Advertisement

Autonomous Robots

, Volume 7, Issue 1, pp 89–113 | Cite as

Learning and Evolution

  • Stefano Nolfi
  • Dario Floreano
Article

Abstract

In the last few years several researchers have resorted to artificial evolution (e.g., genetic algorithms) and learning techniques (e.g., neural networks) for studying the interaction between learning and evolution. These studies have been conducted for two different purposes: (a) looking at the performance advantages obtained by combining these two adaptive techniques; (b) understanding the role of the interaction between learning and evolution in biological organisms. In this paper we describe some of the most representative experiments conducted in this area and point out their implications for both perspectives outlined above. Understanding the interaction between learning and evolution is probably one of the best examples in which computational studies have shed light on problems that are difficult to study with the research tools employed by evolutionary biology and biology in general. From an engineering point of view, the most relevant results are those showing that adaptation in dynamic environments gains a significant advantage by the combination of evolution and learning. These studies also show that the interaction between learning and evolution deeply alters the evolutionary and the learning process themselves, offering new perspectives from a biological point of view. The study of learning within an evolutionary perspective is still in its infancy and in the forthcoming years it will produce an enormous impact on our understanding of how learning and evolution operate.

learning evolution plastic individuals Baldwin Effect 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Ackley, D.E. and Littman, M.L. 1991. Interaction between learning and evolution. In Proceedings of the Second Conference on Artificial Life, C.G. Langton et al. (Eds.), Addison-Wesley: Reading, MA.Google Scholar
  2. Ackley, D.E. and Littman, M.L. 1994. A case for lamarkian evolution. In Proceedings of Artificial Life III, SFI Studies in the Sciences of Complexity, C.G. Langton (Ed.), Addison-Wesley.Google Scholar
  3. Baldwin, J.M. 1896. A new factor in evolution. American Naturalist, 30:441-451.Google Scholar
  4. Belew, R.K., McInerney, J., and Schraudolph, N.N. 1991. Evolving networks: Using the genetic algorithm with connectionistic learning. In Proceedings of the Second Conference on Artificial Life, C.G. Langton et al. (Eds.), Addison-Wesley: Reading, MA.Google Scholar
  5. Cecconi, F., Menczer F., and Belew, R.K. 1996. Maturation and the evolution of imitative learning in artificial organisms. Adaptive Behavior, 4:29-50.Google Scholar
  6. Cliff, D. and Miller, G.F. 1996. Co-evolution of pursuit and evasion II: Simulation methods and results. In From Animals to Animats IV: Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior, P. Maes, M. Mataric, J.-A. Meyer, J. Pollack, H. Roitblat, and S. Wilson (Eds.), MIT Press-Bradford Books: Cambridge, MA.Google Scholar
  7. Floreano, D. and Mondada, F. 1996. Evolution of plastic neurocontrollers for situated agents. In From Animals to Animats IV. P. Maes, M. Mataric, J.-A. Meyer, J. Pollack, and S. Wilson (Eds.), MIT Press: Cambridge, MA.Google Scholar
  8. Floreano, D. and Nolfi, S. 1997a. God save the red queen! Competition in co-evolutionary robotics. In Genetic Programming 1997: Proceedings of the Second Annual Conference, J.R. Koza, D. Kalyanmoy, M. Dorigo, D.B. Fogel, M. Garzon, H. Iba, and R.L. Riolo (Eds.), Morgan Kaufmann: San Francisco, CA, pp. 398-406.Google Scholar
  9. Floreano, D. and Nolfi, S. 1997b. Adaptive behavior in competing co-evolving species. In Proceedings of the Fourth European Conference on Artificial Life, P. Husband and I. Harvey (Eds.), MIT Press: Cambridge, MA, pp. 378-387.Google Scholar
  10. Flotzinger, D. 1996. Evolving plastic neural controllers for autonomous robots. M.Sc. Dissertation 95800131, COGS, University of Sussex at Brighton.Google Scholar
  11. Harvey, I. 1996. Relearning and evolution in neural networks. Adaptive Behavior, 4(1):81-84.Google Scholar
  12. Harvey, I. 1997. Is there another new factor in evolution? Evolutionary Computation, 4(3):313-329.Google Scholar
  13. Harvey, I. and Stone, J.V. 1996. Unicycling helps your French: Spontaneous recovery of associations by learning unrelated tasks. Neural Computation, 8:697-704.Google Scholar
  14. Hertz, J., Krogh, A., and Palmer, R.G. 1991. Introduction to the Theory of Neural Computation, Addison-Wesley: Redwood City, CA.Google Scholar
  15. Hinton, G.E. and Nowlan, S.J. 1987. How learning guides evolution. Complex System, 1:495-502.Google Scholar
  16. Kolen, J.F. and Pollack, J.B. 1990. Back-propagation is sensitive to the initial conditions. Complex Systems, 4:269-280.Google Scholar
  17. de Lamarck, J.B.P.A. 1990. Zoological Philosophy. London: MacMillan, 1914. Relevant excerpts reprinted. In Adaptive Individuals in Evolving Populations, R.K. Belew and M. Mitchell (Eds.), SFI Studies in the Science of Complexity, Vol. XXVI, Addison-Wesley: Reading, MA.Google Scholar
  18. Mayley, G. 1997. Landscapes, learning costs, and genetic assimilation. Evolutionary Computation, 4(3):213-234.Google Scholar
  19. Miller, G.F., Todd, P.M., and Hedge, S.U. 1989. Designing neural networks using genetic algorithms. In Proceedings Third International Conference on Genetic Algorithms, L. Nadel and D. Stein (Eds.), Morgan Kaufmann: San Mateo, CA, pp. 379-384.Google Scholar
  20. Mondada, R., Franzi, E., and Ienne, P. 1993. Mobile robot miniaturization: A tool for investigation in control algorithms. In Proceedings of the Third International Symposium on Experimental Robots, T.Y. Yoshikawa and F. Miyazaki (Eds.), Springer-Verlag: Berlin.Google Scholar
  21. Nolfi, S. 1998. How learning and evolution interact: The case of a learning task which differs from the evolutionary task. Technical Report, Institute of Psychology, C.N.R., Rome.Google Scholar
  22. Nolfi, S., Elman, J.L., and Parisi, D. 1990. Learning and evolution in neural networks, Technical Report CRL-9019, University of California, San Diego.Google Scholar
  23. Nolfi, S., Elman, J.L., and Parisi, D. 1994a. Learning and evolution in neural networks. Adaptive Behavior, 3(1):5-28.Google Scholar
  24. Nolfi, S. and Floreano, D. 1999. Co-evolving predator and prey robots: Do ‘arm races’ arise in artificial evolution? Artificial Life, 4(4):311-335.Google Scholar
  25. Nolfi, S., Miglino, O., and Parisi, D. 1994b. Phenotypic plasticity in evolving neural networks. In Proceedings of the International Conference From Perception to Action, D.P. Gaussier and J.-D. Nicoud (Eds.), IEEE Press: Los Alamitos, CA.Google Scholar
  26. Nolfi, S. and Parisi, D. 1993. Auto-teaching: Networks that develop their own teaching input. In Proceedings of the Second European Conference on Artificial Life, J.L. Deneubourg, H. Bersini, S. Goss, G. Nicolis, and R. Dagonnier (Eds.), Brussels, pp. 845-862.Google Scholar
  27. Nolfi, S. and Parisi, D. 1994. Desired responses do not correspond to good teaching input in ecological neural networks. Neural Processing Letters, 1(2):1-4.Google Scholar
  28. Nolfi, S. and Parisi, D. 1997. Learning to adapt to changing environments in evolving neural networks. Adaptive Behavior, 1:99-105.Google Scholar
  29. Nolfi, S. and Tani, J. 1999. Extracting regularities in space and time through a cascade of prediction networks: The case of a mobile robot navigating in a structured environment. Connection Science, 11(2):129-152.Google Scholar
  30. Osborn, H.F. 1896. Ontogenetic and phylogenetic variation. Science, 4:786-789.Google Scholar
  31. Parisi, D. and Nolfi, S. 1996. How learning can influence evolution within a non-Lamarckian framework. In Adaptive Individuals in Evolving Populations, R.K. Belew and M. Mitchell (Eds.), SFI Studies in the Science of Complexity, Vol. XXVI, Addison-Wesley: Reading, MA.Google Scholar
  32. Parisi, D., Nolfi, S., and Cecconi, F. 1992. Learning, behavior and evolution. In Toward a Practice of Autonomous Systems, F. Varela and P. Bourgine (Eds.), MIT Press: Cambridge, MA, pp. 207-216.Google Scholar
  33. Phillips, W.A., Kay, J., and Smyth, D. 1995. The discovery of structure by multi-stream networks of local processors with contextual guidance. Network, 6:225-246.Google Scholar
  34. Rosin, C.D. and Belew, R.D. 1997. New methods for competitive coevolution. Evolutionary Computation, 5(1):1-29.Google Scholar
  35. Rumelhart, D.E. and McClelland, J.L. 1986. Parallel Distributed Processing, MIT Press: Cambridge, MA.Google Scholar
  36. Sanger, T.D. 1989. Optimal unsupervised learning in a single-layer feedforward neural network. Neural Network, 2:459-473.Google Scholar
  37. Sasaky, T. and Tokoro, M. 1997. Adaptation toward changing environments: Why darwinian in nature? In Proceedings of the Fourth European Conference on Artificial Life, P. Husband and I. Harvey (Eds.), MIT Press: Cambridge, MA, pp. 378-387.Google Scholar
  38. Sims, K. 1995. Evolving 3D morphology and behavior by competition. Artificial Life, 1:353-372.Google Scholar
  39. Todd, P.M. and Miller, G.F. 1991. Exploring adaptive agency II: Simulating the evolution of associative learning. In From Animals to Animats. Proceedings of the First International Conference on Simulation of Adaptive Behavior, J.A. Meyer and S.W. Wilson (Eds.), MIT Press: Cambridge, MA.Google Scholar
  40. van Valen, L. 1973. A new evolutionary law. Evolution Theory, 1:1-30.Google Scholar
  41. Waddington, C.H. 1942. Canalization of development and the inheritance of acquired characters. Nature, 150:563-565.Google Scholar
  42. Widrow, B. and Hoff, M.E. 1960. Adaptive switching circuits, IRE WESCON Convention Record, Vol. IV, pp. 96-104.Google Scholar
  43. Willshaw, D. and Dayan, P. 1990. Optimal plasticity from matrix memories: What goes up must come down. Neural Computation, 2:85-93.Google Scholar
  44. Wilson, S.W. 1987. Classifier systems and the animat problem. Machine Learning, 2:199-228.Google Scholar
  45. Withley, D., Gordon, S., and Mathias, K. 1994. Lamarkian evolution, the Baldwin effect and function optimization. In Parallel Problem Solving from Nature (PPSNIII), Y. Davidor, H.P. Scwefel, and R. Manner (Eds.), Springer-Verlag: Berlin.Google Scholar
  46. Yamauchi, B. and Beer, R.D. 1995. Sequential behavior and learning in evolved dynamical neural networks. Adaptive Behavior, 2(3):219-246.Google Scholar

Copyright information

© Kluwer Academic Publishers 1999

Authors and Affiliations

  • Stefano Nolfi
    • 1
  • Dario Floreano
    • 2
  1. 1.National Research CouncilInstitute of PsychologyRomaItaly
  2. 2.Laboratory of Microcomputing (LAMI)Swiss Federal Institute of Technology (EPFL)LausanneSwitzerland

Personalised recommendations