How the “Baldwin Effect” Can Guide Evolution in Dynamic Environments

  • Nam LeEmail author
  • Anthony Brabazon
  • Michael O’Neill
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11324)


Evolution and learning are two different ways in which the organism can adapt their behaviour to cope with problems posed by the environment. The second type of adaptation occurs when individuals exhibit plasticity in response to environmental conditions that may strengthen their survival. Individuals seek a behaviour that increases fitness. Therefore, it is plausible and rational for the individual to have some learning capabilities to prepare for the uncertain future, some sort of prediction or plastic abilities in different environments. Learning has been shown to benefit the evolutionary process through the Baldwin Effect, enhancing the adaptivity of the evolving population. In nature, when the environment changes too quickly that the slower evolutionary process cannot equip enough information for the population to survive, having the ability to learn during the lifetime is necessary to keep pace with the changing environment. This paper investigates the effect of learning on evolution in evolutionary optimisation. An instance of dynamic optimisation problems is proposed to test the theory. Experimental results show that learning has a significant impact on guiding evolutionary search in the dynamic landscapes. Indications for future work on dynamic optimisation are also presented.


Baldwin effect Dynamic environments Phenotypic plasticity 



This research is funded by the Science Foundation Ireland under Grant No. 13/IA/1850.


  1. 1.
    Ackley, D., Littman, M.: Interactions between learning and evolution. In: Langton, C.G., Taylor, C., Farmer, C.D., Rasmussen, S. (eds.) Artificial Life II, SFI Studies in the Sciences of Complexity, vol. X, pp. 487–509. Addison-Wesley, Reading (1992)Google Scholar
  2. 2.
    Baldwin, J.M.: A new factor in evolution. Am. Nat. 30(354), 441–451 (1896)CrossRefGoogle Scholar
  3. 3.
    Brabazon, A., O’Neill, M., McGarraghy, S.: Natural Computing Algorithms, 1st edn. Springer, Heidelberg (2015)CrossRefGoogle Scholar
  4. 4.
    Branke, J.: Evolutionary Optimization in Dynamic Environments. Springer, US (2002)CrossRefGoogle Scholar
  5. 5.
    Bull, L.: On the baldwin effect. Artif. Life 5(3), 241–246 (1999). Scholar
  6. 6.
    Hinton, G.E., Nowlan, S.J.: How learning can guide evolution. Complex Syst. 1, 495–502 (1987)zbMATHGoogle Scholar
  7. 7.
    Kauffman, S.A., Weinberger, E.D.: The NK model of rugged fitness landscapes and its application to maturation of the immune response. J. Theor. Biol. 141(2), 211–245 (1989). Scholar
  8. 8.
    Le, N.: Adaptive advantage of learning strategies: A study through dynamic landscape. In: Parallel Problem Solving from Nature – PPSN XV. Springer International Publishing (forthcoming)Google Scholar
  9. 9.
    Le, N.: The baldwin effect reconsidered through the prism of social learning. In: IEEE Congress on Evolutionary Computation, CEC 2018. IEEE Press (8–13 July forthcoming)Google Scholar
  10. 10.
    Mayley, G.: Guiding or hiding: explorations into the effects of learning on the rate of evolution. In: In Proceedings of the Fourth European Conference on Artificial Life, pp. 135–144. MIT Press (1997)Google Scholar
  11. 11.
    Nolfi, S., Parisi, D., Elman, J.L.: Learning and evolution in neural networks. Adapt. Behav. 3(1), 5–28 (1994)CrossRefGoogle Scholar
  12. 12.
    Waddington, C.H.: Canalization of development and the inheritance of acquired characters. Nature 150(3811), 563–565 (1942)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Natural Computing Research and ApplicationsUniversity College DublinDublinIreland

Personalised recommendations