Skip to main content

Coordination Developed by Learning from Evaluations

  • Chapter
Collaboration between Human and Artificial Societies

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 1624))

Abstract

This paper reports on research into the origins of communication and coordination. Several problems with defining communication and coordination are noted. A research methodology is described that circumvents these problems. The methodology is used in an experiment concerning the development of coordination. The aim of the experiment is to see whether a learning agent can use coordination signals, which represent evaluations of its behavior, to learn to coordinate its actions in an unknown environment. The task is a pursuit problem where four agents are needed to capture a randomly moving prey. One of these agents adapts its behavior based on the coordination signals it receives from the three other agents. The development of coordination increased the capture rate in this pursuit problem from an initial 5% to 93%. Thus, in combination with a general learning mechanism, coordination signals may be sufficient for the development of coordination.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

eBook
USD 16.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 16.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Benda, M., Jagannathan, V., Dodhiawalla, R.: On optimal cooperation of knowledge sources. Technical Report BCS-G2010-28, Boeing AI Center (1988)

    Google Scholar 

  2. Burghardt, G.M.: Defining ’communication’. In: Johnston, J., Moulton, D., Turk, A. (eds.) Communication by Chemical Signals, pp. 5–18. Appleton-Century-Crofts, New York (1970)

    Google Scholar 

  3. de Jong, E.D.: An accumulative exploration method for reinforcement learning. In: Proceedings of the AAAI 1997 Workshop on Multiagent Learning, available as AAAI Technical Report WS-97-03 (July 1997)

    Google Scholar 

  4. de Jong, E.D.: Multi-agent coordination by communication of evaluations. In: Boman, M., Van de Velde, W. (eds.) MAAMAW 1997. LNCS, vol. 1237. Springer, Heidelberg (1997)

    Google Scholar 

  5. de Jong, E.D., Vogt, P.: How Should a Robot Discriminate Between Objects? A comparison between two methods. In: Proceedings of the Fifth International Conference of The Society for Adaptive Behavior SAB 1988. vol. 5, The MIT Press, Cambridge (1998)

    Google Scholar 

  6. Di Paolo, E.A.: Social coordination and spatial organization: Steps towards the evolution of communication. In: Husbands, P., Harvey, I. (eds.) Proceedings of the 4th European Conference on Artificial Life ECAL 1997. The MIT Press/Bradford Books, Cambridge (1997)

    Google Scholar 

  7. Hauser, M.D.: The evolution of communication. The MIT Press, Cambridge (1997)

    Google Scholar 

  8. Kaplan, F.: A new approach to class formation in multi-agent simulations of language evolution. In: Proceedings of the Third International Conference on Multi Agent Systems ICMAS 1998. IEEE Computer Society Press, Los Alamitos (1998)

    Google Scholar 

  9. Kraus, S., Rosenschein, J.: The role of representation in interaction: Discovering focal points among alternative solutions. Decentralized Artificial Intelligence III (1992)

    Google Scholar 

  10. Fenster, S.K.M., Rosenschein, J.: Coordination without communication: Experimental validation of focal point techniques. In: Lesser, V. (ed.) Proceedings of the First International Conference on Multi-Agent Systems ICMAS 1995, pp. 12–14. AAAI Press/The MIT Press, Menlo Park (1995)

    Google Scholar 

  11. MacLennan, B.: Synthetic ethology: An approach to the study of communication. In: Langton, C.G., Taylor, C., Farmer, J., Rasmussen, S. (eds.) Artificial Life II, SFI Studies in the Sciences of Complexity, vol. X. Addison-Wesley, Reading (1991)

    Google Scholar 

  12. Ogden, C., Richards, I.: The Meaning of Meaning: a study of the influence of language upon thougth and of the science of symbolism. Routledge & Kegan Paul Ltd., London (1923)

    Google Scholar 

  13. Rumelhart, D., McClelland, J., et al.: Parallel distributed processing; explorations in the microstructure of cognition, vol. 1-2. The MIT Press, Cambridge (1987)

    Google Scholar 

  14. Seyfarth, R., Cheney, D., Marler, P.: Monkey responses to three different alarm calls: Evidence of predator classification and semantic communication. Science 210, 801–803 (1980)

    Article  Google Scholar 

  15. Shannon, C., Weaver, W.: The mathematical theory of communication. University of Illinois, Urbana (1949)

    Google Scholar 

  16. Steels, L.: The spontaneous self-organization of an adaptive language. In: Muggleton, S. (ed.) Machine Intelligence, vol. 15. Oxford University Press, Oxford (1996)

    Google Scholar 

  17. Steels, L.: Language learning and language contact. In: Daelemans, W., van den Bosch, A., Weijters, A. (eds.) Workshop Notes of the ECML/MLnet Familiarization Workshop on Empirical Learning of Natural Language Processing Tasks, pp. 11–24 (1997)

    Google Scholar 

  18. Steels, L., Vogt, P.: Grounding adaptive language games in robotic agents. In: Husbands, C., Harvey, I. (eds.) Proceedings of the Fourth European Conference on Artificial Life. The MIT Press, Cambridge MA and London (1997)

    Google Scholar 

  19. Stephens, L.M., Merx, M.B.: The effect of agent control strategy on the performance of a dai pursuit problem. In: Proceedings of the 1990 Distributed AI Workshop (1990)

    Google Scholar 

  20. Thrun, S.: The role of exploration in learning control. In: Handbook of Intelligent Control: Neural, Fuzzy and Adaptive Approaches, Van Nostrand Reinhold, Florence, Kentucky (1992)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 1999 Springer-Verlag Berlin Heidelberg

About this chapter

Cite this chapter

de Jong, E.D. (1999). Coordination Developed by Learning from Evaluations. In: Padget, J.A. (eds) Collaboration between Human and Artificial Societies. Lecture Notes in Computer Science(), vol 1624. Springer, Berlin, Heidelberg. https://doi.org/10.1007/10703260_14

Download citation

  • DOI: https://doi.org/10.1007/10703260_14

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-66930-2

  • Online ISBN: 978-3-540-46624-6

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics