Reinforcement Distribution in Continuous State Action Space Fuzzy Q–Learning: A Novel Approach

  • Andrea Bonarini
  • Francesco Montrone
  • Marcello Restelli
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3849)

Abstract

Fuzzy Q–learning extends the Q–learning algorithm to work in presence of continuous state and action spaces. A Takagi–Sugeno Fuzzy Inference System (FIS) is used to infer the continuous executed action and its action–value, by means of cooperation of several rules. Different kinds of evolution of the parameters of the FIS are possible, depending on different strategies of distribution of the reinforcement signal. In this paper, we compare two strategies: the classical one, focusing on rewarding the rules that have proposed the actions composed to produce the actual action, and a new one we are introducing, where reward goes to the rules proposing actions closest the ones actually executed.

Keywords

Reinforcement Learning Fuzzy Q–learning Fuzzy logic continuous state-action space reinforcement distribution 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Seo, H.-S., Youn, S.J., Oh, K.-W.: A fuzzy reinforcement function for the intelligent agent to process vague goals. In: Fuzzy Information Processing Society, Atlanta, GA, USA, pp. 29–33 (2000)Google Scholar
  2. 2.
    Berenji, H.R.: A reinforcement learning-based architecture for fuzzy logic control. In: Dubois, D., Prade, H., Yager, R.R. (eds.) Readings in Fuzzy Sets for Intelligent Systems, pp. 368–380. Kaufmann, San Mateo (1993)Google Scholar
  3. 3.
    Bonarini, A.: Delayed Reinforcement, Fuzzy Q-Learning and Fuzzy Logic Controllers, pp. 447–466. Springer, Heidelberg (1996)Google Scholar
  4. 4.
    Bonarini, A., Bonacina, C., Matteucci, M.: An approach to the design of reinforcement functions in real wolrd, agent-based applications. IEEE Transactions on Systems. Man, and Cybernetics – Part BGoogle Scholar
  5. 5.
    Glorennec, P.Y., Jouffe, L.: Fuzzy Q-learning. In: Proceedings of Fuzz-Ieee 1997, Sixth International Conference on Fuzzy Systems, Barcelona, Spain, pp. 659–662 (1997)Google Scholar
  6. 6.
    Jouffe, L.: Fuzzy Inference Systems Learning by Reinforcement Methods: Application to a Pig House Atmosphere Control. PhD thesis, Computer Science Department, Universitè de Rennes I, Rennes, France (1997)Google Scholar
  7. 7.
    Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)Google Scholar
  8. 8.
    Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. In: Adaptive Computation and Machine Learning Series. MIT Press, Cambridge (1998)Google Scholar
  9. 9.
    Watkins, C., Dayan, P.: Q-learning. Machine Learning 8, 279–292 (1992)MATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Andrea Bonarini
    • 1
  • Francesco Montrone
    • 1
  • Marcello Restelli
    • 1
  1. 1.Politecnico di Milano Electronic and Information DepartmentMilanItaly

Personalised recommendations