Advertisement

Minds and Machines

, Volume 7, Issue 4, pp 475–494 | Cite as

Brave Mobots Use Representation: Emergence of Representation in Fight-or-Flight Learning

  • Chris Thornton
Article

Abstract

The paper uses ideas from Machine Learning, Artificial Intelligence and Genetic Algorithms to provide a model of the development of a ‘fight-or-flight’ response in a simulated agent. The modelled development process involves (simulated) processes of evolution, learning and representation development. The main value of the model is that it provides an illustration of how simple learning processes may lead to the formation of structures which can be given a representational interpretation. It also shows how these may form the infrastructure for closely-coupled agent/environment interaction.

Emergence learning representation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Barnett, S. (1973), Ethology and Development, Heinemann Medical.Google Scholar
  2. Boden, M. (1979), Piaget, Fontana Modern Masters, Fontana Press.Google Scholar
  3. Bolles, R. (1979), Learning Theory (2nd edition), New York: Holt.Google Scholar
  4. Braitenberg, V. (1984), Vehicles: Experiments in Synthetic Psychology, London: The MIT Press.Google Scholar
  5. Cliff, D., Husbands, P. and Harvey, I. (1993), ‘Evolving visually guided robots’, in J. Meyer, H. Roitblat and S. Wilson (Eds.), From Animals to Animats: Proceedings of the Second International Conference on Simulation of Adaptive Behaviour(SAB92). MIT/Bradford Books.Google Scholar
  6. Feder, M. and Lauder, G. (Eds.) (1986), Predator-Prey Relationships. Perspectives and Approaches from the Study of Lower Vertebrates, Chicago and London: University of Chicago Press.Google Scholar
  7. Flaherty, C. (1985), Animal Learning and Cognition, New York: Knopf.Google Scholar
  8. Gerlai, R. (1993), ‘Can paradise fish (macropodus opercularis anabantidae) recognize a natural predator. an ethological analysis’, Ethology 94, pp. 127-136.Google Scholar
  9. Goldberg, D. (1989), Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley.Google Scholar
  10. Holland, J. (1975), Adaptation in Natural and Artificial Systems, Ann Arbor: University of Michigan Press.Google Scholar
  11. Karmiloff Smith, A. (1992), Beyond Modularity: A Developmental Perspective on Cognitive Science, Cambridge, Ma.: MIT Press/Bradford Books.Google Scholar
  12. K-Team, (1993), Khepera Users Manual. Lausanne: EPFL.Google Scholar
  13. Muggleton, S. (Ed.) (1992), Inductive Logic Programming, Academic Press.Google Scholar
  14. Nolfi, S., Floreano, D., Miglino, O. and Mondada, F. (1994), ‘How to evolve autonomous robots: different approaches in evolutionary robotics’, in R. A. Brooks and P. Maes (Eds.), Proceedings of Artificial Life IV (pp. 190-197).Google Scholar
  15. Quinlan, J. (1986), ‘Induction of decision trees’, Machine Learning 1, pp. 81-106.Google Scholar
  16. Rumelhart, D., Hinton, G. and Williams, R. (1986), ‘Learning representations by back-propagating errors’, Nature 323, pp. 533-6.Google Scholar
  17. Rumelhart, D. and Zipser, D. (1986), ‘Feature discovery by competitive learning’, in D. Rumelhart, J. McClelland and the PDP Research Group (Eds.), Parallel Distributed Processing: Explorations in the Microstructures of Cognition. Vol I (pp. 151-193). Cambridge, Mass.: MIT Press.Google Scholar
  18. Shavlik, J. and Dietterich, T. (Eds.) (1990), Readings in Machine Learning, San Mateo, California: Morgan Kaufmann.Google Scholar
  19. Thornton, C. (1994), ‘Unsupervised learning with the soft-means algorithm’, Proceedings of the World Congress on Neural Networks, Vol. 4 (pp. 200-205 (v. 4)). San Diego.Google Scholar
  20. Thornton, C. (1995a), ‘Measuring the difficulty of specific learning problems’, Connection Science 7 (No. 1), pp. 81-92.Google Scholar
  21. Thornton, C. (1995b), ‘Compression, dilation and the redescriptive role of explicitation’, in J. Hoc (Ed.), Proceedings of the European Conference on Cognitive Science (pp. 19-30).Google Scholar
  22. Wilson, S. (1991), ‘The animat path to AI’, in J. Meyer and S.W. Wilson (Eds.), Proceedings of the First International Conference on the Simulation of Adaptive Behaviour (From Animals to Animats) (p. 16). Cambridge: MIT Press.Google Scholar

Copyright information

© Kluwer Academic Publishers 1997

Authors and Affiliations

  • Chris Thornton
    • 1
  1. 1.Cognitive and Computing SciencesUniversity of SussexBrightonU.K

Personalised recommendations