Learning in BDI Multi-agent Systems

  • Alejandro Guerra-Hernández
  • Amal El Fallah-Seghrouchni
  • Henry Soldano
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3259)


This paper deals with the issue of learning in multi-agent systems (MAS). Particularly, we are interested in BDI (Belief, Desire, Intention) agents. Despite the relevance of the BDI model of rational agency, little work has been done to deal with its two main limitations: i) The lack of learning competences; and ii) The lack of explicit multi-agent functionality. From the multi-agent learning perspective, we propose a BDI agent architecture extended with learning competences for MAS context. Induction of Logical Decision Trees, a first order method, is used to enable agents to learn when their plans are successfully executable. Our implementation enables multiple agents executed as parallel functions in a single Lisp image. In addition, our approach maintains consistency between learning and the theory of practical reasoning.


Multiagent System Commitment Strategy Learning Agent Intentional Stance Event Queue 
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.
    Bradzil, P., et al.: Learning in Distributed Systems and Multi-Agent Environments. In: Kodratoff, Y. (ed.) EWSL 1991. LNCS, vol. 482. Springer, Heidelberg (1991)Google Scholar
  2. 2.
    Bratman, M.: Intention, Plans, and Practical Reasoning. Harvard University Press, Cambridge (1987)Google Scholar
  3. 3.
    Bratman, M., Israel, D.J., Pollack, M.E.: Plans and resource-bounded practical reasoning. Computational Intelligence 4, 349–355 (1988)CrossRefGoogle Scholar
  4. 4.
    Blockeel, H., De Raedt, L.: Top-down induction of first-order logical decision trees. Artificial Intelligence 101(1–2), 285–297 (1998)MathSciNetCrossRefzbMATHGoogle Scholar
  5. 5.
    Blockeel, H., et al.: Executing query packs in ILP. In: Cussens, J., Frisch, A.M. (eds.) ILP 2000. LNCS, vol. 1866, pp. 60–77. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  6. 6.
    Castelfranchi, C.: Modelling Social Action for AI Agents. Artificial Intelligence 103(1), 157–182 (1998)CrossRefzbMATHGoogle Scholar
  7. 7.
    Dennett, D.C.: The Intentional Stance. MIT Press, Cambridge MA (1987)Google Scholar
  8. 8.
    Charniak, E., McDermott, D.: Introduction to Artificial Intelligence. Addison-Wesley, Reading (1985)zbMATHGoogle Scholar
  9. 9.
    García, F.: Apprentissage et Planification. In: Proceedings of JICAA 1997, USA, pp. 15–26 (1997)Google Scholar
  10. 10.
    Geddis, D.F.: Caching and First-Order inference in model elimination theorem provers. Ph.D. Thesis. Stanford University, Stanford, CA, USA (1995)Google Scholar
  11. 11.
    Georgeff, M.P., Lansky, A.L.: Reactive Reasoning and Planning. In: Proceedings of the Sixth National Conference on Artificial Intelligence (AAAI-1987), Seattle WA., USA, pp. 667–682 (1987)Google Scholar
  12. 12.
    Georgeff, M.P., Rao, A.S.: A Profile of the Australian AI Institute. IEEE Expert 11(6), 89–92 (1996)CrossRefGoogle Scholar
  13. 13.
    Georgeff, M.P., et al.: The Belief-Desire-Intention Model of Agency. In: Rao, A.S., Singh, M.P., Müller, J.P. (eds.) ATAL 1998. LNCS, vol. 1555, pp. 1–10. Springer, Heidelberg (1999)CrossRefGoogle Scholar
  14. 14.
    Huber, M.: A BDI-theoretic mobile agent architecture. In: Proceedings of the Third Conference on Autonomous Agents (Agents 1999), Seattle, WA., USA, pp. 236–243 (1999)Google Scholar
  15. 15.
    D’Inverno, M., Kinny, D., Luck, M., Wooldridge, M.: A Formal Specification of dMARS. In: Rao, A., Singh, M.P., Wooldridge, M.J. (eds.) ATAL 1997. LNCS, vol. 1365, pp. 155–176. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  16. 16.
    Kinny, D., Georgeff, M.P.: Commitment and effectiveness of situated agents. In: Proceeding of the Twelfth International Conference on Artificial Intelligence IJCAI 1991, Sidney, Australia, pp. 82–88 (1991)Google Scholar
  17. 17.
    Lightfoot, D.: Formal Specification Using Z. The Macmillan Press LTD, Macmillan Computer Science Series, London, UK (1991)Google Scholar
  18. 18.
    Metral, M.: A generic learning interface architecture. Massachusetts Institute of Technology. Master’s thesis. Cambridge, MA, USA (1992)Google Scholar
  19. 19.
    Mitchell, T.M.: Machine Learning, Mc Graw-Hill International Editions, Singapore (1997)Google Scholar
  20. 20.
    Muggleton, S., de Raed, L.: Inductive Logic Programming: Theory and Methods. Journal of Logic Programming 19, 629–679 (1994)MathSciNetCrossRefzbMATHGoogle Scholar
  21. 21.
    Olivia, C., et al: Case-Based BDI agents: An Effective Approach to Intelligent Search on the WWW. In: AAAI Symposium on Intelligent Agents. Stanford University, Stanford CA (1999)Google Scholar
  22. 22.
    Quinlan, J.R.: Induction of Decision Trees. Machine Learning 1, 81–106 (1986)Google Scholar
  23. 23.
    Rao, A.S., Georgeff, M.P.: Decision procedures of BDI logics. Journal of Logic and Computation 8(3), 293–344 (1998)MathSciNetCrossRefzbMATHGoogle Scholar
  24. 24.
    Russell, S.J., Norvig, P.: Artificial Intelligence, a modern approach. Prentice-Hall, New Jersey (1995)zbMATHGoogle Scholar
  25. 25.
    Singh, M., Rao, A.S., Georgeff, M.P.: Formal Methods in DAI: Logic-based representations and reasoning. In: Weiss, G. (ed.) Multiagent Systems, a modern approach to Distributed Artificial Intelligence, USA. MIT Press, Cambridge MA (1999)Google Scholar
  26. 26.
    Stone, P., Veloso, M.: Multiagent Systems: A Survey from a Machine Learning Perspective. Autonomous Robotics 8(3), 345–383 (2000)CrossRefGoogle Scholar
  27. 27.
    Sutton, R.S., Barto, A.G.: Reinforcement Learning: An introduction. MIT Press, Cambridge (1998)Google Scholar
  28. 28.
    Weiss, G., Sen, S.: Adaptation and Learning in Multiagent Systems. In: Weiss, G., Sen, S. (eds.) IJCAI-WS 1995. LNCS, vol. 1042. Springer, Heidelberg (1996)CrossRefGoogle Scholar
  29. 29.
    Wooldridge, M.: Reasoning about Rational Agents. MIT Press, Cambridge (2000)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Alejandro Guerra-Hernández
    • 1
  • Amal El Fallah-Seghrouchni
    • 2
  • Henry Soldano
    • 1
  1. 1.Laboratoire d’Informatique de Paris Nord, UMR 7030 – CNRSUniversité Paris 13VilletaneueseFrance
  2. 2.Laboratoire d’Informatique de Paris 6, UMR 7606 – CNRSUniversité Paris 6ParisFrance

Personalised recommendations