A Game-Based Competition as Instrument for Teaching Artificial Intelligence

  • Federico Chesani
  • Andrea Galassi
  • Paola MelloEmail author
  • Giada Trisolini
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10640)


This paper reports about teaching Artificial Intelligence (AI) by applying the experiential approach called “learning by doing”, where traditional, formal teaching is integrated with a practical activity (a game competition, in our case), that is relevant for AI discipline and allows for an active and playful participation of students.

Students of the course of Fundamentals of AI at the University of Bologna have been challenged (on a voluntary base) to develop an AI software able to play the game of Nine Men’s Morris: at the end of the course, the software players have been compared within a tournament, so as to establish the competition winner. The game has been chosen to let the students deepen the knowledge about AI techniques in solving games, and to apply it in a real, not trivial setting.

The significance and the impact of this approach, from the educational point of view, have been assessed through two questionnaires, a first one focused on the technical aspects, and a second one on the students’ opinions about the initiative. The results are encouraging: students declare they felt highly motivated in studying AI algorithms and techniques, and they have been stimulated in autonomously search for extensions and new solutions not deeply investigated during traditional lessons.



We would like to thank all the students who have participated to the competition, and whose names are available on the competition website. Moreover, we are especially grateful to those students who answered our questionnaires. We would like to thank also the reviewers for their helpful and detailed suggestions.


  1. 1.
    Allis, L.V., et al.: Searching for Solutions in Games and Artificial Intelligence. Ponsen & Looijen, Wageningen (1994)Google Scholar
  2. 2.
    Bell, R.C.: Board and Table Games from Many Civilizations, vol. 1. Courier Corporation, New York (1979)Google Scholar
  3. 3.
    Carpio Caada, J., Mateo Sanguino, T., Merelo Guervs, J., Rivas Santos, V.: Open classroom: enhancing student achievement on artificial intelligence through an international online competition. J. Comput. Assist. Learn. 31(1), 14–31 (2015).
  4. 4.
    Dewey, J.: How We Think. DC Heath, Lexington (1910)CrossRefGoogle Scholar
  5. 5.
    Galassi, A.: Symbolic versus sub-symbolic approaches: a case study on training Deep Networks to play Nine Men’s Morris game. Master’s thesis, University of Bologna, Italy.
  6. 6.
    Gasser, R.: Solving Nine Men’s Morris. Comput. Intell. 12(1), 24–41 (1996).
  7. 7.
    Gévay, G.E., Danner, G.: Calculating ultrastrong and extended solutions for Nine Men’s Morris, Morabaraba, and Lasker Morris. IEEE Trans. Comput. Intell. AI Games 8(3), 256–267 (2016)CrossRefGoogle Scholar
  8. 8.
    Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016).
  9. 9.
    Kaye, A.: Learning together apart. In: Kaye, A.R. (ed.) Collaborative Learning Through Computer Conferencing, vol. 90, pp. 1–24. Springer, Heidelberg (1992)CrossRefGoogle Scholar
  10. 10.
    Lave, J., Wenger, E.: Situated Learning: Legitimate Peripheral Participation. Cambridge University Press, Cambridge (1991)CrossRefGoogle Scholar
  11. 11.
    Petcu, S.A., Holban, S.: Nine Men’s Morris: evaluation functions. In: International Conferencs on Development and Application Systems, pp. 89–92 (2008)Google Scholar
  12. 12.
    Pumilia-Gnarini, P.M.: Handbook of Research on Didactic Strategies and Technologies for Education: Incorporating Advancements: Incorporating Advancements. IGI Global, Hershey (2012)Google Scholar
  13. 13.
    Reinefeld, A.: Spielbaum-Suchverfahren, vol. 200. Springer, Heidelberg (2013)zbMATHGoogle Scholar
  14. 14.
    Russell, S.J., Norvig, P.: Artificial Intelligence: A Modern Approach. Prentice-Hall, Inc., Upper Saddle River (2010)zbMATHGoogle Scholar
  15. 15.
    Rutko, D.: Fuzzified algorithm for game tree search. In: Second Brazilian Workshop of the Game Theory Society, BWGT (2010)Google Scholar
  16. 16.
    Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evol. Comput. 10(2), 99–127 (2002).
  17. 17.
    Togelius, J.: How to run a successful game-based AI competition. IEEE Trans. Comput. Intell. AI Games 8(1), 95–100 (2016)CrossRefGoogle Scholar
  18. 18.
    Vygotskij, L.S.: Myslenie i rec Psichologiceskie issledovanija. Movska-Leningrad: Gosudarstvennoe Socialno-Ekonomiceskoe Izdatelstvo (Bari, Laterza, It. tr. Pensiero e linguaggio 1992) (1934)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Federico Chesani
    • 1
  • Andrea Galassi
    • 1
  • Paola Mello
    • 1
    Email author
  • Giada Trisolini
    • 2
  1. 1.Department of Computer Science and Engineering (DISI)University of BolognaBolognaItaly
  2. 2.Department of Education Studies (EDU)University of BolognaBolognaItaly

Personalised recommendations