Advertisement

Effectively Evolving Finite State Machines Compared to Enumeration

  • Patrick Ediger
  • Rolf Hoffmann
  • Sylvia Grüner
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6927)

Abstract

We want to answer the question how effectively finite state machines (FSMs) controlling the behavior of local agents in a multi agent system with a global task can be evolved by a genetic algorithm (GA). Different variants of the GA were used by varying the mutation techniques and the population size. In order to evaluate the effectiveness of the GA the optimal behavior is used for comparison. This optimal behavior can be found by a sophisticated enumeration technique. The agents’ global task is to explore an unknown area with obstacles. The number of states of the controlling FSM was restricted to five in order to keep the computation time for the enumeration acceptable. The results show that the GA is reliable and almost as effective as enumeration while being significantly faster.

Keywords

Genetic Algorithm State Machine Cellular Automaton Multi Agent System Finite State Machine 
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.
    Halbach, M., Heenes, W., Hoffmann, R., Tisje, J.: Optimizing the behavior of a moving creature in software and in hardware. Springer, Heidelberg (2004)CrossRefzbMATHGoogle Scholar
  2. 2.
    Koza, J.R.: Genetic Programming II: Automatic Discovery of Reusable Programs. The MIT Press, Cambridge (1994)zbMATHGoogle Scholar
  3. 3.
    Halbach, M.: Algorithmen und Hardwarearchitekturen zur optimierten Aufzählung von Automaten und deren Einsatz bei der Simulation künstlicher Kreaturen. PhD thesis, Technische Universität Darmstadt (2008)Google Scholar
  4. 4.
    Komann, M., Ediger, P., Fey, D., Hoffmann, R.: On the Effectivity of Genetic Programming Compared to the Time-Consuming Full Search of Optimal 6-State Automata. In: Vanneschi, L., Gustafson, S., Moraglio, A., De Falco, I., Ebner, M. (eds.) EuroGP 2009. LNCS, vol. 5481, pp. 280–291. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  5. 5.
    Ediger, P., Hoffmann, R., Halbach, M.: Evolving 6-state Automata for Optimal Behaviors of Creatures Compared to Exhaustive Search. In: Moreno-Díaz, R., Pichler, F., Quesada-Arencibia, A. (eds.) EUROCAST 2009. LNCS, vol. 5717, pp. 689–696. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  6. 6.
    Komann, M., Fey, D.: Evaluating the Evolvability of Emergent Agents with Different Numbers of StatesGoogle Scholar
  7. 7.
    Di Stefano, B.N., Lawniczak, A.T.: Autonomous roving object’s coverage of its universe. In: CCECE, pp. 1591–1594. IEEE, Los Alamitos (2006)Google Scholar
  8. 8.
    Halbach, M., Hoffmann, R., Both, L.: Optimal 6-state algorithms for the behavior of several moving creatures. In: El Yacoubi, S., Chopard, B., Bandini, S. (eds.) ACRI 2006. LNCS, vol. 4173, pp. 571–581. Springer, Heidelberg (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Patrick Ediger
    • 1
  • Rolf Hoffmann
    • 1
  • Sylvia Grüner
    • 1
  1. 1.FB Informatik, FG RechnerarchitekturTechnische Universität DarmstadtDarmstadtGermany

Personalised recommendations