Neural Processing Letters

, Volume 42, Issue 2, pp 257–274 | Cite as

Adaptive Agents in Changing Environments, the Role of Modularity

  • Raffaele Calabretta
  • Juan Neirotti


We explored the role of modularity as a means to improve evolvability in populations of adaptive agents. We performed two sets of artificial life experiments. In the first, the adaptive agents were neural networks controlling the behavior of simulated garbage collecting robots, where modularity referred to the networks architectural organization and evolvability to the capacity of the population to adapt to environmental changes measured by the agents performance. In the second, the agents were programs that control the changes in network’s synaptic weights (learning algorithms), the modules were emerged clusters of symbols with a well defined function and evolvability was measured through the level of symbol diversity across programs. We found that the presence of modularity (either imposed by construction or as an emergent property in a favorable environment) is strongly correlated to the presence of very fit agents adapting effectively to environmental changes. In the case of learning algorithms we also observed that character diversity and modularity are also strongly correlated quantities.


Evolvability Emergence of modularity Artificial life simulations Evolutionary robotics 



The financial support of the Italian National Research Council (Short-Term Mobility Program at Yale University to RC) is gratefully acknowledged. The authors thank the referees for valuable suggestions on the manuscript. RC would also like to thank Gunter Wagner, Stefano Nolfi and Freek Duynstee for their contribution to the early stages of this work.


  1. 1.
    Wagner GP, Altenberg L (1996) Complex adaptations and the evolution of evolvability. Evolution 50:967–976CrossRefzbMATHGoogle Scholar
  2. 2.
    Kirschner M, Gerhart J (1998) Evolvability. Proc Natl Acad Sci USA 95:8420–8427CrossRefGoogle Scholar
  3. 3.
    Calabretta R, Di Ferdinando A, Wagner GP, Parisi D (2003) What does it take to evolve behaviorally complex organisms? BioSyst 69:245–262CrossRefGoogle Scholar
  4. 4.
    Calabretta R (2007) Genetic interference reduces the evolvability of modular and non-modular visual neural networks. Philos Trans R Soc B 362:403–410CrossRefGoogle Scholar
  5. 5.
    Calabretta R, Nolfi S, Parisi D, Wagner GP (1997) An artificial life model for investigating the evolution of modularity. In: Bar-Yam Y (ed) Proceedings of the International Conference on Complex Systems. Addison-Wesley, BostonGoogle Scholar
  6. 6.
    Calabretta R, Nolfi S, Parisi D, Wagner GP (2000) Duplication of modules facilitates the evolution of functional specialization. Artificial Life 6:69–84CrossRefGoogle Scholar
  7. 7.
    Di Ferdinando A, Calabretta R, Parisi D (2000) Evolving modular architectures for neural networks. In: R. French and J. Sougné (eds) Procs. of the sixth Neural computation and Psychology Workshop, pp 253–262Google Scholar
  8. 8.
    Neirotti J, Caticha N (2003) Dynamics of the evolution of learning algorithms by selection. Phys Rev E 67:041912MathSciNetCrossRefGoogle Scholar
  9. 9.
    Rumelhart D, McClelland J (1986) Parallel distributed processing: explorations in the microstructure of cognition. MIT Press, CambridgeGoogle Scholar
  10. 10.
    Kashtan N, Alon U (2005) Spontaneous evolution of modularity and network motifs. Proc Nac Acad Sci USA 102:13773CrossRefGoogle Scholar
  11. 11.
    Sun J, Deem MW (2007) Spontaneous emergence of modularity in a model of evolving individuals. Phys Rev Lett 99:228107CrossRefGoogle Scholar
  12. 12.
    Nolfi S (1997) Using emergent modularity to develop control systems for mobile robots. Adapt Behav 5:343–363CrossRefGoogle Scholar
  13. 13.
    Hornby GS, (2005) Measuring, enabling and comparing modularity, regularity and hierarchy in evolutionary design. Proceedings of the 2005 conference on Genetic and evolutionary computation, pp. 1729–1736. Washington, DC, USAGoogle Scholar
  14. 14.
    Miglino O, Lund HH, Nolfi S (1995) Evolving mobile robots in simulated and real environments. Artificial Life 4:417–434CrossRefGoogle Scholar
  15. 15.
    Holland JH (1992) Adaptations in natural and artificial systems: an introductory analysis with applications to biology, control and artificial intelligence. University of Michigan Press, Ann ArborGoogle Scholar
  16. 16.
    Koza J (1992) Genetic programming: on the programming of computers by means of natural selection. MIT Press, CambridgeGoogle Scholar
  17. 17.
    Neirotti JP (2010) Can a student learn optimally from two different teachers? J Phys A 43:015101MathSciNetCrossRefGoogle Scholar
  18. 18.
    Caticha N, Kinouchi Osame (1998) Time ordering in the evolution of information processing and modulation systems. Philos Mag 77:1565CrossRefGoogle Scholar
  19. 19.
    Neirotti JP, Franco L (2010) Computational capabilities of multilayer committee machines. J Phys A 43:445103MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2014

Authors and Affiliations

  1. 1.Laboratory of Autonomous Robotics and Artificial Life, Institute of Cognitive Sciences and TechnologiesItalian National Research Council (CNR)RomeItaly
  2. 2.NCRGAston UniversityBirminghamUK

Personalised recommendations