Abstract
In recent years, the development of AI that plays Werewolf attracts attention. This study researches on Werewolf, which is an incomplete information game. In order to create a good game agent, we tried to get unknown information that makes us advantageous in the game. Since Werewolf is communication game, we assumed that there are common strategies or features. For learning such something from enormous game logs, we proposed using LSTM that is a kind of deep learning.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Suyama, J., Hashiyama, T., Tano, S.: Feature extraction from skilled player’s logs in PuyoPuyo. In: 31st Fuzzy System Symposium (2015)
Firoiu, V., Whitney, W.F., Tenenbaum, J.B.: Beating the world’s best at super smash bros. with deep reinforcement learning. Cornell University Library (2017)
Nakamura, N., Inaba, M., Takahashi, K., Shinoda, K.: Constructing a human-like agent for the werewolf game using a psychological model based multiple perspectives. In: The 2016 IEEE Symposium Series on Computational Intelligence (IEEE SSCI 2016) (2016)
Kaziwara, K., et al.: Development of AI wolf agent using SVM to detect werewolves. In: The 30th Annual Conference of the Japanese Society for Artificial Intelligence (2016)
Gers, F.A., Schmidhuber, J., Cummins, F.: Learning to forget: continual prediction with LSTM. Technical report IDSIA 01-99 (1999)
Kondoh, M., et al.: Agent of werewolf game applying deep learning predictions. In: The 6th Asian Conference on Information Systems (2017)
Toriumi, F., et al.: AI wolf contest-development of game AI using collective intelligence. In: Computer Games Workshop at IJCAI (2016)
Toriumi, F., et al.: Artificial Intelligence Based Werewolf Cheat, Penetrate, Persuade. Morikita Publishing Co., Ltd. (2016). (in Japanese)
Toriumi, F., et al.: Development of AI wolf server. In: The 19th Game Programming Workshop (2014)
Artificial intelligence based werewolf. http://aiwolf.org/
Zaremba, W.: Recurrent neural network regularization. In: Under Review as a Conference Paper at ICLR 2015 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Kondoh, M., Matsumoto, K., Mori, N. (2019). Development of Agent Predicting Werewolf with Deep Learning. In: De La Prieta, F., Omatu, S., Fernández-Caballero, A. (eds) Distributed Computing and Artificial Intelligence, 15th International Conference. DCAI 2018. Advances in Intelligent Systems and Computing, vol 800. Springer, Cham. https://doi.org/10.1007/978-3-319-94649-8_3
Download citation
DOI: https://doi.org/10.1007/978-3-319-94649-8_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-94648-1
Online ISBN: 978-3-319-94649-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)