International Workshop on Logic, Rationality and Interaction

Logic, Rationality, and Interaction pp 40-52 | Cite as

Learning Actions Models: Qualitative Approach

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9394)

Abstract

In dynamic epistemic logic, actions are described using action models. In this paper we introduce a framework for studying learnability of action models from observations. We present first results concerning propositional action models. First we check two basic learnability criteria: finite identifiability (conclusively inferring the appropriate action model in finite time) and identifiability in the limit (inconclusive convergence to the right action model). We show that deterministic actions are finitely identifiable, while non-deterministic actions require more learning power—they are identifiable in the limit. We then move on to a particular learning method, which proceeds via restriction of a space of events within a learning-specific action model. This way of learning closely resembles the well-known update method from dynamic epistemic logic. We introduce several different learning methods suited for finite identifiability of particular types of deterministic actions.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Andersen, M.B., Bolander, T., Jensen, M.H.: Conditional epistemic planning. In: del Cerro, L.F., Herzig, A., Mengin, J. (eds.) JELIA 2012. LNCS, vol. 7519, pp. 94–106. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  2. 2.
    Angluin, D.: Inductive inference of formal languages from positive data. Information and Control 45(2), 117–135 (1980)MathSciNetCrossRefMATHGoogle Scholar
  3. 3.
    Baltag, A., Gierasimczuk, N., Smets, S.: Belief revision as a truth-tracking process. In: Apt, K. (ed.) TARK 2011: Proceedings of the 13th Conference on Theoretical Aspects of Rationality and Knowledge, pp. 187–190. ACM (2011)Google Scholar
  4. 4.
    Baltag, A., Gierasimczuk, N., Smets, S.: Truth tracking by belief revision. ILLC Prepublication Series PP-2014-20 (to appear in Studia Logica 2015) (2014)Google Scholar
  5. 5.
    Baltag, A., Gierasimczuk, N., Smets, S.: On the solvability of inductive problems: A study in epistemic topology. ILLC Prepublication Series PP-2015-13 (to appear in Proceedings of TARK 2015) (2015)Google Scholar
  6. 6.
    Baltag, A., Moss, L.S., Solecki, S.: The logic of public announcements and common knowledge and private suspicions. In: Gilboa, I. (ed.) TARK 1998: Proceedings of the 7th Conference on Theoretical Aspects of Rationality and Knowledge, pp. 43–56. Morgan Kaufmann (1998)Google Scholar
  7. 7.
    Bolander, T., Andersen, M.B.: Epistemic planning for single- and multi-agent systems. Journal of Applied Non-Classical Logics 21, 9–34 (2011)MathSciNetCrossRefMATHGoogle Scholar
  8. 8.
    van Ditmarsch, H., Kooi, B.: Semantic results for ontic and epistemic change. In: Bonanno, G., van der Hoek, W., Wooldridge, M. (eds.) LOFT 7: Logic and the Foundation of Game and Decision Theory. Texts in Logic and Games, vol. 3, pp. 87–117. Amsterdam University Press (2008)Google Scholar
  9. 9.
    Ghallab, M., Nau, D.S., Traverso, P.: Automated Planning: Theory and Practice. Morgan Kaufmann (2004)Google Scholar
  10. 10.
    Gierasimczuk, N.: Learning by erasing in dynamic epistemic logic. In: Dediu, A.H., Ionescu, A.M., Martín-Vide, C. (eds.) LATA 2009. LNCS, vol. 5457, pp. 362–373. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  11. 11.
    Gierasimczuk, N.: Knowing One’s Limits. Logical Analysis of Inductive Inference. Ph.D. thesis, Universiteit van Amsterdam, The Netherlands (2010)Google Scholar
  12. 12.
    Gierasimczuk, N., de Jongh, D., Hendricks, V.F.: Logic and learning. In: Baltag, A., Smets, S. (eds.) Johan van Benthem on Logical and Informational Dynamics. Springer (2014)Google Scholar
  13. 13.
    Gierasimczuk, N., de Jongh, D.: On the complexity of conclusive update. The Computer Journal 56(3), 365–377 (2013)CrossRefGoogle Scholar
  14. 14.
    Lange, S., Zeugmann, T.: Types of monotonic language learning and their characterization. In: COLT 1992: Proceedings of the 5th Annual ACM Conference on Computational Learning Theory, pp. 377–390. ACM (1992)Google Scholar
  15. 15.
    Mukouchi, Y.: Characterization of finite identification. In: Jantke, K.P. (ed.) AII 1992. LNCS, vol. 642, pp. 260–267. Springer, Heidelberg (1992)CrossRefGoogle Scholar
  16. 16.
    Sadzik, T.: Exploring the Iterated Update Universe, ILLC Prepublications PP-2006-26 (2006)Google Scholar
  17. 17.
    Sietsma, F., van Eijck, J.: Action emulation between canonical models. Journal of Philosophical Logic 42(6), 905–925 (2013)MathSciNetCrossRefMATHGoogle Scholar
  18. 18.
    Walsh, T.J., Littman, M.L.: Efficient learning of action schemas and web-service descriptions. In: AAAI 2008: Proceedings of the 23rd National Conference on Artificial Intelligence, vol. 2, pp. 714–719. AAAI Press (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2015

Authors and Affiliations

  1. 1.DTU ComputeTechnology University of DenmarkCopenhagenDenmark
  2. 2.ILLCUniversity of AmsterdamAmsterdamThe Netherlands

Personalised recommendations