Design for a Darwinian Brain: Part 2. Cognitive Architecture

  • Chrisantha Fernando
  • Vera Vasas
  • Alexander W. Churchill
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8064)

Abstract

The accumulation of adaptations in an open-ended manner during lifetime learning is a holy grail in reinforcement learning, intrinsic motivation, artificial curiosity, and developmental robotics. We present a design for a cognitive architecture that is capable of specifying an unlimited range of behaviors. We then give examples of how it can stochastically explore an interesting space of adjacent possible behaviors. There are two main novelties; the first is a proper definition of the fitness of self-generated games such that interesting games are expected to evolve. The second is a modular and evolvable behavior language that has systematicity, productivity, and compositionality, i.e. it is a physical symbol system. A part of the architecture has already been implemented on a humanoid robot.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bellas, F., Duro, R., Faina, A., Souto, D.: Multilevel darwinist brain (mdb): Artificial evolution in a cognitive architecture for real robots. IEEE Transactions on Autonomous Mental Development 2(4), 340–354 (2010)CrossRefGoogle Scholar
  2. 2.
    Fisher, R.: The Genetical Theory of Natural Selection. Clarendon Press (1930)Google Scholar
  3. 3.
    Rechenberg, I.: Evolutionstrategie 94. Frommann-Holzboog, Stuttgart (1994)Google Scholar
  4. 4.
    Bongard, J., Lipson, H.: Nonlinear system identification using coevolution of models and tests. IEEE Transactions on Evolutionary Computation 8(4), 361–384 (2005)CrossRefGoogle Scholar
  5. 5.
    Baranes, A., Oudeyer, P.Y.: R-iac: Robust intrinsically motivated active learning. In: 2009 IEEE 8th International Conference on Development and Learning, Shanghai, China, pp. 1–6 (2009)Google Scholar
  6. 6.
    Baranes, A., Oudeyer, P.Y.: Intrinsically motivated goal exploration for active motor learning in robots: a case study (2010)Google Scholar
  7. 7.
    Baranes, A., Oudeyer, P.Y.: Active learning of inverse models with intrinsically motivated goal exploration in robots. Robotics and Autonomous Systems (2012)Google Scholar
  8. 8.
    Oudeyer, P.Y., Kaplan, F., Hafner, V.: Intrinsic motivation systems for autonomoys mental development. IEEE Transactions on Evolutionary Computation 11(2), 265–286 (2007)CrossRefGoogle Scholar
  9. 9.
    Fodor, J., Pylyshyn, Z.: Connectionism and cognitive architecture: A critical analysis. Cognition 28, 3–71 (1988)CrossRefGoogle Scholar
  10. 10.
    Hofstadter, D., Mitchell, M.: The copycat project: A model of mental fluidity and analogy-making. In: Fluid Concepts and Creative Analogies: Computer Models of the Fundamental Mechanisms of Thought, pp. 205–267. Basic Books, New York (1995)Google Scholar
  11. 11.
    Newell, A.: Unified Theories of Cognition. Harvard University Press (1990)Google Scholar
  12. 12.
    Anderson, J.: How Can the Human Mind Occur in the Physical Universe. Oxford University Press (2007)Google Scholar
  13. 13.
    Sun, R.: Duality of the Mind: A Bottom-up Approach Toward Cognition. Lawrence Erlbaum Associates, Mahwah (2002)Google Scholar
  14. 14.
    Marcus, G.: The Algebraic Mind: Integrating Connectionism and Cognitive Science. MIT Press (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Chrisantha Fernando
    • 1
  • Vera Vasas
    • 1
  • Alexander W. Churchill
    • 1
  1. 1.Dept. of Electronic Engineering and Computer ScienceQueen Mary University of LondonUK

Personalised recommendations