HybrID: A Hybridization of Indirect and Direct Encodings for Evolutionary Computation

  • Jeff Clune
  • Benjamin E. Beckmann
  • Robert T. Pennock
  • Charles Ofria
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5778)


Evolutionary algorithms typically use direct encodings, where each element of the phenotype is specified independently in the genotype. Because direct encodings have difficulty evolving modular and symmetric phenotypes, some researchers use indirect encodings, wherein one genomic element can influence multiple parts of a phenotype. We have previously shown that HyperNEAT, an indirect encoding, outperforms FT-NEAT, a direct-encoding control, on many problems, especially as the regularity of the problem increases. However, HyperNEAT is no panacea; it had difficulty accounting for irregularities in problems. In this paper, we propose a new algorithm, a Hybridized Indirect and Direct encoding (HybrID), which discovers the regularity of a problem with an indirect encoding and accounts for irregularities via a direct encoding. In three different problem domains, HybrID outperforms HyperNEAT in most situations, with performance improvements as large as 40%. Our work suggests that hybridizing indirect and direct encodings can be an effective way to improve the performance of evolutionary algorithms.


Indirect (generative developmental) encodings (representations) artificial neural networks neuroevolution evolutionary algorithms 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Hornby, G.S., Lipson, H., Pollack, J.B.: Generative representations for the automated design of modular physical robots. IEEE Transactions on Robotics and Automation 19(4), 703–719 (2003)CrossRefGoogle Scholar
  2. 2.
    Stanley, K.O., Miikkulainen, R.: A taxonomy for artificial embryogeny. Artificial Life 9(2), 93–130 (2003)CrossRefGoogle Scholar
  3. 3.
    Clune, J., Beckmann, B.E., Ofria, C., Pennock, R.T.: Evolving coordinated quadruped gaits with the hyperneat generative encoding. In: IEEE Congress on Evolutionary Computing (CEC), Trondheim, Norway, pp. 2674–2771 (2009)Google Scholar
  4. 4.
    Clune, J., Ofria, C., Pennock, R.T.: How a generative encoding fares as problem-regularity decreases. In: Rudolph, G., Jansen, T., Lucas, S., Poloni, C., Beume, N. (eds.) PPSN 2008. LNCS, vol. 5199, pp. 358–367. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  5. 5.
    Gruau, F.: Automatic definition of modular neural networks. Adaptive Behavior 3, 151–183 (1994)CrossRefGoogle Scholar
  6. 6.
    Eiben, A.E., Hinterding, R., Michalewicz, Z.: Parameter control in evolutionary algorithms. IEEE Transactions on Evolutionary Computation 3(2), 124–141 (1999)CrossRefGoogle Scholar
  7. 7.
    Grimbleby, J.: Automatic analogue circuit synthesis using genetic algorithms. IEE Proceedings - Circuits, Devices and Systems 147(6), 319–323 (2000)CrossRefGoogle Scholar
  8. 8.
    Stanley, K.O., D’Ambrosio, D.B., Gauci, J.: A hypercube-based indirect encoding for evolving large-scale neural networks. Artificial Life 15(2) (2009)Google Scholar
  9. 9.
    Stanley, K.O.: Compositional pattern producing networks: A novel abstraction of development. Genetic Programming and Evolvable Machines 8(2), 131–162 (2007)CrossRefGoogle Scholar
  10. 10.
    Clune, J., Ofria, C., Pennock, R.T.: The sensitivity of hyperneat to different geometric representations of a problem. In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO), Montreal, Canada, pp. 675–682 (2009)Google Scholar
  11. 11.
    Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evolutionary Computation 10(2), 99–127 (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Jeff Clune
    • 1
  • Benjamin E. Beckmann
    • 1
  • Robert T. Pennock
    • 1
    • 2
  • Charles Ofria
    • 1
  1. 1.Department of Computer Science and EngineeringMichigan State UniversityEast LansingUSA
  2. 2.Department of Philosophy and Lyman Briggs CollegeMichigan State UniversityEast LansingUSA

Personalised recommendations