- Quentin Gendre and Tomoyuki Kaneko.
Playing Catan with Cross-dimensional Neural Network. ICONIP. LNCS, 2020 (to appear)

(also available as Arxiv abs/2008.07079)

- Quentin Gendre and Tomoyuki Kaneko. Playing Catan with Cross-dimensional Neural Network. ICONIP. 2020 (to appear)
- Tomoyuki Kaneko and Takenobu Takizawa. Computer Shogi Tournaments and Techniques. IEEE Transactions on Games, 11(3), pp. 267--274, 2019. doi: 10.1109/TG.2019.2939259
- Yusaku Mandai and Tomoyuki Kaneko. RankNet for evaluation functions of the game of Go. ICGA Journal 41(2): 78-91 (2019), doi:10.3233/ICG-190108
- Yuji Kanagawa and Tomoyuki Kaneko. Rogue-Gym: A New Challenge for Generalization in Reinforcement Learning. IEEE Conference on Games (CoG) DOI: 10.1109/CIG.2019.8848075 (also available as Arxiv abs/1904.08129) (2019)
- Hanhua Zhu and Tomoyuki Kaneko. Deep Residual Attention Reinforcement Learning. International Conference on Technologies and Applications of Artificial Intelligence, 2019, pp. 1-6. (DOI: 10.1109/TAAI48200.2019.8959896) (Excellent Paper Award)
- Zhejie Hu and Tomoyuki Kaneko Application of Deep-RL with Sample-Efficient Method in Mini-games of StarCraft II. International Conference on Technologies and Applications of Artificial Intelligence, 2019, pp. 1-6. (DOI: 10.1109/TAAI48200.2019.8959866)
- Chen Chen and Tomoyuki Kaneko Acquiring Strategies for the Board Game Geister by Regret Minimization. International Conference on Technologies and Applications of Artificial Intelligence, 2019, pp. 1-6. (DOI: 10.1109/TAAI48200.2019.8959878)
- Shanchuan Wan and Tomoyuki Kaneko. Heterogeneous Multi-Task Learning of Evaluation Functions for Chess and Shogi. ICONIP 2018, pp. 347--358 (DOI 10.1007/978-3-030-04182-3_31)
- Shanchuan Wan and Tomoyuki Kaneko. Building Evaluation Functions for Chess and Shogi with Uniformity Regularization Networks. IEEE Conference on Computational Intelligence and Games 2018, pp. 70--77. doi: 10.1109/CIG.2018.8490455
- Yusaku Mandai and Tomoyuki Kaneko. An Alternative Multitask Training for Evaluation Functions in the Game of Go. IEEE Technologies and Applications of Artificial Intelligence, Taiwan, 2018, pp. 132--135 (DOI 10.1109/TAAI.2018.00037)
- Taichi Nakayashiki and Tomoyuki Kaneko. Learning of Evaluation Functions via Self-Play Enhanced by Checkmate Search. IEEE Technologies and Applications of Artificial Intelligence, Taiwan, 2018, pp. 126--131 (DOI 10.1109/TAAI.2018.00036)
- Hanhua Zhu and Tomoyuki Kaneko. Comparison of Loss Functions for Training of Deep Neural Networks in Shogi IEEE Technologies and Applications of Artificial Intelligence, Taiwan, 2018, pp. 18--23 (DOI 10.1109/TAAI.2018.00014)
- Hyunwoo Oh and Tomoyuki Kaneko. Deep Recurrent Q-Network with Truncated History. IEEE Technologies and Applications of Artificial Intelligence, Taiwan, 2018, pp. 34--39 (DOI 10.1109/TAAI.2018.00017)
- Tianhe Wang and Tomoyuki Kaneko. Application of Deep Reinforcement Learning in Werewolf Game Agents. IEEE Technologies and Applications of Artificial Intelligence, Taiwan, 2018, pp. 28--33 (DOI 10.1109/TAAI.2018.00016)
- Takahisa Imagawa and Tomoyuki Kaneko. Estimating the maximum expected value through upper confidence bound of likelihood. IEEE Technologies and Applications of Artificial Intelligence, Taiwan, 2017, pp. 92--95 (DOI: 10.1109/TAAI.2017.19)
- Shanchuan Wan and Tomoyuki Kaneko. Imitation Learning for Playing Shogi Based on Generative Adversarial Networks IEEE Technologies and Applications of Artificial Intelligence, Taiwan, 2017, pp. 202--207 (DOI: 10.1109/TAAI.2017.19)
- Y. Mandai and T. Kaneko: Improved LinUCT and Its Evaluation on Incremental Random-Feature Tree, IEEE Conference on Computational Intelligence and Games 2016, pp. 1--8 (DOI: 10.1109/CIG.2016.7860440).
- T. Imagawa and T. Kaneko: Monte Carlo Tree Search with Robust Exploration, LNCS, Computers and Games 2016. pp. 34-46. (doi: 10.1007/978-3-319-50935-8_4)
- Y. Mandai and T. Kaneko: LinUCB Applied to Monte Carlo Tree Search, Theoretical Computer Science. Volume 644, 6 September 2016, Pages 114-126. doi: 10.1016/j.tcs.2016.06.035
- S. Omori and T. Kaneko: Learning of Evaluation Functions to Realize Playing Styles in Shogi, LNCS, PRICAI. 367-379. DOI: 10.1007/978-3-319-42911-3_31
- Machine Learning of Evaluation Functions and Playing Styles in Shogi, TCGA, June 4, 2016 (invited talk)
- Recent Improvements in Game Tree Search Techniques and Shogi, @NCTU, June 3, 2016 (invited talk)
- Machine Learning of Evaluation Functions and Playing Styles in Shogi, JAIST Symposium on Game & Entertainment Technology & Its Application, (Feb. 10, invited talk)
- S. Takeuchi and T. Kaneko: Estimating Ratings of Computer Players by the Evaluation Scores and Principal Variations in Shogi. 3rd International Conference on Applied Computing and Information Technology (ACIT 2015), July 2015
- T. Imagawa and T. Kaneko: Enhancements in Monte Carlo Tree Search Algorithms for Biased Game Trees, the 2015 IEEE Conference on Computational Intelligence and Games (CIG 2015), 43-50. DOI:10.1109/CIG.2015.7317924
- S. Yokoyama, T. Kaneko, and T. Tetsuro: Parameter-Free Tree Style Pipeline in Asynchronous Parallel Game-Tree Search, The 14th International Conference on Advances in Computer and Games, LNCS, (210-222)
- Y. Mandai and T. Kaneko: LinUCB Applied to Monte Carlo Tree Search, The 14th International Conference on Advances in Computer and Games, LNCS, (41-52)

- K. Hoki and T. Kaneko (2014) "Large-Scale Optimization for Evaluation Functions with Minimax Search", Volume 49, pages 527-568. JAIR.
- Kunihito Hoki, Tomoyuki Kaneko, Daisaku Yokoyama, Takuya Obata, Hiroshi Yamashita, Yoshimasa Tsuruoka, and Takeshi Ito: Distributed-Shogi-System Akara 2010 and its Demonstration, The International Association for Computer and Information Science (ACIS), International Journal of Computer & Information Science, 14(2), 55-63, December 2013.
- A System-Design Outline of the Distributed-Shogi-System Akara 2010

K. Hoki, T. Kaneko, D. Yokoyama, T. Obata, H. Yamashita, Y. Tsuruoka, T. Ito. 14th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD), 466-471, 2013 - Parallel Dovetailing and Its Application to Depth-First
Proof-Number Search.

Kunihito Hoki, Tomoyuki Kaneko, Akihiro Kishimoto and Takeshi Ito. ICGA Journal, 36(1), 22--36, 2013 (2013 ICGA Journal Award) - Analysis of Evaluation-Function Learning
by Comparison of Sibling Nodes. (slides)

Tomoyuki Kaneko and Kunihito Hoki. Advances in Computer Games 13, 2011.

(LNCS 7168, pp. 158--169, 2012) - The Global Landscape of Objective Functions for the Optimization of
Shogi Piece Values with Game-Tree Search.

Kunihito Hoki and Tomoyuki Kaneko. Advances in Computer Games 13, 2011.

(LNCS 7168, pp. 184--195, 2012) - Infinite Connect-Four is Solved: Draw.

Yoshiaki Yamaguchi, Kazunori Yamaguchi, Tetsuro Tanaka and Tomoyuki Kaneko. Advances in Computer Games 13.

(LNCS 7168, pp. 208--219, 2012) - Scalable Distributed Monte-Carlo Tree
Search.

Kazuki Yoshizoe, Akihiro Kishimoto, Tomoyuki Kaneko, Haruhiro Yoshimoto and Yutaka Ishikawa. In Proceedings of the 4th Symposium on Combinatorial Search (SoCS'2011), pages 180-187, 2011 - Evaluation of Game Tree Search Methods by Game Records

Takeuchi, S.; Kaneko, T.; Yamaguchi, K.; IEEE Transactions on Computational Intelligence and AI in Games, 2 (4), 288 - 302, Dec. 2010. - Parallel Depth First Proof Number Search

T. Kaneko, AAAI2010, pp. 95--100, 2010.

- Evaluation of Monte Carlo Tree Search and the Application to Go

S. Takeuchi, T. Kaneko and K. Yamaguchi, CIG08, pages 191--198, 2008. ("This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder." ) - Visualization and Adjustment of Evaluation Functions Based on
Evaluation Values and Win Probability

S. Takeuchi, T. Kaneko, K. Yamaguchi and S. Kawai, AAAI07, pages 858-863, 2007. - Dual Lambda Search and Shogi Endgames

S. Soeda, T. Kaneko, T. Tanaka. Advances in Computer Games (2006) Springer-Verlag LNCS 4250, pages 126-139. - H. Yoshimoto, K. Yoshizoe, T. Kaneko, A. Kishimoto, and K. Taura: Monte Carlo Go Has a Way to Go, Twenty-First National Conference on Artificial Intelligence (AAAI-06), pages 1070-1075, 2006
- Enhancement of Dual Lambda Search

S. Soeda, T. Kaneko, T. Tanaka. The 10th Game Programming Workshop (2005) pp. 150--153

- Towards Evaluation of Shogi Endgames with Speed of Attack

S. Soeda, T. Kaneko, T. Tanaka. The 9th Game Programming Workshop (2004) pp. 125-128 - Automated Identification of Patterns in Evaluation Functions for General Game Players, T. Kaneko, K. Yamaguchi and S. Kawai, Advances in Computer Games Many Games, Many Challenges, published by Kluwer Academic Publishers/Boston, copyright 2004 by IFIP, (2003) pp. 279-298
- Pattern Selection Problem for Automatically Generating Evaluation Functions For General Game Player, T. Kaneko, K. Yamaguchi and S. Kawai, The Seventh Game Programming Workshop (IPSJ Symposium Series) 17 (2002) pp. 28-35
- T. Kaneko, K. Yamaguchi and S. Kawai. Automatic Feature Construction and Optimization for General Game Player,
*Proceedings of Game Programming Workshop 2001 (GPW2001),*pp. 25-32, Hakone, Japan, October 2001.

gzipped postscript | pdf - T. Kaneko, K. Yamaguchi and S. Kawai.
Compiling
Logical Features into Specialized State-Evaluators by Partial
Evaluation, Boolean Tables and Incremental Calculation.
*Proceedings of the 6th Pacific Rim International Conference on Artificial Intelligence (PRICAI2000),*Springer LNAI 1886, pages 72-82, Melbourne, Australia, August/September 2000.

gzipped postscript | pdf © Springer-Verlag