Teamwork pp 236-251 | Cite as

Learning in Robot Teams

  • Jeremy Wyatt
  • Yoshiyuki Matsumura
  • Matthew Todd

Abstract

Robots are most likely to be useful to us when they can work with both humans and other robots. Robots that work in teams pose many challenges for engineers. How should robots communicate with one another and with humans; how can they represent and share beliefs about an uncertain and changing world, or indeed about the beliefs of other agents; how should tasks be divided among team members; how much information about the actions of other team members do robots need to act usefully within the team?

Keywords

Arena 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Dario Floreano, Stefano Nolfi and Francesco Mondada (1998) ‘Competitive Coevolutionary robotics: from theory to practice’ in R. Pfeifer (ed.) From Animals to Animats V: Proceedings of the Fifth International Conference on Simulation of Adaptive Behavior (Cambridge, Ma.: MIT Press-Bradford Books).Google Scholar
  2. David Goldberg (1989) Genetic Algorithms in Search, Optimisation and Machine Learning (Reading Ma.: Addison Wesley).Google Scholar
  3. Kevin Gurney (1997) Introduction to Neural Networks (London: UCL Press).CrossRefGoogle Scholar
  4. Yoshiyuki Matsumura, Kazuhiro Ohkura and Kanji Ueda (2002) ‘Robust Evolutionary Programming Applied to Artificial Neural Networks’ Proceedings of 4th Asia Pacific Conference on Simulated Evolution and Learning (SEAL 02), pp. 345–349.Google Scholar
  5. John Maynard Smith (1982) Evolution and the Theory of Games (Cambridge: Cambridge University Press).CrossRefGoogle Scholar
  6. Tom Mitchell (1997) Machine Learning (New York: McGraw Hill).Google Scholar
  7. R. B. Myerson (1991) Game Theory: Analysis of Conflict (Cambridge, Ma.: Harvard University Press).Google Scholar
  8. Elliott Sober and David Sloan Wilson (1998) Unto Others: The Evolution and Psychology of Unselfish Behaviour (Cambridge Ma.: Harvard University Press).Google Scholar
  9. Richard Sutton and Andrew Barto (1990) ‘Time Derivative Models of Pavlovian Reinforcement’ in M. Gabriel and J. Moore (eds) Learning and Computational Neuroscience: Foundations of Adaptive Networks, pp. 497–537 (Cambridge Ma.: MIT Press).Google Scholar
  10. Richard Sutton and Andrew Barto (1998) Reinforcement Learning: An Introduction (Cambridge, Ma.: MIT Press/Bradford Books).Google Scholar
  11. Peter Stone (2000) Layered Learning in Multiagent Systems: A Winning Approach to Robotic Soccer (Cambridge, Ma.: MIT Press).Google Scholar
  12. Matthew Todd (1999) Multi-agent Learning, unpublished BSc Thesis, School of Computer Science, University of Birmingham.Google Scholar

Copyright information

© Jeremy Wyatt, Yoshiyuki Matsumura and Matthew Todd 2005

Authors and Affiliations

  • Jeremy Wyatt
  • Yoshiyuki Matsumura
  • Matthew Todd

There are no affiliations available

Personalised recommendations