Skip to main content
SpringerLink
Log in

A New Learning Algorithm for the Hierarchical Structure Learning Automata Operating in the General Nonstationary Multiteacher Environment

  • Conference paper
Knowledge-Based Intelligent Information and Engineering Systems (KES 2003)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 2773))

Abstract

Learning behaviors of the hierarchical structure stochastic automata operating in the general nonstationary multiteacher environment are considered. It is shown that convergence with probability 1 to the optimal path is ensured by a new learning algorithm which is an extended form of the relative reward strength algorithm.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 74.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 99.00
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Varshavskii, V.I., Vorontsova, I.P.: On the behavior of stochastic automata with variable structure. Atutom. Remote Control 22, 1345–1354 (1961)

    Google Scholar 

  2. Lakshmivarahan, S.: Learning Algorithms Theory and Applications. Springer, Heidelberg (1981)

    Book  MATH  Google Scholar 

  3. Baba, N.: New Topics in Learning Automata Theory and Applications. Springer, Heidelberg (1985)

    Book  MATH  Google Scholar 

  4. Narendra, K.S., Thathachar, M.A.L.: Learning Automata: An Introduction. Prentice-Hall, Englewood Cliffs (1989)

    Google Scholar 

  5. Poznyak, A.S., Najim, K.: Learning Automata and Stochastic Optimization. Springer, Heidelberg (1997)

    MATH  Google Scholar 

  6. Thathachar, M.A.L., Ramakrishnan, K.R.: A hierarchical system of learning automata. IEEE Trans. Syst. Man. Cybern. SMC-11, 236–241 (1981)

    MathSciNet  Google Scholar 

  7. Srikantakumar, R.P., Narendra, K.S.: A learning model for routing in telephone networks. SIAM J. Control Optim. 20, 4–57 (1982)

    Article  MathSciNet  Google Scholar 

  8. Zeng, X., Zhou, J., Vasseur, C.: A strategy for controlling nonlinear systems using a learning automata. Atutomatica 36, 1517–1524 (2000)

    Article  MathSciNet  MATH  Google Scholar 

  9. Papadimitriou, G.I., et al.: On the use of learning automata in the control of broadcast networks: A methodology. IEEE Trans. Syst. Man. Cybern. 32, 781–790 (2002)

    Article  Google Scholar 

  10. Baba, N., Sawaragi, Y.: On the learning behavior of stochastic automata under a nonstationary random enrironment. IEEE Trans. Syst. Man. Cybern. SMC-5, 273–275 (1975)

    Article  MathSciNet  Google Scholar 

  11. Thathachar, M.A.L., Sastry, P.S.: A class of rapidly converging algorithms for learning automata. In: Proc. IEEE Int. Conf. Cybernetics and Society, Bombay, India, pp. 602–606 (1984)

    Google Scholar 

  12. Thathachar, M.A.L., Sastry, P.S.: A hierarchical system of learning automata that can learn the globally optimal path. Inf. Sci. 42, 143–166 (1987)

    Article  MathSciNet  MATH  Google Scholar 

  13. Simha, R., Kurose, J.F.: Relative reward strength algorithms for learning automata. IEEE Trans. Syst. Man. Cybern. 19, 388–398 (1989)

    Article  MathSciNet  Google Scholar 

  14. Baba, N., Mogami, Y.: A new learning algorithm for the hierarchical structure learning automata operating in the nonstationary S-Model random environment. IEEE Trans. Syst. Man. Cybern. 32, 750–758 (2002)

    Article  Google Scholar 

  15. Oommen, B.J., Ageche, M.: Continuour and discretized pursuit learning scheme: Various algorithms and their comparison. IEEE Trans. Syst. Man. Cybern. B 31, 277–287 (2001)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Information Science, Osaka Kyoiku University, 582-8582, Japan

    Norio Baba

  2. Intelligent Information Engineering Systems, Tokushima University, 770-8506, Japan

    Yoshio Mogami

Authors
  1. Norio Baba
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yoshio Mogami
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Computing Laboratory, Oxford University, Parks Road, OXI 3QD, United Kingdom

    Vasile Palade

  2. Intelligent Systems and Signal Processing Labs, Moulsecoomb, University of Brighton, BN2 4GJ, Brighton, United Kingdom

    Robert J. Howlett

  3. Knowledge-Based Intelligent Engineering Systems Centre, Mawson Lakes, University of South Australia, 5095, Adelaide, SA, Australia

    Lakhmi Jain

Rights and permissions

Reprints and permissions

Copyright information

© 2003 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Baba, N., Mogami, Y. (2003). A New Learning Algorithm for the Hierarchical Structure Learning Automata Operating in the General Nonstationary Multiteacher Environment. In: Palade, V., Howlett, R.J., Jain, L. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2003. Lecture Notes in Computer Science(), vol 2773. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45224-9_151

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-45224-9_151

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-40803-1

  • Online ISBN: 978-3-540-45224-9

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation