Skip to main content

Advertisement

SpringerLink
  • Log in
Book cover

Joint European Conference on Machine Learning and Knowledge Discovery in Databases

ECML PKDD 2011: Machine Learning and Knowledge Discovery in Databases pp 503–515Cite as

  1. Home
  2. Machine Learning and Knowledge Discovery in Databases
  3. Conference paper
Unsupervised Modeling of Partially Observable Environments

Unsupervised Modeling of Partially Observable Environments

  • Vincent Graziano23,
  • Jan Koutník23 &
  • Jürgen Schmidhuber23 
  • Conference paper
  • 2659 Accesses

  • 2 Citations

Part of the Lecture Notes in Computer Science book series (LNAI,volume 6911)

Abstract

We present an architecture based on self-organizing maps for learning a sensory layer in a learning system. The architecture, temporal network for transitions (TNT), enjoys the freedoms of unsupervised learning, works on-line, in non-episodic environments, is computationally light, and scales well. TNT generates a predictive model of its internal representation of the world, making planning methods available for both the exploitation and exploration of the environment. Experiments demonstrate that TNT learns nice representations of classical reinforcement learning mazes of varying size (up to 20×20) under conditions of high-noise and stochastic actions.

Keywords

  • Self-Organizing Maps
  • POMDPs
  • Reinforcement Learning

Download conference paper PDF

References

  1. Fernández, F., Borrajo, D.: Two steps reinforcement learning. International Journal of Intelligent Systems 23(2), 213–245 (2008)

    CrossRef  MATH  Google Scholar 

  2. Ferro, M., Ognibene, D., Pezzulo, G., Pirrelli, V.: Reading as active sensing: a computational model of gaze planning during word discrimination. Frontiers in Neurorobotics 4 (2010)

    Google Scholar 

  3. Fritzke, B.: A growing neural gas network learns topologies. In: Advances in Neural Information Processing Systems, vol. 7, pp. 625–632. MIT Press, Cambridge (1995)

    Google Scholar 

  4. Gisslén, L., Graziano, V., Luciw, M., Schmidhuber, J.: Sequential Constant Size Compressors and Reinforcement Learning. In: Proceedings of the Fourth Conference on Artificial General Intelligence (2011)

    Google Scholar 

  5. Kohonen, T.: Self-Organizing Maps, 3rd edn. Springer, Heidelberg (2001)

    CrossRef  MATH  Google Scholar 

  6. Koutník, J.: Inductive modelling of temporal sequences by means of self-organization. In: Proceeding of Internation Workshop on Inductive Modelling (IWIM 2007), pp. 269–277. CTU in Prague, Ljubljana (2007)

    Google Scholar 

  7. Koutník, J., Šnorek, M.: Temporal hebbian self-organizing map for sequences. In: ICANN 2006, vol. 1, pp. 632–641. Springer, Heidelberg (2008)

    Google Scholar 

  8. Lange, S., Riedmiller, M.: Deep auto-encoder neural networks in reinforcement learning. In: The 2010 International Joint Conference on Neural Networks (IJCNN), pp. 1–8 (July 2010)

    Google Scholar 

  9. Luciw, M., Graziano, V., Ring, M., Schmidhuber, J.: Artificial Curiosity with Planning for Autonomous Perceptual and Cognitive Development. In: Proceedings of the International Conference on Development and Learning (2011)

    Google Scholar 

  10. Marsland, S., Shapiro, J., Nehmzow, U.: A self-organising network that grows when required. Neural Netw. 15 (October 2002)

    Google Scholar 

  11. Provost, J.: Reinforcement Learning in High-Diameter, Continuous Environments. Ph.D. thesis, Computer Sciences Department, University of Texas at Austin, Austin, TX (2007)

    Google Scholar 

  12. Provost, J., Kuipers, B.J., Miikkulainen, R.: Developing navigation behavior through self-organizing distinctive state abstraction. Connection Science 18 (2006)

    Google Scholar 

  13. Schmidhuber, J.: Formal Theory of Creativity, Fun, and Intrinsic Motivation (1990–2010). IEEE Transactions on Autonomous Mental Development 2(3), 230–247 (2010)

    CrossRef  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. IDSIA, SUPSI, University of Lugano, Manno, CH-6928, Switzerland

    Vincent Graziano, Jan Koutník & Jürgen Schmidhuber

Authors
  1. Vincent Graziano
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jan Koutník
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jürgen Schmidhuber
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Department of Informatics and Telecommunications, University of Athens, Panepistimioupolis, Ilisia, 15784, Athens, Greece

    Dimitrios Gunopulos

  2. Google Switzerland GmbH, Brandschenkestrasse 110, 8002, Zurich, Switzerland

    Thomas Hofmann

  3. Department of Computer Science, University of Bari “Aldo Moro”, via Orabona 4, 70125, Bari, Italy

    Donato Malerba

  4. Deptartment of Informatics, Athens University of Economics and Business, Patision 76, 10434, Athens, Greece

    Michalis Vazirgiannis

Rights and permissions

Reprints and Permissions

Copyright information

© 2011 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Graziano, V., Koutník, J., Schmidhuber, J. (2011). Unsupervised Modeling of Partially Observable Environments. In: Gunopulos, D., Hofmann, T., Malerba, D., Vazirgiannis, M. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2011. Lecture Notes in Computer Science(), vol 6911. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23780-5_42

Download citation

  • .RIS
  • .ENW
  • .BIB
  • DOI: https://doi.org/10.1007/978-3-642-23780-5_42

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-23779-9

  • Online ISBN: 978-3-642-23780-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Share this paper

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

Over 10 million scientific documents at your fingertips

Switch Edition
  • Academic Edition
  • Corporate Edition
  • Home
  • Impressum
  • Legal information
  • Privacy statement
  • California Privacy Statement
  • How we use cookies
  • Manage cookies/Do not sell my data
  • Accessibility
  • FAQ
  • Contact us
  • Affiliate program

Not logged in - 44.200.168.16

Not affiliated

Springer Nature

© 2023 Springer Nature Switzerland AG. Part of Springer Nature.