Advertisement

Learning as a Consequence of Selection

  • Samuel Delepoulle
  • Philippe Preux
  • Jean-Claude Darcheville
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2310)

Abstract

Since the end of the XIXth century, the influence of learning on natural selection has been considered. More recently, this influence has been investigated using computer simulations. However, it has not yet been shown how the ability of learning can be the product of natural selection. This point is precisely the subject of this paper.

Keywords

Natural Selection Reinforcement Learning Input Sensor Discrimination Task XIXth Century 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    D. Ackley and M. Littman. Interactions between learning and evolution. In Christopher Langton, Charles Taylor, J. Doyne Farmer, and Steen Rasmussen, editors, Artificial Life II, Santa Fe Institute Studies in the Sciences of Complexity, pages 487–509. Addison-Wesley Publishing Company, 1992.Google Scholar
  2. [2]
    J.M. Baldwin. A new factor in evolution. The american naturalist, 30, 1896.Google Scholar
  3. [3]
    A.G. Barto. Reinforcement learning and adaptive critic methods. In D.A. White and D.A. Sofge, editors, Handbook of intellkigent control: neural, fuzzy, and adaptive approach, pages 469–491. Van Nostrand Reinhold, 1992.Google Scholar
  4. [4]
    C. Catania. Thorndike’s legacy: learning, selection, and the law of effect. Journal of the experimental analysis of behavior, 72:425–428, 1999.CrossRefGoogle Scholar
  5. [5]
    P. Chance. Thorndike’s puzzle boxes and the origins of the experimental analysis of behavior. Journal of the Experimental Analysis of Behavior, 72(3):433–440, 1999.CrossRefGoogle Scholar
  6. [6]
    S. Delepoulle. Coopération entre agents adaptatifs; étude de la sélection des comportements sociaux, expérimentations et simulations. PhD thesis, Université de Lille 3, URECA, Villeneuve d’Ascq, October 2000. Thèse de doctorat de Psychologie.Google Scholar
  7. [7]
    S. Delepoulle, Ph. Preux, and J-Cl. Darcheville. Dynamique de l’interaction. In B. Chaib-Dra and P. Enjalbert, editors, Proc. Modèles Formels de l’Interaction, Toulouse, pages 141–150, 2001.Google Scholar
  8. [8]
    S. Delepoulle, Ph. Preux, and J-Cl. Darcheville. Selection of behavior in social situations—application to the development of coordinated movements. In Applications of Evolutionary Computing, volume 2037 of Lecture Notes in Computer Science, pages 384–393. Springer-Verlag, April 2001.CrossRefGoogle Scholar
  9. [9]
    G.E. Hinton and S.J. Nowlan. How learning can guide evolution. 1:495–502, 1987.zbMATHGoogle Scholar
  10. [10]
    J. Maynard-Smith. When learning guides evolution. Nature, 329:761–762, October 1987.Google Scholar
  11. [11]
    D. McFarland. Animal Behavior. Psychology, Ethology and Evolution. Longman Science and Technology, 1998.Google Scholar
  12. [12]
    C. Lloyd Morgan. On modification and variation. Science, 4:733–740, 1896.CrossRefGoogle Scholar
  13. [13]
    H.F. Osborn. Ontogenetic and phylogenetic variation. Science, 4:786–789, 1896.CrossRefGoogle Scholar
  14. [14]
    Ph. Preux, S. Delepoulle, and J-Cl. Darcheville. Selection of behaviors by their consequences in the human baby, software agents, and robots. In Proc. Computational Biology, Genome Information Systems and Technology, March 2001.Google Scholar
  15. [15]
    J.B. Sidowski, B. Wycko., and L. Tabory. The influence of reinforcement and punishment in a minimal social situation. Journal of Abnormal Social Psychology, 52:115–119, 1956.CrossRefGoogle Scholar
  16. [16]
    B.F. Skinner. The behavior of organisms. Appleton-Century Crofts, 1938.Google Scholar
  17. [17]
    B.F. Skinner. Science and human behavior. MacMillan, 1958.Google Scholar
  18. [18]
    B.F. Skinner. Selection by consequences. Science, 213:501–514, 1981.CrossRefGoogle Scholar
  19. [19]
    R.S. Sutton and A.G. Barto. Reinforcement learning: an introduction. MIT Press, 1998.Google Scholar
  20. [20]
    E.L. Thorndike. Animal intelligence: An experimental study of the associative process in animals. Psychology Monographs, 2, 1898.Google Scholar
  21. [21]
    E.L. Thorndike. Animal Intelligence: Experimental Studies. Mac Millan, 1911.Google Scholar
  22. [22]
    J. Urzelai. Evolutionary Adaptive Robots: artificial evolution of adaptation mechanisms for autonomous systems. PhD thesis, EPFL, Lausanne, Suisse, 2000.Google Scholar
  23. [23]
    C. Waddington. Genetic assimilation for acquired character. Evolution, 7:118–126, 1953.CrossRefGoogle Scholar
  24. [24]
    C. Waddington. Genetic assimilation of the bithorax phenotype. Evolution, 10:1–13, 1956.CrossRefGoogle Scholar

Copyright information

© Springer-VerlagBerlin Heidelberg 2002

Authors and Affiliations

  • Samuel Delepoulle
    • 1
    • 2
  • Philippe Preux
    • 2
  • Jean-Claude Darcheville
    • 1
  1. 1.Unité de Recherche sur l’Évolution des Comportements et des Apprentissages (URECA)Université de Lille 3Villeneuve d’Ascq CedexFrance
  2. 2.Laboratoire d’Informatique du Littoral (LIL)Université du Littoral Côte d’OpaleCalais CedexFrance

Personalised recommendations