Teaching Randomized Learners

  • Frank J. Balbach
  • Thomas Zeugmann
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4005)


The present paper introduces a new model for teaching randomized learners. Our new model, though based on the classical teaching dimension model, allows to study the influence of various parameters such as the learner’s memory size, its ability to provide or to not provide feedback, and the influence of the order in which examples are presented. Furthermore, within the new model it is possible to investigate new aspects of teaching like teaching from positive data only or teaching with inconsistent teachers.

Furthermore, we provide characterization theorems for teachability from positive data for both ordinary teachers and inconsistent teachers with and without feedback.


Markov Decision Process Concept Class Teaching Process Public Output Positive Data 
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.
    Angluin, D.: Queries and concept learning. Machine Learning 2(4), 319–342 (1988)Google Scholar
  2. 2.
    Angluin, D.: Queries revisited. Theoret. Comput. Sci. 313(2), 175–194 (2004)CrossRefMathSciNetzbMATHGoogle Scholar
  3. 3.
    Angluin, D., Kriķis, M.: Teachers, learners and black boxes. In: Proc. of the 10th Annual Conference on Computational Learning Theory, pp. 285–297. ACM Press, New York (1997)Google Scholar
  4. 4.
    Angluin, D., Kriķis, M.: Learning from different teachers. Machine Learning 51(2), 137–163 (2003)Google Scholar
  5. 5.
    Anthony, M., Brightwell, G., Cohen, D., Shawe-Taylor, J.: On exact specification by examples. In: Proc. of the 5th Annual ACM Workshop on Computational Learning Theory, pp. 311–318. ACM Press, New York (1992)CrossRefGoogle Scholar
  6. 6.
    Bertsekas, D.P.: Dynamic Programming and Optimal Control. Athena ScientificGoogle Scholar
  7. 7.
    Feige, U.: A threshold of ln n for approximating set cover. J. of the ACM 45(4), 634–652 (1998)CrossRefMathSciNetzbMATHGoogle Scholar
  8. 8.
    Freivalds, R., Kinber, E.B., Wiehagen, R.: On the power of inductive inference from good examples. Theoret. Comput. Sci. 110(1), 131–144 (1993)CrossRefMathSciNetzbMATHGoogle Scholar
  9. 9.
    Goldman, S.A., Kearns, M.J.: On the complexity of teaching. J. Comput. Syst. Sci. 50(1), 20–31 (1995)CrossRefMathSciNetzbMATHGoogle Scholar
  10. 10.
    Goldman, S.A., Mathias, H.D.: Teaching a smarter learner. J. Comput. Syst. Sci. 52(2), 255–267 (1996)CrossRefMathSciNetGoogle Scholar
  11. 11.
    Goldman, S.A., Rivest, R.L., Schapire, R.E.: Learning binary relations and total orders. SIAM J. on Computing 22(5), 1006–1034 (1993)CrossRefMathSciNetzbMATHGoogle Scholar
  12. 12.
    Jackson, J., Tomkins, A.: A computational model of teaching. In: Proc. of the 5th Annual ACM Workshop on Computational Learning Theory, pp. 319–326. ACM Press, New York (1992)CrossRefGoogle Scholar
  13. 13.
    Jain, S., Lange, S., Nessel, J.: Learning of r.e. languages from good examples. In: Li, M. (ed.) ALT 1997. LNCS (LNAI), vol. 1316, pp. 32–47. Springer, Heidelberg (1997)Google Scholar
  14. 14.
    Madani, O., Hanks, S., Condon, A.: On the undecidability of probabilistic planning and infinite-horizon partially observable Markov decision problems. In: Proc. of the 16th National Conference on Artificial Intelligence and 11th Conference on Innovative Applications of Artificial Intelligence, pp. 541–548. AAAI Press/The MIT Press, Menlo Park (1999)Google Scholar
  15. 15.
    Mathias, H.D.: A model of interactive teaching. J. Comput. Syst. Sci. 54(3), 487–501 (1997)CrossRefMathSciNetzbMATHGoogle Scholar
  16. 16.
    Mundhenk, M., Goldsmith, J., Lusena, C., Allender, E.: Complexity of finite-horizon Markov decision process problems. J. of the ACM 47(4), 681–720 (2000)CrossRefMathSciNetGoogle Scholar
  17. 17.
    Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. John Wiley & Sons, Chichester (1994)zbMATHGoogle Scholar
  18. 18.
    Raz, R., Safra, S.: A sub-constant error-probability low-degree test, and a sub-constant error-probability PCP characterization of NP. In: Proc. of the 29th ACM Symposium on Theory of Computing, pp. 475–484 (1997)Google Scholar
  19. 19.
    Shinohara, A., Miyano, S.: Teachability in computational learning. New Generation Computing 8(4), 337–348 (1991)CrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Frank J. Balbach
    • 1
  • Thomas Zeugmann
    • 2
  1. 1.Institut für Theoretische InformatikUniversität zu LübeckLübeckGermany
  2. 2.Division of Computer ScienceHokkaido UniversitySapporoJapan

Personalised recommendations