MASIVE: A Case Study in Multiagent Systems

  • Goran Trajkovski
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2412)


The project MASIVE (Multi-Agent Systems Interactive Virtual Environments) is the multi-agent extension of our Interactivist-Expectative Theory on Agency and Learning (IETAL). The agents in the environment learn expectations from their interactions with the environment. In addition to that, they are equipped with special sensors for sensing akin agents, and interchange their knowledge of the environment (their intrinsic representations) during their imitation conventions. In this paper we discuss the basics of the theory, and the social consequences of such an environment from the perspective of learning, knowledge dissemination, and emergence of language.


Contingency Table Multiagent System Emotional Context Active Drive Information Interchange 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bozinovski, S., Stojanov, G., Bozinovska L., “Emotion, Embodiment, and Consequence Driven Systems”, 1996 AAAI Fall Symposium, FS-96-02 (1996) 12–17.Google Scholar
  2. 2.
    Byrne R.W.„ Russon, A.E. “ Learning by Imitation”, Behavioral and Brain Sciences (2001).Google Scholar
  3. 3.
    Ferber, J: Multi-Agent Systems: An Introduction to Distributed Artificial Intelligence, Addison-Wesley, 1999.Google Scholar
  4. 4.
    Nehaniv, C., Dautenhahn, K. Mapping between dissimilar bodies: Affordances and the algebraic foundations of imitation. Proceedings of the Seventh European Workshop on Learning Robots Edinburgh, UK (1998) pp. 64–72.Google Scholar
  5. 5.
    Piaget, J Play, Dreams, and Imitation in Childhood. New York: Norton,. 1945.Google Scholar
  6. 6.
    Rizzolatti G, Fadiga L, Gallese V, Fogassi L, Premotor cortex and the recognition of motor actions. Cognitive Brain Research, 3(2) (1996) 131–141CrossRefGoogle Scholar
  7. 7.
    Stojanov, G., Bozinovski S., Trajkovski, G “Interactionist-Expectative View on Agency and Learning”, IMACS Journal for Mathematics and Computers in Simulation, North-Holland Publishers, Amsterdam, Vol. 44 (1997).Google Scholar
  8. 8.
    Stojanov, G., Trajkovski, G., Bozinovski, S. “The Status of Representation in Behavior Based Robotic Systems: The Problem and A Solution”, IEEE Conference Systems, Man, and Cybernetics, Orlando (1997).Google Scholar
  9. 9.
    Thorndike, E.L. “Animal intelligence: an experimental study of the associative process in animals” Psychological Review Monograph 2(8) (1898) 551–553.CrossRefGoogle Scholar
  10. 10.
    Trajkovski, G., Stojanov, G., ”Algebraic Formalization of Environment Representation“, in (Tatai, G., Gulyas, L. (eds)) Agents Everywhere, Springer, Budapest, HU (1998) 59–65.Google Scholar
  11. 11.
    Trajkovski, G., Goode, M., Chapman, J., Swearingen, W., “Investigating Learning in Human Agents: The POPSICLE experiment”, KES 2002, Crema, IT (to appear).Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Goran Trajkovski
    • 1
  1. 1.Towson UniversityTowsonUSA

Personalised recommendations