Knowledge Extraction from Reinforcement Learning

Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 84)


This chapter is concerned with knowledge extraction from reinforcement learners. It addresses two approaches towards knowledge extraction: the extraction of explicit, symbolic rules from neural reinforcement learners, and the extraction of complete plans from such learners. The advantages of such knowledge extraction include (1) the improvement of learning (especially with the rule extraction approach), and (2) the improvement of the usability of results of learning.


Reinforcement Learner Bottom Level Sequential Decision Rule Extraction Knowledge Extraction 
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.
    Fu, L.M. (1991), “Rule learning by searching on adapted nets,” Proc. of AAAI’91, pp. 590–595.Google Scholar
  2. 2.
    Lavrac, N. and Dzeroski, S. (1994), Inductive Logic Programming, Ellis Horword, New York.MATHGoogle Scholar
  3. 3.
    Lin, L. (1992), “Self-improving reactive agents based on reinforcement learning, planning, and teaching,” Machine Learning, vol. 8, pp. 293–321.Google Scholar
  4. 4.
    Maclin, R. and Shavlik, J. (1994), “Incorporating advice into agents that learn from reinforcements,” Proc. of AAAI-9.4, Morgan Kaufmann, San Meteo, CA.Google Scholar
  5. 5.
    Sun, R. (1992), “On variable binding in connectionist networks,” Connection Science, vol. 4, no. 2, pp. 93–124.CrossRefGoogle Scholar
  6. 6.
    Sun, R. (1997), “Learning, action, and consciousness: a hybrid approach towards modeling consciousness,” Neural Networks, vol. 10, no. 7, pp. 1317–1331.CrossRefGoogle Scholar
  7. 7.
    Sun, R. (1997), “Multi-agent approaches toward reinforcement learning,” TRCS-97–0028, University of AlabamaGoogle Scholar
  8. 8.
    Sun, R. and Peterson, T. (1997), “A hybrid model for learning sequential navigation,” Proc. of IEEE International Symposium on Computational Intelligence in Robotics and Automation (CIRA’97), IEEE Press, Monterey, CA, pp. 234–239.Google Scholar
  9. 9.
    Sun, R. and Peterson, T. (1998), “Autonomous learning of sequential tasks: experiments and analyses,” IEEE Transactions on Neural Networks, vol. 9, no. 6, pp. 1217–1234.CrossRefGoogle Scholar
  10. 10.
    Sun, R., Peterson, T., and Merrill, E. (1999), “A hybrid architecture for situated learning of reactive sequential decision making,” Applied Intelligence,in press.Google Scholar
  11. 11.
    Sun, R. and Sessions, C. (1998), “Extracting plans from reinforcement learners,” in L. Xu, L. Chan, I. King, and A. Fu (Eds.), Proceedings of the 1998 International Symposium on Intelligent Data Engineering and Learning (IDEAL’98), Springer-Verlag, pp. 243–248.Google Scholar
  12. 12.
    Sun, R. and Sessions, C. (1998), “Learning to plan probabilistically from neural networks,” Proceedings of IEEE International Conference on Neural Networks, Anchorage, Alaska. May 4–9, IEEE Press, Piscataway, NJ, pp. 1–6.Google Scholar
  13. 13.
    Sutton, R. (1990), “Integrated architectures for learning, planning, and reacting based on approximating dynamic programming,” Proc. of Seventh International Conference on Machine Learning, Morgan Kaufmann, San Mateo, CA.Google Scholar
  14. 14.
    Tesauro, T. (1992), “Practical issues in temporal difference learning,” Machine Learning, vol. 8, pp. 257–277.MATHGoogle Scholar
  15. 15.
    Towell, G. and Shavlik, J. (1993), “Extracting refined rules from Knowledge-Based Neural Networks,” Machine Learning, vol. 13, no. 1, pp. 71–101.Google Scholar
  16. 16.
    Watkins, C. (1989), Learning with Delayed Rewards, Ph.D. Thesis, Cambridge University, Cambridge, U.K.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Ron Sun
    • 1
  1. 1.Department of Computer Engineering and Computer ScienceUniversity of Missouri-ColumbiaColumbiaUSA

Personalised recommendations