Informatik-Spektrum

, Volume 29, Issue 3, pp 175–190 | Cite as

Die Brainstormers: Entwurfsprinzipien lernfähiger autonomer Roboter

  • Martin Riedmiller
  • Thomas Gabel
  • Roland Hafner
  • Sascha Lange
  • Martin Lauer
HAUPTBEITRAG DIE BRAINSTORMERS

Zusammenfassung

Das “Brainstormers” Projekt wurde 1998 gestartet mit dem Ziel, lernfähige autonome Agenten in komplexen Umgebungen am Beispiel Roboterfußball zu erforschen. Dabei hat die Bearbeitung der vielfältigen Fragestellungen, die sich in dieser sehr dynamischen und verrauschten Umgebung ergeben, zu einer Vielzahl neuartiger Methoden und theoretischer Ergebnisse geführt.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bertsekas DP, Tsitsiklis J: Neuro-Dynamic Programming. Athena Scientific, 1996Google Scholar
  2. 2.
    Gabel T, Riedmiller M: Learning a partial behavior for a competitive robotic soccer agent. KI Zeitschrift, 2006Google Scholar
  3. 3.
    Hafner R, Riedmiller M: Reinforcement learning on an omnidirectional mobile robot. In: Proceedings of the 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003), Las Vegas, 2003Google Scholar
  4. 4.
    Hafner R, Riedmiller M: Neural RL controller for speed control of a real robot. Subitted to: Robotics Science and Systems (RSS 2006), 2006Google Scholar
  5. 5.
    Lauer M, Lange S, Riedmiller M: Calculating the perfect match: an efficient and accurate approach for robot self-localization. In: Robocup 2005, 2005Google Scholar
  6. 6.
    Lauer M, Lange S, Riedmiller M (2006) Motion estimation of moving objects for autonomous mobile robots. Künstliche Intelligenz 20(1):11–17Google Scholar
  7. 7.
    Lauer M, Riedmiller M: An algorithm for distributed reinforcement learning in cooperative multi-agent systems. In: Proceedings of International Conference on Machine Learning, ICML ’00, pp 535–542, Stanford, CA, 2000Google Scholar
  8. 8.
    Lauer M, Riedmiller M: Reinforcement learning for stochastic cooperative multi-agent systems. In: Proceedings of the AAMAS ’04, New York, 2004Google Scholar
  9. 9.
    Merke A, Riedmiller M: Karlsruhe Brainstormers – a reinforcement learning way to robotic soccer II. In: RoboCup-2001: Robot Soccer World Cup V, LNCS. Springer, 2001Google Scholar
  10. 10.
    Nardi D, Riedmiller M, Sammut C, Santos-Victor J (eds) RoboCup 2004: Robot Soccer World Cup VIII, vol 3276, 2005. ISBN 3-540-25046-8Google Scholar
  11. 11.
    Ng A, Harada D, Russell S: Policy invariance under reward transformations: Theory and application to reward shaping. In: Proceedings of the 16th International Conference on Machine Learning (ICML), Slovenia, 1999. Morgan KaufmannGoogle Scholar
  12. 12.
    Noda I, Matsubara H, Hiraki K, Frank I (1998) Soccer Server: A tool for research on multi-agent systems. Appl Artif Intell 12(2–3):233–250Google Scholar
  13. 13.
    Riedmiller M: Neural fitted Q iteration – first experiences with a data efficient neural reinforcement learning method. In: Machine Learning: ECML 2005, Porto, Portugal, 2005. SpringerGoogle Scholar
  14. 14.
    Sutton RS, Barto AG: Reinforcement Learning: An Introduction. MIT Press, Cambridge, MA, 1998Google Scholar
  15. 15.
    Withopf D, Riedmiller M (2005) Effective methods for reinforcement learning in large multi-agent domains. Inf Technol J 5(47):241–249Google Scholar

Copyright information

© Springer-Verlag 2006

Authors and Affiliations

  • Martin Riedmiller
    • 1
  • Thomas Gabel
    • 1
  • Roland Hafner
    • 1
  • Sascha Lange
    • 1
  • Martin Lauer
    • 1
  1. 1.Arbeitsgruppe NeuroinformatikUniversität OsnabrückOsnabrückDeutschland

Personalised recommendations