Improving Control-Knowledge Acquisition for Planning by Active Learning

  • Raquel Fuentetaja
  • Daniel Borrajo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4212)


Automatically acquiring control-knowledge for planning, as it is the case for Machine Learning in general, strongly depends on the training examples. In the case of planning, examples are usually extracted from the search tree generated when solving problems. Therefore, examples depend on the problems used for training. Traditionally, these problems are randomly generated by selecting some difficulty parameters. In this paper, we discuss several active learning schemes that improve the relationship between the number of problems generated and planning results in another test set of problems. Results show that these schemes are quite useful for increasing the number of solved problems.


  1. 1.
    Cohn, D., Ghabhramani, Z., Jordan, M.: Active learning with statistical models. Journal of Artificial Intelligence Research 4, 129–145 (1996)zbMATHGoogle Scholar
  2. 2.
    Liere, R., Tadepalli, P., Hall, D.: Active learning with committees for text categorization. In: Proceedings of the Fourteenth Conference on Artificial Intelligence, Providence, RI, USA, pp. 591–596 (1997)Google Scholar
  3. 3.
    Lin, F.R., Shaw, M.: Active training of backpropagation neural networks using the learning by experimentation methodology. Annals of Operations Research 75, 129–145 (1997)CrossRefGoogle Scholar
  4. 4.
    Mitchell, T.M., Utgoff, P.E., Banerji, R.B.: Learning by experimentation: Acquiring and refining problem-solving heuristics. In: Machine Learning, An Artificial Intelligence Approach. Tioga Press, Palo Alto (1983)Google Scholar
  5. 5.
    Bryant, C., Muggleton, S., Oliver, S., Kell, D., Reiser, P., King, R.: Combining inductive logic programming, active learning and robotics to discover the function of genes. Linkoping Electronic Articles in Computer and Information Science 6(12) (2001)Google Scholar
  6. 6.
    Fedorov, V.: Theory of Optimal Experiments. Academic Press, London (1972)Google Scholar
  7. 7.
    Zimmerman, T., Kambhampati, S.: Learning-assisted automated planning: Looking back, taking stock, going forward. AI Magazine 24(2), 73–96 (2003)Google Scholar
  8. 8.
    Minton, S.: Learning Effective Search Control Knowledge: An Explanation-Based Approach. Kluwer Academic Publishers, Boston (1988)Google Scholar
  9. 9.
    Fikes, R.E., Hart, P.E., Nilsson, N.J.: Learning and executing generalized robot plans. Artificial Intelligence 3, 251–288 (1972)CrossRefGoogle Scholar
  10. 10.
    Borrajo, D., Veloso, M.: Lazy incremental learning of control knowledge for efficiently obtaining quality plans. AI Review Journal. Special Issue on Lazy Learning 11(1-5), 371–405 (1997), also in: Aha, D. (ed.) Lazy Learning. Kluwer Academic Publishers, Dordrecht (1997)Google Scholar
  11. 11.
    Rodríguez-Moreno, M.D., Borrajo, D., Cesta, A., Oddi, A.: Integrating planning and scheduling in workflow domains. Expert System with Applications 33(2) (2007)Google Scholar
  12. 12.
    Veloso, M., Carbonell, J., Pérez, A., Borrajo, D., Fink, E., Blythe, J.: Integrating planning and learning: The PRODIGY architecture. Journal of Experimental and Theoretical AI 7, 81–120 (1995)zbMATHCrossRefGoogle Scholar
  13. 13.
    McCluskey, T.L., Porteous, J.M.: Engineering and compiling planning domain models to promote validity and efficiency. Artificial Intelligence 95(1), 1–65 (1997)zbMATHCrossRefGoogle Scholar
  14. 14.
    Fox, M., Long, D.: The automatic inference of state invariants in tim. Journal of Artificial Intelligence Research 9, 317–371 (1998)Google Scholar
  15. 15.
    Fox, M., Long, D.: PDDL2.1: An Extension to PDDL for Expressing Temporal Planning Domains. University of Durham, Durham (UK) (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Raquel Fuentetaja
    • 1
  • Daniel Borrajo
    • 1
  1. 1.Departamento de InformáticaUniversidad Carlos III de MadridLeganés (Madrid)Spain

Personalised recommendations