Enhancing Exploration and Exploitation of NSGA-II with GP and PDL

  • Peter David Shannon
  • Chrystopher L. Nehaniv
  • Somnuk Phon-Amnuaisuk
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10385)

Abstract

In this paper, we show that NSGA-II can be applied to GP and the Process Description Language (PDL) and describe two modifications to NSGA-II. The first modification removes individuals which have the same behaviour from GP populations. It selects for de-duplication by taking the result of each objective fitness function together to make a comparison. NSGA-II is designed to expand its Pareto front of solutions by favouring individuals who have the highest or lowest value (boundary points) in a front, for any objective. The second modification enhances exploitation by preferring individuals who occupy an extreme position for most objective fitness functions. The results show, for the first time, that NSGA-II can be used with PDL and GP to successfully solve a robot control problem and that the suggested modifications offer significant improvements over an algorithm used previously with GP and PDL and unmodified NSGA-II for our test problem.

Keywords

Genetic programming Process description language Exploration and exploitation NSGA-II 

References

  1. 1.
    Shannon, P., Nehaniv, C.L.: Evolving robot controllers in PDL using genetic programming. In: IEEE SSCI 2011-Symposium Series on Computational Intelligence-IEEE ALIFE 2011: 2011 IEEE Symposium on Artificial Life, pp. 92–99. IEEE, Paris (2011)Google Scholar
  2. 2.
    Koza, J.R.: A genetic approach to finding a controller to back up a tractor-trailer truck. In: American Control Conference, pp. 2307–2311. IEEE, Chicago (1992)Google Scholar
  3. 3.
    Nehaniv, C., Dautenhahn, K.: Embodiment and memories-algebras of time and history for autobiographic agents. In: Trappl, R. (ed.) Cybernetics and Systems, vol. 2, pp. 651–656. Austrian Society for Cybernetic Studies, Vienna, Austria (1998)Google Scholar
  4. 4.
    Nehaniv, C.L., Dautenhahn, K.: Semigroup expansions for autobiographic agents. In: First Symposium on Algebra, Languages and Computation, pp. 77–84. University of Aizu, Japan (1998)Google Scholar
  5. 5.
    Mauldin, M.L.: Maintaining diversity in genetic search. In: AAAI, pp. 247–250 (1984)Google Scholar
  6. 6.
    Shimodaira, H.: DCGA: a diversity control oriented genetic algorithm. In: Proceedings of the Ninth IEEE International Conference on Tools with Artificial Intelligence 1997, pp. 367–374. IEEE (1997)Google Scholar
  7. 7.
    Sangkawelert, N., Chaiyaratana, N.: Diversity control in a multi-objective genetic algorithm. In: The 2003 Congress on Evolutionary Computation, CEC 2003, vol. 4, pp. 2704–2711. IEEE (2003)Google Scholar
  8. 8.
    Steels, L.: Mathematical analysis of behavior systems. In: Proceedings From Perception to Action Conference 1994, pp. 88–95. IEEE (1994)Google Scholar
  9. 9.
    Fortin, F.A., Rainville, F.M.D., Gardner, M.A., Parizeau, M., Gagné, C.: DEAP: evolutionary algorithms made easy. J. Mach. Learn. Res. 13, 2171–2175 (2012)MathSciNetMATHGoogle Scholar
  10. 10.
    Nelson, A.L., Barlow, G.J., Doitsidis, L.: Fitness functions in evolutionary robotics: a survey and analysis. Robot. Auton. Syst. 57(4), 345–370 (2009). ElsevierCrossRefGoogle Scholar
  11. 11.
    Olson-Manning, C.F., Wagner, M.R., Mitchell-Olds, T.: Adaptive evolution: evaluating empirical support for theoretical predictions. Nature Rev. Genet. 13(12), 867–877 (2012). Nature Publishing GroupCrossRefGoogle Scholar
  12. 12.
    Deb, K., Pratap, A., Agarwal, S., Meyarivan, T.A.M.T.: A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evol. Comput. 6(2), 182–197 (2002). IEEECrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Peter David Shannon
    • 1
    • 2
  • Chrystopher L. Nehaniv
    • 2
  • Somnuk Phon-Amnuaisuk
    • 1
  1. 1.School of Computing and InformaticsUniversiti of Teknologi BruneiBandar Seri BegawanBrunei
  2. 2.School of Computer ScienceUniversity of HertfordshireHatfieldUK

Personalised recommendations