Socionics pp 155-175 | Cite as

On the Organisation of Agent Experience: Scaling Up Social Cognition

  • Michael Rovatsos
  • Kai Paetow
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3413)


This paper introduces “micro-scalability” as a novel design objective for social reasoning architectures operating in open multiagent systems. Micro-scalability is based on the idea that social reasoning algorithms should be devised in a way that allows for social complexity reduction, and that this can be achieved by operationalising principles of interactionist sociology. We first present a formal model of InFFrA agents called m 2 InFFrA that utilises two cornerstones of micro-scalability, the principles of social abstraction and transient social optimality. Then, we exemplify the usefulness of these concepts by presenting experimental results with a novel opponent classification heuristic AdHoc that has been developed using the InFFrA social reasoning architecture. These results prove that micro-scalability deserves further investigation as a useful aspect of socionic research.


Social Cognition Multiagent System Markov Decision Process Agent Experience Opponent Model 
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.
    Fischer, F., Rovatsos, M.: An Empirical Semantics Approach to Reasoning About Communication. Engineering Applications of Artificial Intelligence 18 (2005) (to appear)Google Scholar
  2. 2.
    Fischer, F., Rovatsos, M., Weiß, G.: Acquiring and Adapting Probabilistic Models of Agent Conversations. In: Proceedings of the Fourth International Joint Conference on Agents and Multiagent Systems (AAMAS 2005), Utrecht, Netherlands (2005) (to appear)Google Scholar
  3. 3.
    Rovatsos, M.: Computational Interaction Frames. PhD thesis, Department of Informatics, Technical University of Munich (2004)Google Scholar
  4. 4.
    Malsch, T.: Naming the Unnamable: Socionics or the Sociological Turn of/to Distributed Artificial Intelligence. Autonomous Agents and Multi-Agent Systems 4, 155–186 (2001)CrossRefGoogle Scholar
  5. 5.
    Gasser, L.: Social conceptions of knowledge and action: DAI foundations and open systems semantics. Artificial Intelligence 47, 107–138 (1991)CrossRefMathSciNetGoogle Scholar
  6. 6.
    Hewitt, C.: Open information sytems semantics for distributed artificial intelligence. Artificial Intelligence 47, 79–106 (1991)CrossRefMathSciNetGoogle Scholar
  7. 7.
    Paetow, K., Schmitt, M., Malsch, T.: Scalability, Scaling Processes, and the Management of Complexity. a system theoretical approach. In: Fischer, K., Florian, M., Malsch, T. (eds.) Socionics. LNCS (LNAI), vol. 3413, pp. 132–154. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  8. 8.
    Luhmann, N.: Social Systems. Stanford University Press, Palo Alto (1995)Google Scholar
  9. 9.
    Blumer, H.: Society as Symbolic Interaction. In: Rose, A.M. (ed.) Human Behavior and Social Process, Routledge and Kegan Paul, London (1962)Google Scholar
  10. 10.
    Goffman, E.: Frame Analysis: An Essay on the Organisation of Experience. Harper and Row, New York (1974); Reprinted by Northeastern University PressGoogle Scholar
  11. 11.
    Mead, G.H.: Mind, Self, and Society. University of Chicago Press, Chicago (1934)Google Scholar
  12. 12.
    Nickles, M., Weiss, G.: Multiagent Systems without Agents – Mirror-Holons for the Compilcation and Enactment of Communication Structures. In: Fischer, K., Florian, M., Malsch, T. (eds.) Socionics. LNCS (LNAI), vol. 3413, pp. 263–288. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  13. 13.
    Paetow, K., Rovatsos, M.: Grundlagen einer interaktionistischen Sozionik (“Foundations of Interactionist Socionics”). Research Report RR-8, Department of Technology Assessment, Technical University of Hamburg, Hamburg (2003)Google Scholar
  14. 14.
    Rovatsos, M.: Interaction frames for artificial agents. Technical Report Research Report FKI-244-01, Department of Informatics, Technical University of Munich (2001)Google Scholar
  15. 15.
    Rovatsos, M., Weiß, G., Wolf, M.: Multiagent Learning for Open Systems: A Study in Opponent Classification. In: Alonso, E., Kazakov, D., Kudenko, D. (eds.) AAMAS 2000 and AAMAS 2002. LNCS (LNAI), vol. 2636. Springer, Hidelberg(2003)Google Scholar
  16. 16.
    Rao, A.S., Georgeff, M.P.: BDI agents: From theory to practice. In: Proceedings of the First International Conference on Multi-Agent Systems (ICMAS 1995), pp. 312–319 (1995)Google Scholar
  17. 17.
    Rovatsos, M., Nickles, M., Weiß, G.: Interaction is Meaning: A New Model for Communication in Open Systems. In: Rosenschein, J.S., Sandholm, T., Wooldridge, M., Yokoo, M. (eds.) Proceedings of the Second International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS 2003), Melbourne, Australia (2003)Google Scholar
  18. 18.
    Fischer, F.: Frame-Based Learning and Generalisation for Multiagent Communication. Diploma Thesis, Department of Informatics, Technical University of Munich, Munich, Germany (2003)Google Scholar
  19. 19.
    Nickles, M., Rovatsos, M.: Communication Systems: A Unified Model of Socially Intelligent Systems. In: Fischer, K., Florian, M., Malsch, T. (eds.) Socionics. LNCS (LNAI), vol. 3413, pp. 289–313. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  20. 20.
    Kolodner, J.L.: Case-Based Reasoning. Morgan Kaufmann, San Francisco (1993)Google Scholar
  21. 21.
    Puterman, M.L.: Markov Decision Problems. John Wiley & Sons, New York (1994)CrossRefGoogle Scholar
  22. 22.
    Sutton, R., Barto, A.: Reinforcement Learning. An Introduction. The MIT Press/A Bradford Book, Cambridge/MA (1998)Google Scholar
  23. 23.
    Barto, A., Mahadevan, S.: Recent Advances in Hierarchical Reinforcement Learning. Discrete Event Systems 13, 41–77 (2003)zbMATHCrossRefMathSciNetGoogle Scholar
  24. 24.
    Sutton, R.S., Precup, D., Singh, S.: Between MDPs and semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning. Artificial Intelligence 112, 181–211 (1999)zbMATHCrossRefMathSciNetGoogle Scholar
  25. 25.
    Watkins, C., Dayan, P.: Q-learning. Machine Learning 8, 279–292 (1992)zbMATHGoogle Scholar
  26. 26.
    Luce, R.D., Raiffa, H.: Games and Decisions. John Wiley & Sons, New York (1957)zbMATHGoogle Scholar
  27. 27.
    Carmel, D., Markovitch, S.: Learning and using opponent models in adversary search. Technical Report 9609, Technion (1996)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Michael Rovatsos
    • 1
  • Kai Paetow
    • 2
  1. 1.School of InformaticsThe University of EdinburghEdinburghUnited Kingdom
  2. 2.Department of Technology AssessmentTechnical University of HamburgHamburgGermany

Personalised recommendations