Multiagent Incremental Learning in Networks

  • Gauvain Bourgne
  • Amal El Fallah Seghrouchni
  • Nicolas Maudet
  • Henry Soldano
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5357)


This paper investigates incremental multiagent learning in structured networks. Learning examples are incrementally distributed among the agents, and the objective is to build a common hypothesis that is consistent with all the examples present in the system, despite communication constraints. Recently, different mechanisms have been proposed that allow groups of agents to coordinate their hypotheses. Although these mechanisms have been shown to guarantee (theoretically) convergence to globally consistent states of the system, others notions of effectiveness can be considered to assess their quality. Furthermore, this guaranteed property should not come at the price of a great loss of efficiency (for instance a prohibitive communication cost). We explore these questions theoretically and experimentally (using different boolean formulas learning problems).


Span Tree Multiagent System Communicational Cost Boolean Formula Learner Agent 
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.
    Bourgne, G., Seghrouchni, A.E.F., Soldano, H.: SMILE: Sound Multi-agent Incremental LEarning. In: Proc. of AAMAS 2007, pp. 164–171. ACM Press, New York (2007)Google Scholar
  2. 2.
    Stone, P.: Intelligent Autonomous Robotics: A Robot Soccer Case Study. Synthesis Lectures on Artificial Intelligence and Machine Learning. Morgan & Claypool Publishers, San Francisco (2007)Google Scholar
  3. 3.
    Ontañon, S., Plaza, E.: Recycling data for multi-agent learning. In: ICML 2005, pp. 633–640. ACM Press, New York (2005)Google Scholar
  4. 4.
    Bourgne, G., Seghrouchni, A.E.F., Maudet, N.: Towards refinement of abductive or inductive hypothesis through propagation (2008) (under review)Google Scholar
  5. 5.
    Henniche, M.: MGI: an incremental bottom-up algorithm. In: IEEE Aust. and New Zealand Conference on Intelligent Information Systems, pp. 347–351 (1994)Google Scholar
  6. 6.
    Califf, M.E., Mooney, R.J.: Bottom-up relational learning of pattern matching rules for information extraction. Journal of Mach. Learn. Res. 4, 177–210 (2003)MathSciNetzbMATHGoogle Scholar
  7. 7.
    Esmeir, S., Markovitch, S.: Lookahead-based algorithms for anytime induction of decision trees. In: ICML2004, pp. 257–264. Morgan Kaufmann, San Francisco (2004)Google Scholar
  8. 8.
    Cohen, W.W.: Fast effective rule induction. In: ICML, pp. 115–123 (1995)Google Scholar
  9. 9.
    Quinlan, J.R.: Induction of decision trees. Machine Learning 1(1), 81–106 (1986)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Gauvain Bourgne
    • 1
  • Amal El Fallah Seghrouchni
    • 2
  • Nicolas Maudet
    • 1
  • Henry Soldano
    • 3
  1. 1.LAMSADE, Université Paris-DauphineParis Cedex 16France
  2. 2.LIP6, Université Pierre and Marie CurieParisFrance
  3. 3.LIPN, Université Paris-NordVilletaneuseFrance

Personalised recommendations