Abstract
In this paper we describe and analyze the use of the Cartesian Genetic Programming method to evolve Artificial Neural Networks (CGPANN) in an open-ended evolution scenario. The issue of open-ended evolution has for some time been considered one of the open problems in the field of Artificial Life. In this paper we analyze the capabilities of CGPANN to evolve behaviors in a scenario without artificial selection, more specifically, without the use of explicit fitness functions. We use the BitBang framework and one of its example scenarios as a proof of concept. The results obtained in these first experiments show that it is indeed possible to evolve CGPANN brains, in an open-ended environment, without any explicit fitness function. We also present an analysis of different parameter configurations for the CGPANN when used in this type of scenario.
This is a preview of subscription content, log in via an institution to check access.
References
Banzhaf, W., Baumgaertner, B., Beslon, G., Doursat, R., Foster, J.A., McMullin, B., de Melo, V.V., Miconi, T., Spector, L., Stepney, S., White, R.: Defining and simulating open-ended novelty: requirements, guidelines, and challenges. Theory Biosci. 135(3), 1–31 (2016)
Baptista, T.: Complexity and emergence in societies of agents. Ph.D. thesis, University of Coimbra, Coimbra, July 2012
Baptista, T., Menezes, T., Costa, E.: Bitbang: a model and framework for complexity research. In: Proceedings of the European Conference on Complex Systems 2006, Oxford, UK, p. 73, September 2006
Bedau, M.A., McCaskill, J.S., Packard, N.H., Rasmussen, S., Adami, C., Green, D.G., Ikegami, T., Kaneko, K., Ray, T.S.: Open problems in artificial life. Artif. Life 6(4), 363–376 (2000)
Channon, A.: Three evolvability requirements for open-ended evolution. In: Maley, C.C., Boudreau, E. (eds.) Artificial Life VII Workshop Proceedings, Portland, USA, pp. 39–40 (2000)
Channon, A.: Unbounded evolutionary dynamics in a system of agents that actively process and transform their environment. Genet. Program. Evolvable Mach. 7(3), 253–281 (2006)
Floreano, D., Durr, P., Mattiussi, C.: Neuroevolution: from architectures to learning. Evol. Intell. 1, 47–62 (2008)
Khan, M.M., Khan, G.M., Miller, J.F.: Evolution of neural networks using Cartesian genetic programming. In: IEEE Congress on Evolutionary Computation, pp. 1–8, July 2010
McCulloch, W., Pitts, W.: A logical calculus of ideas immanent in nervous activity. Bull. Math. Biophys. 5(3), 115–133 (1943)
Miller, J.F. (ed.): Cartesian Genetic Programming. Natural Computing Series, 1st edn. Springer, Heidelberg (2011)
Miller, J.F., Thomson, P.: Cartesian Genetic Programming. Genet. Program. 10802(3), 121–132 (2000)
Standish, R.K.: Open-ended artificial evolution. Int. J. Comput. Intell. Appl. 3(2), 167–175 (2003)
Stanley, K.O.: Efficient evolution of neural networks through complexification. Ph.D. thesis, The University of Texas at Austin, November 2004
Stanley, K.O., Miikkulainen, R.: Efficient reinforcement learning through evolving neural network topologies. In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2002), San Francisco, US, p. 9 (2002)
Taylor, T., Bedau, M.A., Channon, A., Ackley, D., Banzhaf, W., Beslon, G., Dolson, E., Froese, T., Hickinbotham, S., Ikegami, T., McMullin, B., Packard, N., Rasmussen, S., Virgo, N., Agmon, E., Clark, E., McGregor, S., Ofria, C., Ropella, G., Spector, L., Stanley, K.O., Stanton, A., Timperley, C., Vostinar, A., Wiser, M.: Open-ended evolution: perspectives from the OEE workshop in York. Artif. Life 22(3), 408–423 (2016)
Turner, A.: Evolving artificial neural networks using Cartesian genetic programming. Ph.D. thesis, University of York, York, September 2015
Turner, A., Miller, J.F.: Cartesian genetic programming: why no bloat? In: 2013 Proceedings of the Thirty-third SGAI International Conference on Artificial Intelligence, pp. 193–204 (2014)
Turner, A., Miller, J.F.: Introducing a cross platform open source Cartesian genetic programming library. Genet. Program. Evolvable Mach. 16, 83–91 (2015)
Turner, A.J., Miller, J.F.: Cartesian genetic programming encoded artificial neural networks: a comparison using three benchmarks. In: Proceedings of the 15th Annual Conference on Genetic and Evolutionary Computation, GECCO 2013, NY, USA, pp. 1005–1012 (2013). http://doi.acm.org/10.1145/2463372.2463484
Vassilev, V.K., Fogarty, T.C., Miller, J.F.: Smoothness, ruggedness and neutrality of fitness landscapes: from theory to application. In: Ghosh, A., Tsutsui, S. (eds.) Advances in Evolutionary Computing. Natural Computing Series, pp. 3–44. Springer, Berlin (2003). doi:10.1007/978-3-642-18965-4_1
Vassilev, V.K., Miller, J.F.: The advantages of landscape neutrality in digital circuit evolution. In: Miller, J., Thompson, A., Thomson, P., Fogarty, T.C. (eds.) ICES 2000. LNCS, vol. 1801, pp. 252–263. Springer, Heidelberg (2000). doi:10.1007/3-540-46406-9_25
Yao, X.: Evolving artificial neural networks. In: Proceedings of the IEEE, pp. 1423–1447, February 1999
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Simões, A., Baptista, T., Costa, E. (2017). Cartesian Genetic Programming in an Open-Ended Evolution Environment. In: Oliveira, E., Gama, J., Vale, Z., Lopes Cardoso, H. (eds) Progress in Artificial Intelligence. EPIA 2017. Lecture Notes in Computer Science(), vol 10423. Springer, Cham. https://doi.org/10.1007/978-3-319-65340-2_34
Download citation
DOI: https://doi.org/10.1007/978-3-319-65340-2_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-65339-6
Online ISBN: 978-3-319-65340-2
eBook Packages: Computer ScienceComputer Science (R0)