How Game Complexity Affects the Playing Behavior of Synthetic Agents

  • Chairi KiourtEmail author
  • Dimitris Kalles
  • Panagiotis Kanellopoulos
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10767)


Agent based simulation of social organizations, via the investigation of agents’ training and learning tactics and strategies, has been inspired by the ability of humans to learn from social environments which are rich in agents, interactions and partial or hidden information. Such richness is a source of complexity that an effective learner has to be able to navigate. This paper focuses on the investigation of the impact of the environmental complexity on the game playing-and-learning behavior of synthetic agents. We demonstrate our approach using two independent turn-based zero-sum games as the basis of forming social events which are characterized both by competition and cooperation. The paper’s key highlight is that as the complexity of a social environment changes, an effective player has to adapt its learning and playing profile to maintain a given performance profile.


Board games Playing behaviors Multi-agent systems Game complexity Social events 


  1. 1.
    Ferber, J., Gutknecht, O., Michel, F.: From agents to organizations: an organizational view of multi-agent systems. In: Giorgini, P., Müller, J.P., Odell, J. (eds.) AOSE 2003. LNCS, vol. 2935, pp. 214–230. Springer, Heidelberg (2004). Scholar
  2. 2.
    Shoham, Y., Leyton-Brown, K.: Multiagent Systems: Algorithmic, Game-Theoretic, and Logical Foundations. Cambridge University Press, Cambridge (2008)CrossRefGoogle Scholar
  3. 3.
    Wooldridge, M.: An Introduction to MultiAgent Systems, 2nd edn. Wiley Publishing, Hoboken (2009)Google Scholar
  4. 4.
    Ferber, J.: Multi-Agent Systems: An Introduction to Distributed Artificial Intelligence. Addison-Wesley/Longman Publishing, Boston/Harlow (1999)Google Scholar
  5. 5.
    Kiourt, C., Kalles, D.: Synthetic learning agents in game-playing social environments. Adapt. Behav. 24(6), 411–427 (2016)CrossRefGoogle Scholar
  6. 6.
    Marom, Y., Maistros, G., Hayes, G.: Experiments with a social learning model. Adapt. Behav. 9(3–4), 209–240 (2001)CrossRefGoogle Scholar
  7. 7.
    Al-Khateeb, B., Kendall, G.: Introducing a round robin tournament into evolutionary individual and social learning checkers. In: Proceedings of the Developments in E-systems Engineering (DeSE), pp. 294–299 (2011)Google Scholar
  8. 8.
    Caballero, A., Botía, J., Gómez-Skarmeta, A.: Using cognitive agents in social simulations. Eng. Appl. Artif. Intell. 24, 1098–1109 (2011)CrossRefGoogle Scholar
  9. 9.
    Gilbert, N., Troitzsch, K.G.: Simulation for the Social Scientist. Open University Press, Buckingham (2005)Google Scholar
  10. 10.
    Kiourt, C., Kalles, D.: Using opponent models to train inexperienced synthetic agents in social environments. In: Proceedings of the 2016 IEEE Conference on Computational Intelligence and Games (CIG), pp. 1–4 (2016)Google Scholar
  11. 11.
    Kiourt, C., Kalles, D.: Learning in multi agent social environments with opponent models. In: Rovatsos, M., Vouros, G., Julian, V. (eds.) EUMAS/AT -2015. LNCS (LNAI), vol. 9571, pp. 137–144. Springer, Cham (2016). Scholar
  12. 12.
    Allis, L. V.: Knowledge-based approach of connect four: The game is over, white to move wins. Master’s thesis, Vrije Universiteit (1988)Google Scholar
  13. 13.
    Allis, L. V.: Searching for Solutions in Games and Artificial Intelligence. PhD thesis, Maastricht University (1994)Google Scholar
  14. 14.
    van den Herik, H., Uiterwijk, J.W., van Rijswijck, J.: Games solved: now and in the future. Artif. Intell. 134(1), 277–311 (2002)CrossRefGoogle Scholar
  15. 15.
    Heule, M., Rothkrantz, L.: Solving games. Sci. Comput. Program. 67(1), 105–124 (2007)CrossRefGoogle Scholar
  16. 16.
    Edelkamp, S., Kissmann, P.: Symbolic classification of general two-player games. In: Dengel, A.R., Berns, K., Breuel, T.M., Bomarius, F., Roth-Berghofer, T.R. (eds.) KI 2008. LNCS (LNAI), vol. 5243, pp. 185–192. Springer, Heidelberg (2008). Scholar
  17. 17.
    Kalles, D., Kanellopoulos, P.: On verifying game designs and playing strategies using reinforcement learning. In: Proceedings of the 2001 ACM Symposium on Applied Computing (SAC), pp. 6–11 (2001)Google Scholar
  18. 18.
    Tesauro, G.: Practical issues in temporal difference learning. Mach. Learn. 8, 257–277 (1992)zbMATHGoogle Scholar
  19. 19.
    Tesauro, G.: Temporal difference learning and TD-Gammon. Commun. ACM 38, 58–68 (1995)CrossRefGoogle Scholar
  20. 20.
    Sutton, R.S., Barto, A.G.: Introduction to Reinforcement Learning. MIT Press, Cambridge (1998)Google Scholar
  21. 21.
    March, J.G.: Exploration and exploitation in organizational learning. Organ. Sci. 2, 71–87 (1991)CrossRefGoogle Scholar
  22. 22.
    Tromp, J.: Solving connect-4 on medium board sizes. ICGA J. 31(1), 110–112 (2008)CrossRefGoogle Scholar
  23. 23.
    Tromp, J.: John’s connect four playground. Accessed 27 Oct 2017
  24. 24.
    Sutton, R.S.: Learning to predict by the methods of temporal differences. Mach. Learn. 3, 9–44 (1988)Google Scholar
  25. 25.
    Wiering, M. A., Patist, J. P., Mannen, H.: Learning to play board games using temporal difference methods. Technical report: UU-CS-2005-048 (2005)Google Scholar
  26. 26.
    Kiourt, C., Pavlidis, G., Kalles, D.: Reskill: relative skill-level calculation system. In: Proceedings of the 9th Hellenic Conference on Artificial Intelligence (SETN), pp. 39:1–39:4 (2016)Google Scholar
  27. 27.
    Spearman, C.: The proof and measurement of association between two things. Am. J. Psychol. 15(1), 70–101 (1904)CrossRefGoogle Scholar
  28. 28.
    Kendall, M.: A new measure of rank correlation. Biometrica 30(1–2), 81–93 (1936)zbMATHGoogle Scholar
  29. 29.
    Langville, N., Meyer, C.: Who’s #1?: The Science of Rating and Ranking. Princeton University Press, Princeton (2012)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.School of Science and TechnologyHellenic Open UniversityPatrasGreece
  2. 2.CTI “Diophantus” and University of PatrasRionGreece

Personalised recommendations