Latent Learning and Action Planning in Robots with Anticipatory Classifier Systems

  • Wolfgang Stolzmann
  • Martin Butz
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1813)


Two applications of Anticipatory Classifier Systems (ACS) in robotics are discussed. The first one is a simulation of an experiment about latent learning in rats with a mobile robot. It shows that an ACS is able to learn latently, i.e. in the absence of environmental reward and that ACS can do action planning. The second one is about learning of the hand-eye coordination of a robot arm in conjunction with a camera. Goal-directed learning will be introduced. This combination of action planning and latent learning leads to a substantial reduction of the number of trials which are required to learn a complete model of a prototypical environment.


Action Planning Mobile Robot Exploration Phase Learn Classifier System Latent Learning 
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.
    Birk, Andreas (1995). Stimulus Response Lernen. Dissertation. University of Saarbruecken. Germany.Google Scholar
  2. 2.
    Butz, M., Goldberg, D., & Stolzmann, W. (1999). New Challenges for an Anticipatory Classifier System: Some Hard Problems and Possible Solutions. IlliGAL Report No. 99019. Illinois Genetic Algorithms Laboratory, University of Illinois at Urbana-ChampaignGoogle Scholar
  3. 3.
    Croake, J. W. (1971). Unrewarded exploration and maze learning. Psychological Reports, 1971, 29, 1335–1340.Google Scholar
  4. 4.
    Hoffmann, Joachim (1993). Vorhersage und Erkenntnis. Göttingen: Hogrefe.Google Scholar
  5. 5.
    Michel, Olivier (1998). Webots-User Guide. Cyberbotics (
  6. 6.
    Riolo, Rick L. (1991). Lookahead planning and latent learning in a classifier system. In Meyer, J.A., and Wilson, S. W. (editors.). From Animals to Animats: Proceedings of the First International Conference on Simulation of Adaptive Behavior. Cambridge, MA: The MIT Press. 316–326.Google Scholar
  7. 7.
    Seward, John P. (1949). An Experimental Analysis of Latent Learning. Journal of Experimental Psychology. 39 177–186.CrossRefGoogle Scholar
  8. 8.
    Stolzmann, Wolfgang (1997). Antizipative Classifier Systeme-PhD Dissertation. Fachbereich Mathematik /Informatik. University of Osnabrueck. Aachen: Shaker Verlag.Google Scholar
  9. 9.
    Stolzmann, Wolfgang (1998). Anticipatory Classifier Systems. In Koza, John R. et al. (editors). Genetic Programming 1998: Proceedings of the Third Annual Conference, July 22–25, 1998, University of Wisconsin, Madison, Wisconsin. San Francisco, CA: Morgan Kaufmann. 658–664.Google Scholar
  10. 10.
    Stolzmann, Wolfgang (2000). An Introduction to Anticipatory Classifier Systems. In Lanzi, Stolzmann, Wilson Learning Classifier Systems: An Introduction to Contemporary Research. Pagg. 175–194. LNAI 1813. Springer, Berlin (This Volume)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Wolfgang Stolzmann
    • 1
  • Martin Butz
    • 1
  1. 1.Institute for PsychologyUniversity of WuerzburgGermany

Personalised recommendations