Abstract
In this paper we present application of genetic programming (GP) [1] to evolution of indirect encoding of neural network weights. We compare usage of original HyperNEAT algorithm with our implementation, in which we replaced the underlying NEAT with genetic programming. The algorithm was named HyperGP. The evolved neural networks were used as controllers of autonomous mobile agents (robots) in simulation. The agents were trained to drive with maximum average speed. This forces them to learn how to drive on roads and avoid collisions. The genetic programming lacking the NEAT complexification property shows better exploration ability and tends to generate more complex solutions in fewer generations. On the other hand, the basic genetic programming generates quite complex functions for weights generation. Both approaches generate neural controllers with similar abilities.
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
Koza, J.R.: Genetic Programming: On the Programming of Computers by Means of Natural Selection. The MIT Press, Cambridge (1992)
D’Ambrosio, D.B., Stanley, K.O.: A novel generative encoding for exploiting neural network sensor and output geometry. In: GECCO 2007: Proceedings of the 9th annual conference on Genetic and evolutionary computation, pp. 974–981. ACM, New York (2007)
Gauci, J., Stanley, K.: Generating large-scale neural networks through discovering geometric regularities. In: GECCO 2007: Proceedings of the 9th annual conference on Genetic and evolutionary computation, pp. 997–1004. ACM, New York (2007)
Drchal, J., Koutník, J., Šnorek, M.: Hyperneat controlled robots learn to drive on roads in simulated environment. In: Submitted to IEEE Congress on Evolutionary Computation (CEC 2009) (2009)
Mattiussi, C.: Evolutionary synthesis of analog networks. Ph.D thesis, EPFL, Lausanne (2005)
Dürr, P., Mattiussi, C., Floreano, D.: Neuroevolution with Analog Genetic Encoding. In: Parallel Problem Solving from Nature - PPSN iX, vol. 9, pp. 671–680. Springer, Heidelberg (2006)
Dürr, P., Mattiussi, C., Soltoggio, A., Floreano, D.: Evolvability of Neuromodulated Learning for Robots. In: The 2008 ECSIS Symposium on Learning and Adaptive Behavior in Robotic Systems, pp. 41–46. IEEE Computer Society, Los Alamitos (2008)
Buk, Z., Šnorek, M.: Hybrid evolution of heterogeneous neural networks. In: Kůrková, V., Neruda, R., Koutník, J. (eds.) ICANN 2008, Part I. LNCS, vol. 5163, pp. 426–434. Springer, Heidelberg (2008)
Angeline, P.J., Saunders, G.M., Pollack, J.B.: An evolutionary algorithm that constructs recurrent neural networks. IEEE Transactions on Neural Networks 5, 54–65 (1993)
Schmidhuber, J., Wierstra, D., Gagliolo, M., Gomez, F.: Training recurrent networks by evolino. Neural computation 19(3), 757–779 (2007)
Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evolutionary Computation 10, 99–127 (2002)
D’Ambrosio, D.B., Stanley, K.O.: Generative encoding for multiagent learning. In: GECCO 2008: Proceedings of the 10th annual conference on Genetic and evolutionary computation, pp. 819–826. ACM, New York (2008)
Waibel, M.: Evolution of Cooperation in Artificial Ants. Ph.D thesis, EPFL (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Buk, Z., Koutník, J., Šnorek, M. (2009). NEAT in HyperNEAT Substituted with Genetic Programming. In: Kolehmainen, M., Toivanen, P., Beliczynski, B. (eds) Adaptive and Natural Computing Algorithms. ICANNGA 2009. Lecture Notes in Computer Science, vol 5495. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-04921-7_25
Download citation
DOI: https://doi.org/10.1007/978-3-642-04921-7_25
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-04920-0
Online ISBN: 978-3-642-04921-7
eBook Packages: Computer ScienceComputer Science (R0)