Advertisement

State Space Properties of Boolean Networks Trained for Sequence Tasks

  • Andrea Roli
  • Matteo Amaducci
  • Lorenzo Garattoni
  • Carlo Pinciroli
  • Mauro Birattari
Part of the Springer Proceedings in Complexity book series (SPCOM)

Abstract

In a recent work, it has been shown that Boolean networks (BN), a well-known genetic regulatory network model, can be utilised to control robots. In this work, we use a genetic algorithm to train robots controlled by a BN so as to accomplish a sequence learning task. We analyse the robots’ dynamics by studying the corresponding BNs’ phase space. Our results show that a phase space structure emerges enabling the robot to have memory of the past and to exploit this piece of information to choose the next action to perform. This finding is in accordance with previous results on minimally cognitive behaviours and shows that the phase space of Boolean networks can be shaped by the learning process in such a way that the robot can accomplish non-trivial tasks requiring the use of memory.

Keywords

State Space Boolean Function Sequence Learning Boolean Network Finite State Automaton 
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.

References

  1. 1.
    Aldana M, Coppersmith S, Kadanoff L (2003) Boolean dynamics with random couplings. In: Kaplan E, Marsden J, Sreenivasan K (eds) Perspectives and problems in nonlinear science. A celebratory volume in honor of Lawrence Sirovich. Springer applied mathematical sciences series. Springer, Berlin Google Scholar
  2. 2.
    Bar–Yam Y (1997) Dynamics of complex systems. Studies in nonlinearity. Addison-Wesley, Reading zbMATHGoogle Scholar
  3. 3.
    Beer R (1995) A dynamical systems perspective on agent-environment interaction. Artif Intell 72:173–215 CrossRefGoogle Scholar
  4. 4.
    Kauffman S (1993) The origins of order: self-organization and selection in evolution. Oxford University Press, London Google Scholar
  5. 5.
    Mondada F, Bonani M, Raemy X, Pugh J, Cianci C, Klaptocz A, Magnenat S, Zufferey JC, Floreano D, Martinoli A (2009) The e-puck, a robot designed for education in engineering. In: Gonçalves P, Torres P, Alves C (eds) Proceedings of the 9th conference on autonomous robot systems and competitions, vol 1, pp 59–65 Google Scholar
  6. 6.
    Nolfi S (2005) Categories formation in self-organizing embodied agents. In: Cohen H, Lefebvre C (eds) Handbook of categorization in cognitive science. Elsevier, Amsterdam, pp 869–889 CrossRefGoogle Scholar
  7. 7.
    Nolfi S, Floreano D (2000) Evolutionary robotics. MIT Press, Cambridge Google Scholar
  8. 8.
    Pfeifer R, Bongard J (2006) How the body shapes the way we think: a new view of intelligence. MIT Press, Cambridge Google Scholar
  9. 9.
    Pinciroli C, Trianni V, O’Grady R, Pini G, Brutschy A, Brambilla M, Mathews N, Ferrante E, Di Caro G, Ducatelle F, Stirling T, Gutiérrez A, Gambardella L, Dorigo M (2011) ARGoS: a modular, multi-engine simulator for heterogeneous swarm robotics. In: Proceedings of the IEEE/RSJ international conference on intelligent robots and systems (IROS 2011). IEEE Comput Soc, Los Alamitos, pp 5027–5034 CrossRefGoogle Scholar
  10. 10.
    Roli A, Manfroni M, Pinciroli C, Birattari M (2011) On the design of Boolean network robots. In: Di Chio C, Cagnoni S, Cotta C, Ebner M, Ekárt A, Esparcia-Alcázar A, Merelo J, Neri F, Preuss M, Richter H, Togelius J, Yannakakis G (eds) Applications of evolutionary computation. Lecture notes in computer science, vol 6624. Springer, Heidelberg, pp 43–52 CrossRefGoogle Scholar
  11. 11.
    Serra R, Villani M, Graudenzi A, Kauffman S (2007) Why a simple model of genetic regulatory networks describes the distribution of avalanches in gene expression data. J Theor Biol 246:449–460 MathSciNetCrossRefGoogle Scholar
  12. 12.
    Serra R, Zanarini G (1990) Complex systems and cognitive processes. Springer, Berlin CrossRefGoogle Scholar
  13. 13.
    Shmulevich I, Dougherty E (2009) Probabilistic Boolean networks: the modeling and control of gene regulatory networks. SIAM, Philadelphia Google Scholar
  14. 14.
    Sun R, Giles C (2001) Sequence learning: from recognition and prediction to sequential decision making. IEEE Intell Syst 16(4):67–70 CrossRefGoogle Scholar
  15. 15.
    Yamauchi B, Beer R (1994) Sequential behavior and learning in evolved dynamical neural networks. Adapt Behav 2(3):219–246 CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2013

Authors and Affiliations

  • Andrea Roli
    • 1
  • Matteo Amaducci
    • 1
  • Lorenzo Garattoni
    • 2
  • Carlo Pinciroli
    • 2
  • Mauro Birattari
    • 2
  1. 1.Dipartimento di Informatica: Scienza e Ingegneria, DISI, Alma Mater StudiorumUniversità di BolognaCesenaItaly
  2. 2.IRIDIA-CoDEUniversité libre de BruxellesBrusselsBelgium

Personalised recommendations