Learning and Teaching as a Game: A Sabotage Approach

  • Nina Gierasimczuk
  • Lena Kurzen
  • Fernando R. Velázquez-Quesada
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5834)

Abstract

In formal approaches to inductive learning, the ability to learn is understood as the ability to single out a correct hypothesis from a range of possibilities. Although most of the existing research focuses on the characteristics of the learner, in many paradigms the significance of the teacher’s abilities and strategies is in fact undeniable. Motivated by this observation, this paper highlights the interactive nature of learning by showing its relation with games. We show how learning can be seen as a sabotage-type game between Teacher and Learner, and we present different variants based on the level of cooperativeness and the actions available to the players, characterizing the existence of winning strategies by formulas of Sabotage Modal Logic and analyzing their complexity. We also give a two-way conceptual account of how to further combine games and learning: we propose to use game theory to analyze the grammar inference approach, and moreover, we indicate that existing inductive inference games can be analyzed using learning theory tools. Our work aims at unifying game-theoretical and logical approach to formal learning theory.

Keywords

Formal learning theory game theory modal logic sabotage games inductive inference games learning algorithms 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Jain, S., Osherson, D., Royer, J.S., Sharma, A.: Systems that Learn. MIT Press, Chicago (1999)Google Scholar
  2. 2.
    Gold, E.: Language identification in the limit. Information and Control 10, 447–474 (1967)MathSciNetCrossRefMATHGoogle Scholar
  3. 3.
    van Ditmarsch, H., van der Hoek, W., Kooi, B.: Dynamic Epistemic Logic. Springer, Netherlands (2007)CrossRefMATHGoogle Scholar
  4. 4.
    Looney, A., Cooper, J., Heath, K., Davenport, J., Looney, K.: Playing with Pyramides. Looneylabs (1997)Google Scholar
  5. 5.
    Matuszek, D.: New eleusis (1995), http://matuszek.org/eleusis1.html
  6. 6.
    Angluin, D.: Learning regular sets from queries and counterexamples. Information and Computation 75(2), 87–106 (1987)MathSciNetCrossRefMATHGoogle Scholar
  7. 7.
    Löding, C., Rohde, P.: Solving the sabotage game is PSPACE-hard. In: Rovan, B., Vojtáš, P. (eds.) MFCS 2003. LNCS, vol. 2747, pp. 531–540. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  8. 8.
    van Benthem, J.: An essay on sabotage and obstruction. In: Mechanizing Mathematical Reasoning, Essays in Honor of Jörg H. Siekmann on the Occasion of His 60th Birthday, pp. 268–276 (2005)Google Scholar
  9. 9.
    Gierasimczuk, N., Kurzen, L., Velázquez-Quesada, F.R.: Games for learning: a sabotage approach (2008), http://www.illc.uva.nl/Publications/ResearchReports/PP-2009-30.text.pdf
  10. 10.
    Löding, C., Rohde, P.: Solving the sabotage game is PSPACE-hard. Technical report, Aachener Informatik Berichte, Rwth Aachen (2003)Google Scholar
  11. 11.
    Papadimitriou, C.M.: Computational complexity. Addison-Wesley, MA (1994)MATHGoogle Scholar
  12. 12.
    Dietterich, T.G.: Applying general induction methods to the card game eleusis. In: Proceedings of AAAI 1980, Stanford, CA, pp. 218–220 (1980)Google Scholar
  13. 13.
    Dietterich, T.G., Michalski, R.S.: Learning to predict sequences. In: Michalski, R., Carbonell, J., Mitchell, T. (eds.) Machine Learning: An Artificial Intelligence Approach, vol. II, pp. 63–106. Morgan Kaufmann Publishers, Los Altos (1986)Google Scholar
  14. 14.
    Klein, D., Radmacher, F.G., Thomas, W.: The complexity of reachability in randomized sabotage games. In: Proceedings of FSEN 2009. LNCS. Springer, Heidelberg (2009)Google Scholar
  15. 15.
    Scott, D., de Bakker, W.: A theory of programs. Unpublished manuscript, IBM, Vienna (1969)Google Scholar
  16. 16.
    Kozen, D.: Results on the propositional mu-calculus. Theoretical Computer Science 27, 333–354 (1983)MathSciNetCrossRefMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Nina Gierasimczuk
    • 1
  • Lena Kurzen
    • 1
  • Fernando R. Velázquez-Quesada
    • 1
  1. 1.Institute for Logic, Language and ComputationUniversiteit van AmsterdamAmsterdamthe Netherlands

Personalised recommendations