Skip to main content

Autonomous Shaping via Coevolutionary Selection of Training Experience

  • Conference paper
  • 1530 Accesses

Part of the Lecture Notes in Computer Science book series (LNTCS,volume 7492)

Abstract

To acquire expert skills in a sequential decision making domain that is too vast to be explored thoroughly, an intelligent agent has to be capable of inducing crucial knowledge from the most representative parts of it. One way to shape the learning process and guide the learner in the right direction is effective selection of such parts that provide the best training experience. To realize this concept, we propose a shaping method that orchestrates the training by iteratively exposing the learner to subproblems generated autonomously from the original problem. The main novelty of the proposed approach consists in equalling the learning process with the search in subproblem space and in employing a coevolutionary algorithm to perform this search. Each individual in the population encodes a sequence of subproblems that is evaluated by confronting the learner trained on it with other learners shaped in this way by particular individuals. When applied to the game of Othello, temporal difference learning on the best found subproblem sequence yields substantially better players than learning on the entire problem at once.

Keywords

  • reinforcement learning
  • coevolutionary algorithms
  • shaping

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-642-32964-7_22
  • Chapter length: 10 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   84.99
Price excludes VAT (USA)
  • ISBN: 978-3-642-32964-7
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   107.00
Price excludes VAT (USA)

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. The MIT Press (1998)

    Google Scholar 

  2. Skinner, B.: The behavior of organisms: An experimental analysis. Appleton-Century (1938)

    Google Scholar 

  3. Randløv, J., Alstrøm, P.: Learning to drive a bicycle using reinforcement learning and shaping. In: Proceedings of the Fifteenth International Conference on Machine Learning, pp. 463–471. Morgan Kaufmann, San Francisco (1998)

    Google Scholar 

  4. Popovici, E., Bucci, A., Wiegand, R.P., de Jong, E.D.: Coevolutionary principles. In: Handbook of Natural Computing. Springer, Berlin (2010)

    Google Scholar 

  5. Jaśkowski, W., Krawiec, K.: Formal analysis, hardness and algorithms for extracting internal structure of test-based problems. Evolutionary Computation 19(4), 639–671 (2011)

    CrossRef  Google Scholar 

  6. Szubert, M.: cECJ — Coevolutionary Computation in Java (2010), http://www.cs.put.poznan.pl/mszubert/projects/cecj.html

  7. Sutton, R.S.: Learning to predict by the methods of temporal differences. Machine Learning 3, 9–44 (1988)

    Google Scholar 

  8. Szubert, M., Jaśkowski, W., Krawiec, K.: Coevolutionary Temporal Difference Learning for Othello. In: 2009 IEEE Symposium on Computational Intelligence and Games, pp. 104–111 (2009)

    Google Scholar 

  9. Mihalkova, L., Mooney, R.: Using active relocation to aid reinforcement learning. In: Proceedings of the 19th International FLAIRS Conference, pp. 580–585 (2006)

    Google Scholar 

  10. Cohn, D., Atlas, L., Ladner, R.: Improving generalization with active learning. Machine Learning 15(2), 201–221 (1994)

    Google Scholar 

  11. Rachelson, E., Schnitzler, F., Wehenkel, L., Ernst, D.: Optimal sample selection for batch-mode reinforcement learning. In: Proceedings of the 3rd International Conference on Agents and Artificial Intelligence, ICAART 2011 (2011)

    Google Scholar 

  12. Torrey, L., Shavlik, J.: Transfer Learning. In: Handbook of Research on Machine Learning Applications and Trends: Algorithms, Methods, and Techniques, pp. 242–264. IGI Global (2009)

    Google Scholar 

  13. Konidaris, G., Barto, A.: Autonomous shaping: Knowledge transfer in reinforcement learning. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 489–496. ACM (2006)

    Google Scholar 

  14. Epstein, S.: Toward an ideal trainer. Machine Learning 15(3), 251–277 (1994)

    MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2012 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Szubert, M., Krawiec, K. (2012). Autonomous Shaping via Coevolutionary Selection of Training Experience. In: Coello, C.A.C., Cutello, V., Deb, K., Forrest, S., Nicosia, G., Pavone, M. (eds) Parallel Problem Solving from Nature - PPSN XII. PPSN 2012. Lecture Notes in Computer Science, vol 7492. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32964-7_22

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-32964-7_22

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-32963-0

  • Online ISBN: 978-3-642-32964-7

  • eBook Packages: Computer ScienceComputer Science (R0)