TY - GEN
T1 - Constructing a Human-like agent for the Werewolf Game using a psychological model based multiple perspectives
AU - Nakamura, Noritsugu
AU - Inaba, Michimasa
AU - Takahashi, Kenichi
AU - Toriumi, Fujio
AU - Osawa, Hirotaka
AU - Katagami, Daisuke
AU - Shinoda, Kousuke
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2017/2/9
Y1 - 2017/2/9
N2 - In this paper, we focus on the Werewolf Game. The Werewolf Game is an advanced communication-game in which winning or losing is directly linked to one's success or failure in communication. Therefore, we expect exponential developments in artificial intelligence by studying the Werewolf Game. In this current study, we propose a psychological model that considers multiple perspectives to model the play of a human such as inferring the intention of the other side. As one of the psychological models, we constructed a 'one's self model' that models the role of others as viewed from their own viewpoint. In addition, to determine whether one's opinion is reliable after inferring other's intentions, we also constructed an 'others model' that models the role of others as viewed from their viewpoints. Combining these models, we showed through experimentation that a combined approach achieved better results, i.e., higher win percentages.
AB - In this paper, we focus on the Werewolf Game. The Werewolf Game is an advanced communication-game in which winning or losing is directly linked to one's success or failure in communication. Therefore, we expect exponential developments in artificial intelligence by studying the Werewolf Game. In this current study, we propose a psychological model that considers multiple perspectives to model the play of a human such as inferring the intention of the other side. As one of the psychological models, we constructed a 'one's self model' that models the role of others as viewed from their own viewpoint. In addition, to determine whether one's opinion is reliable after inferring other's intentions, we also constructed an 'others model' that models the role of others as viewed from their viewpoints. Combining these models, we showed through experimentation that a combined approach achieved better results, i.e., higher win percentages.
UR - http://www.scopus.com/inward/record.url?scp=85016046643&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85016046643&partnerID=8YFLogxK
U2 - 10.1109/SSCI.2016.7850031
DO - 10.1109/SSCI.2016.7850031
M3 - Conference contribution
AN - SCOPUS:85016046643
T3 - 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016
BT - 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016
Y2 - 6 December 2016 through 9 December 2016
ER -