AI Wolf Contest — Development of Game AI Using Collective Intelligence —

  • Fujio ToriumiEmail author
  • Hirotaka Osawa
  • Michimasa Inaba
  • Daisuke Katagami
  • Kosuke Shinoda
  • Hitoshi Matsubara
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 705)


In this study, we specify the design of an artificial intelligence (AI) player for a communication game called “Are You a Werewolf?” (AI Wolf). We present the Werewolf game as a standard game problem in the AI field. It is similar to game problems such as Chess, Shogi, Go, and Poker. The Werewolf game is a communication game that requires several AI technologies such as multi-agent coordination, intentional reading, and understanding of the theory of mind. Analyzing and solving the Werewolf game as a standard problem will provide useful results for our research field and its applications. Similar to the RoboCup project, the goal of this project is to determine new themes while creating a communicative AI player that can play the Werewolf game with humans. As an initial step, we designed a platform to develop a game-playing AI for a competition. First, we discuss the essential factors in Werewolf with reference to other studies. We then develop a platform for an AI game competition that uses simplified rules to support the development of AIs that can play Werewolf. The paper reports the process and analysis of the results of the competition.


Artificial Intelligence Collective Intelligence Action Video Game Agent Game Artificial Intelligence Research 
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.



This work was partially supported by Hayao Nakayama Foundation for Science & Technology and Culture, Foundation for Fusion of Science and Technology, and JSPS KAKENHI Grant Number 26118006. We also want to say thanks for Computer Entertainment Developers Conference and Japan Society for Artificial Intelligence.


  1. 1.
    Silver, D., Huang, A., Maddison, C.J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., Dieleman, S., Grewe, D., Nham, J., Kalchbrenner, N., Sutskever, I., Lillicrap, T., Leach, M., Kavukcuoglu, K., Graepel, T., Hassabis, D.: Mastering the game of Go with deep neural networks and tree search. Nature 529, 484–489 (2016)CrossRefGoogle Scholar
  2. 2.
    Genesereth, M., Love, N., Pell, B.: General game playing: overview of the AAAI competition. AI Mag. 26, 1–16 (2005)Google Scholar
  3. 3.
    Bowling, M., Burch, N., Johanson, M., Tammelin, O.: Heads-up limit hold’em poker is solved. Science 347, 145–149 (2015)CrossRefGoogle Scholar
  4. 4.
    Karakovskiy, S., Togelius, J.: The Mario AI benchmark and competitions. IEEE Trans. Comput. Intell. AI Games 4, 55–67 (2012)CrossRefGoogle Scholar
  5. 5.
    Zinkevich, M.A., Bowling, M., Wunder, M.: The lemonade stand game competition. ACM SIGecom Exchanges 10, 35–38 (2011)CrossRefGoogle Scholar
  6. 6.
    ACPC: Computer Poker Competition.
  7. 7.
    Kitano, H., Asada, M., Kuniyoshi, Y., Noda, I., Osawa, E.: RoboCup: the robot world cup initiative. In: Proceedings of the First International Conference on Autonomous Agents - AGENTS 1997, pp. 340–347. ACM Press, New York (1997)Google Scholar
  8. 8.
    Abramson, B.: Control strategies for two-player games. ACM Comput. Surv. 21, 137–161 (1989)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Krawiec, K., Szubert, M.G.: Learning N-tuple networks for othello by coevolutionary gradient search. In: Proceedings of the 13th Annual Conference on Genetic and Evolutionary Computation - GECCO 2011, pp. 355–362. ACM Press, New York (2011)Google Scholar
  10. 10.
    Gelly, S., Kocsis, L., Schoenauer, M., Sebag, M., Silver, D., Szepesvári, C., Teytaud, O.: The grand challenge of computer Go. Commun. ACM 55, 106–113 (2012)CrossRefGoogle Scholar
  11. 11.
    Ganzfried, S., Sandholm, T.: Game theory-based opponent modeling in large imperfect-information games. In: International Conference on Autonomous Agents and Multiagent Systems, pp. 533–540. International Foundation for Autonomous Agents and Multiagent Systems (2011)Google Scholar
  12. 12.
    Billings, D., Burch, N., Davidson, A., Holte, R., Schaeffer, J., Schauenberg, T., Szafron, D.: Approximating game-theoretic optimal strategies for full-scale poker. In: International Joint Conference on Artificial Intelligence, pp. 661–668 (2003)Google Scholar
  13. 13.
    Ginsberg, M.L.: GIB: imperfect information in a computationally challenging game. J. Artif. Intell. Res. 14, 303–358 (2001)zbMATHGoogle Scholar
  14. 14.
    Whitehouse, D., Powley, E.J., Cowling, P.I.: Determinization and information set Monte Carlo tree search for the card game Dou Di Zhu. In: 2011 IEEE Conference on Computational Intelligence and Games (CIG 2011), pp. 87–94. IEEE (2011)Google Scholar
  15. 15.
    Inaba, M.I., Toriumi, F.U., Takahashi, K.E.: The statistical analysis of werewolf game data. In: Proceedings of Game Programming Workshop 2012, pp. 144–147 (2012) (in Japanese)Google Scholar
  16. 16.
    Dias, J., Reis, H., Paiva, A.: Lie to me: virtual agents that lie. In: Proceedings of the 2013 International Conference on Autonomous Agents and Multi-agent Systems, pp. 1211–1212 (2013)Google Scholar
  17. 17.
    Braverman, M., Etesami, O., Mossel, E.: Mafia: a theoretical study of players and coalitions in a partial information environment. Ann. Appl. Probab. 18, 825–846 (2008)MathSciNetCrossRefzbMATHGoogle Scholar
  18. 18.
    Yao, E.: A theoretical study of Mafia games (2008). Arxiv Prepr. arXiv:0804.0071
  19. 19.
    Chittaranjan, G., Hung, H.: Are you a werewolf? Detecting deceptive roles and outcomes in a conversational role-playing game. In: 2010 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 5334–5337. IEEE (2010)Google Scholar
  20. 20.
    Katagami, D., Kanazawa, M., Toriumi, F., Osawa, H., Inaba, M., Shinoda, K.: Movement design of a life-like agent for the werewolf game. In: IEEE International Conference on Fuzzy Systems, pp. 982–987 (2015)Google Scholar
  21. 21.
    Xia, F., Wang, H., Huang, J.: Deception detection via blob motion pattern analysis. In: Paiva, A.C.R., Prada, R., Picard, R.W. (eds.) ACII 2007 Proceedings of the 2nd International Conference on Affective Computing and Intelligent Interaction, pp. 727–728. Springer, Heidelberg (2007)Google Scholar
  22. 22.
    Zhou, L., Sung, Y.: Cues to deception in online chinese groups. In: Proceedings of the 41st Annual Hawaii International Conference on System Sciences (HICSS 2008), p. 146. IEEE (2008)Google Scholar
  23. 23.
    Aylett, R., Hall, L., Tazzyman, S., Endrass, B., André, E., Ritter, C., Nazir, A., Paiva, A., Höfstede, G., Kappas, A.: Werewolves, cheats, and cultural sensitivity. In: Autonomous Agents and Multi-Agent Systems, pp. 1085–1092. International Foundation for Autonomous Agents and Multiagent Systems (2014)Google Scholar
  24. 24.
    White, M., Bowling, M.: Learning a value analysis tool for agent evaluation. In: IJCAI 2009 Proceedings of the 21st International Joint Conference on Artificial Intelligence, pp. 1976–1981 (2009)Google Scholar
  25. 25.
    Davidson, J., Archibald, C., Bowling, M.: Baseline: practical control variates for agent evaluation in zero-sum domains. In: Proceedings of the 2013 International Conference on Autonomous Agents and Multi-agent Systems, pp. 1005–1012 (2013)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Fujio Toriumi
    • 1
    Email author
  • Hirotaka Osawa
    • 2
  • Michimasa Inaba
    • 3
  • Daisuke Katagami
    • 4
  • Kosuke Shinoda
    • 5
  • Hitoshi Matsubara
    • 6
  1. 1.The University of TokyoTokyoJapan
  2. 2.University of TsukubaTsukubaJapan
  3. 3.Hiroshima City UniversityHiroshimaJapan
  4. 4.Tokyo Polytechnic UniversityTokyoJapan
  5. 5.The University of Electro-CommunicationsChofuJapan
  6. 6.Future University HakodateHakodateJapan

Personalised recommendations