Continuous-State Reinforcement Learning with Fuzzy Approximation

  • Lucian Buşoniu
  • Damien Ernst
  • Bart De Schutter
  • Robert Babuška
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4865)


Reinforcement learning (RL) is a widely used learning paradigm for adaptive agents. There exist several convergent and consistent RL algorithms which have been intensively studied. In their original form, these algorithms require that the environment states and agent actions take values in a relatively small discrete set. Fuzzy representations for approximate, model-free RL have been proposed in the literature for the more difficult case where the state-action space is continuous. In this work, we propose a fuzzy approximation architecture similar to those previously used for Q-learning, but we combine it with the model-based Q-value iteration algorithm. We prove that the resulting algorithm converges. We also give a modified, asynchronous variant of the algorithm that converges at least as fast as the original version. An illustrative simulation example is provided.


Radial Basis Function Reinforcement Learning Action Space Reward Function Fuzzy Partition 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)Google Scholar
  2. 2.
    Bertsekas, D.P.: Dynamic Programming and Optimal Control, 2nd edn., vol. 2. Athena Scientific (2001)Google Scholar
  3. 3.
    Watkins, C.J.C.H., Dayan, P.: Q-learning. Machine Learning 8, 279–292 (1992)zbMATHGoogle Scholar
  4. 4.
    Glorennec, P.Y.: Reinforcement learning: An overview. In: ESIT 2000. Proceedings European Symposium on Intelligent Techniques, Aachen, Germany, September 14–15, 2000, pp. 17–35 (2000)Google Scholar
  5. 5.
    Horiuchi, T., Fujino, A., Katai, O., Sawaragi, T.: Fuzzy interpolation-based Q-learning with continuous states and actions. In: FUZZ-IEEE 1996. Proceedings 5th IEEE International Conference on Fuzzy Systems, New Orleans, US, September 8–11, 1996, pp. 594–600 (1996)Google Scholar
  6. 6.
    Jouffe, L.: Fuzzy inference system learning by reinforcement methods. IEEE Transactions on Systems, Man, and Cybernetics—Part C: Applications and Reviews 28(3), 338–355 (1998)CrossRefGoogle Scholar
  7. 7.
    Berenji, H.R., Khedkar, P.: Learning and tuning fuzzy logic controllers through reinforcements. IEEE Transactions on Neural Networks 3(5), 724–740 (1992)CrossRefGoogle Scholar
  8. 8.
    Berenji, H.R., Vengerov, D.: A convergent actor-critic-based FRL algorithm with application to power management of wireless transmitters. IEEE Transactions on Fuzzy Systems 11(4), 478–485 (2003)CrossRefGoogle Scholar
  9. 9.
    Vengerov, D., Bambos, N., Berenji, H.R.: A fuzzy reinforcement learning approach to power control in wireless transmitters. IEEE Transactions on Systems, Man, and Cybernetics—Part B: Cybernetics 35(4), 768–778 (2005)CrossRefGoogle Scholar
  10. 10.
    Lin, C.K.: A reinforcement learning adaptive fuzzy controller for robots. Fuzzy Sets and Systems 137, 339–352 (2003)zbMATHCrossRefMathSciNetGoogle Scholar
  11. 11.
    Tsitsiklis, J.N., Van Roy, B.: Feature-based methods for large scale dynamic programming. Machine Learning 22(1–3), 59–94 (1996)zbMATHGoogle Scholar
  12. 12.
    Szepesvári, C., Munos, R.: Finite time bounds for sampling based fitted value iteration. In: ICML 2005. Proceedings Twenty-Second International Conference on Machine Learning, Bonn, Germany, August 7–11, 2005, pp. 880–887 (2005)Google Scholar
  13. 13.
    Gordon, G.: Stable function approximation in dynamic programming. In: ICML 1995. Proceedings Twelfth International Conference on Machine Learning, Tahoe City, US, July 9–12, 1995, pp. 261–268 (1995)Google Scholar
  14. 14.
    Wiering, M.: Convergence and divergence in standard and averaging reinforcement learning. In: Boulicaut, J.-F., Esposito, F., Giannotti, F., Pedreschi, D. (eds.) ECML 2004. LNCS (LNAI), vol. 3201, pp. 477–488. Springer, Heidelberg (2004)Google Scholar
  15. 15.
    Ormoneit, D., Sen, S.: Kernel-based reinforcement learning. Machine Learning 49(2–3), 161–178 (2002)zbMATHCrossRefGoogle Scholar
  16. 16.
    Ernst, D., Geurts, P., Wehenkel, L.: Tree-based batch mode reinforcement learning. Journal of Machine Learning Research 6, 503–556 (2005)MathSciNetGoogle Scholar
  17. 17.
    Szepesvári, C., Smart, W.D.: Interpolation-based Q-learning. In: ICML 2004. Proceedings Twenty-First International Conference on Machine Learning, Bannf, Canada, July 4–8, 2004 (2004)Google Scholar
  18. 18.
    Singh, S.P., Jaakkola, T., Jordan, M.I.: Reinforcement learning with soft state aggregation. In: NIPS 1994. Advances in Neural Information Processing Systems 7, Denver, US, pp. 361–368 (1994)Google Scholar
  19. 19.
    Ernst, D.: Near Optimal Closed-loop Control. Application to Electric Power Systems. PhD thesis, University of Liège, Belgium (March 2003)Google Scholar
  20. 20.
    Munos, R., Moore, A.: Variable-resolution discretization in optimal control. Machine Learning 49(2–3), 291–323 (2002)zbMATHCrossRefGoogle Scholar
  21. 21.
    Sherstov, A., Stone, P.: Function approximation via tile coding: Automating parameter choice. In: Zucker, J.-D., Saitta, L. (eds.) SARA 2005. LNCS (LNAI), vol. 3607, pp. 194–205. Springer, Heidelberg (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Lucian Buşoniu
    • 1
  • Damien Ernst
    • 2
  • Bart De Schutter
    • 1
  • Robert Babuška
    • 1
  1. 1.Delft University of TechnologyThe Netherlands
  2. 2.Supélec, RennesFrance

Personalised recommendations