A Constructive Reinforcement Learning approach for Robot behavior Learning. In: Proceedings of IEEE/RSJ International Conference on Intelligent on Intelligent Robot and System (2006)
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)
Moody, J., Darken, C.J.: Fast Learning in Networks of Locally tuned Processing units. Neural Computation, 281–294 (1989)
Sutton, R.S., Barto, A.G.: Reinforcement Learning; An Introduction. MIT Press (1998)
Wieland, A.: Evolving Neural Network Controllers for Unstable Systems. In: Proceedings of the IJCNN, Seattle, WA, pp. 667–673. IEEE (1991)
Gruau, F., Whitley, D., Pyeatt, L.: A comparison between Cellular Encoding and Direct Encoding for Genetic Programming. In: Genetic Programming 1996: Proceedings of the First Annual Conference, pp. 81–89 (1996)
Gomez, F.J., Miikkulainen, R.: Solving Non-Markovian Control tasks with Neuroevolution. In: Proceedings of the IJCAI, pp. 1356–1361 (1999)
Dürr, P., Mattiussi, C., Floreano, D.: Neuroevolution with Analog Genetic Encoding. In: Runarsson, T.P., Beyer, H.-G., Burke, E.K., Merelo-Guervós, J.J., Whitley, L.D., Yao, X. (eds.) PPSN IX. LNCS, vol. 4193, pp. 671–680. Springer, Heidelberg (2006)
Jakobsen, M.: Learning to Race in a Simulated Environment, http://www.hiof.no.neted/upload/attachment/site/group12/Morgan_Jakobsen_Learning_to_race_in_a_simulated_environment.pdf (last accessed March 18, 2012)
Kietzmann, T.C., Reidmiller, M.: The Neuro Slot car Racer; Reinforcement Learning in a Real World Setting, http://ml.informatik.unifreiburg.de/_media/publications/kr09.pdf (last accessed March 12, 2013)
Kohl, N., Miikkulainen, R.: Evolving Neural Networks for Fractured Domains. Neural Networks 22(3), 326–337 (2009)
Togelius, J., Lucas, S.M.: IEEE CEC Car Racing Competition, http://Julian.togelius.com/cec2007competition/ (last accessed February10, 2012)
NEAT Matlab, http://www.cs.utexas.edu/users/ai-lab/?neatmatlab (last accessed March 02, 2012)
The Radial Basis Function Network, http://www.csc.kth.se/utildning/kth/kurser/DD2432/ann12/forelasningsanteckningar/RBF.pdf (last accessed: June 21, 2012)
Bajpai, P., Kumar, M.: Genetic Algorithm-an Approach to Solve Global Optimization Problems. Indian Journal of Computer Science and Engineering 1(3), 199–206 (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Mohabeer, H., Soyjaudah, K.M.S. (2014). A Hybrid Genetic Algorithm and Radial Basis Function NEAT. In: Golovko, V., Imada, A. (eds) Neural Networks and Artificial Intelligence. ICNNAI 2014. Communications in Computer and Information Science, vol 440. Springer, Cham. https://doi.org/10.1007/978-3-319-08201-1_15
Download citation
DOI: https://doi.org/10.1007/978-3-319-08201-1_15
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-08200-4
Online ISBN: 978-3-319-08201-1
eBook Packages: Computer ScienceComputer Science (R0)