Tomoyuki Kaneko

Home * People * Tomoyuki Kaneko

Tomoyuki Kaneko

Tomoyuki Kaneko,
a Japanese computer scientist, and associate professor at Graduate School of the University of Tokyo. His research interests include machine learning in games, and automated feature construction for evaluation functions of general game players. He is co-author of the open source Shogi program GPS Shogi , available under GPL version 2 or later. In April 2013, GPS Shogi, running on a computer cluster of 700 PCs in the University of Tokyo, beat Hiroyuki Miura, one of the Top-10 professional Shogi players .

See also

• P-GPP

Selected Publications

2000 ...

• Tomoyuki Kaneko, Kazunori Yamaguchi, Satoru Kawai (2000). Compiling Logical Features into Specialized State-Evaluators by Partial Evaluation, Boolean Tables and Incremental Calculation. PRICAI 2000
• Tomoyuki Kaneko, Kazunori Yamaguchi, Satoru Kawai (2001). Automatic Feature Construction and Optimization for General Game Player. 6th Game Programming Workshop, Hakone
• Tomoyuki Kaneko, Kazunori Yamaguchi, Satoru Kawai (2002). Pattern Selection Problem for Automatically Generating Evaluation Functions For General Game Player. 7th Game Programming Workshop, Hakone
• Tomoyuki Kaneko, Kazunori Yamaguchi, Satoru Kawai (2003). Automated Identification of Patterns in Evaluation Functions for General Game Players. Advances in Computer Games 10

2005 ...

• Shunsuke Soeda, Tomoyuki Kaneko, Tetsuro Tanaka (2005). Dual Lambda Search and Shogi Endgames. Advances in Computer Games 11
• Haruhiro Yoshimoto, Kazuki Yoshizoe, Tomoyuki Kaneko, Akihiro Kishimoto, Kenjiro Taura (2006). Monte Carlo Go Has a Way to Go. AAAI 2006, pdf
• Shogo Takeuchi, Tomoyuki Kaneko, Kazunori Yamaguchi, Satoru Kawai (2007). Visualization and Adjustment of Evaluation Functions Based on Evaluation Values and Win Probability. AAAI 2007
• Shogo Takeuchi, Tomoyuki Kaneko, Kazunori Yamaguchi (2008). Evaluation of Monte Carlo tree search and the application to Go. CIG 2008

2010 ...

• Tomoyuki Kaneko (2010). Parallel Depth First Proof Number Search. AAAI 2010
• Shogo Takeuchi, Tomoyuki Kaneko, Kazunori Yamaguchi (2010). Evaluation of Game Tree Search Methods by Game Records. IEEE Transactions on Computational Intelligence and AI in Games, Vol. 2, No. 4
• Kazuki Yoshizoe, Akihiro Kishimoto, Tomoyuki Kaneko, Haruhiro Yoshimoto, Yutaka Ishikawa (2011). Scalable Distributed Monte Carlo Tree Search. SoCS2011, pdf
• Tomoyuki Kaneko, Kunihito Hoki (2011). Analysis of Evaluation-Function Learning by Comparison of Sibling Nodes. Advances in Computer Games 13
• Kunihito Hoki, Tomoyuki Kaneko (2011). The Global Landscape of Objective Functions for the Optimization of Shogi Piece Values with a Game-Tree Search. Advances in Computer Games 13
• Yoshiaki Yamaguchi, Kazunori Yamaguchi, Tetsuro Tanaka, Tomoyuki Kaneko (2011). Infinite Connect-Four Is Solved: Draw. Advances in Computer Games 13
• Tomoyuki Kaneko, Tetsuro Tanaka (2012). GPSShogi and Assembly of Large Shogi Software with Text Protocol. Computer Software - JSSST Journal, Vol. 29, No. 1
• Kunihito Hoki, Tomoyuki Kaneko, Akihiro Kishimoto, Takeshi Ito (2013). Parallel Dovetailing and its Application to Depth-First Proof-Number Search. ICGA Journal, Vol. 36, No. 1
• Kunihito Hoki, Tomoyuki Kaneko, Daisaku Yokoyama, Takuya Obata, Hiroshi Yamashita, Yoshimasa Tsuruoka, Takeshi Ito (2013). A System-Design Outline of the Distributed-Shogi-System Akara 2010. SNPD 2013
• Kunihito Hoki, Tomoyuki Kaneko (2014). Large-Scale Optimization for Evaluation Functions with Minimax Search. JAIR Vol. 49, pdf » Automated Tuning, Shogi

2015 ...

• Yusaku Mandai, Tomoyuki Kaneko (2015). LinUCB Applied to Monte Carlo Tree Search. Advances in Computer Games 14
• Shu Yokoyama, Tomoyuki Kaneko, Tetsuro Tanaka (2015). Parameter-Free Tree Style Pipeline in Asynchronous Parallel Game-Tree Search. Advances in Computer Games 14 » Stockfish DD
• Shogo Takeuchi, Tomoyuki Kaneko (2015). Estimating Ratings of Computer Players by the Evaluation Scores and Principal Variations in Shogi. ACIT-CSI
• Takahisa Imagawa, Tomoyuki Kaneko (2016). Monte Carlo Tree Search with Robust Exploration. CG 2016
• Taichi Nakayashiki, Tomoyuki Kaneko (2018). Learning of Evaluation Functions via Self-Play Enhanced by Checkmate Search. TAAI 2018
• Yusaku Mandai, Tomoyuki Kaneko (2018). Alternative Multitask Training for Evaluation Functions in Game of Go. TAAI 2018
• Hanhua Zhu, Tomoyuki Kaneko (2018). Comparison of Loss Functions for Training of Deep Neural Networks in Shogi. TAAI 2018
• Tianhe Wang, Tomoyuki Kaneko (2018). Application of Deep Reinforcement Learning in Werewolf Game Agents. TAAI 2018
• Hyunwoo Oh, Tomoyuki Kaneko (2018). Deep Recurrent Q-Network with Truncated History. TAAI 2018
• Yusaku Mandai, Tomoyuki Kaneko (2019). RankNet for evaluation functions of the game of Go. ICGA Journal, Vol. 41, No. 2
• Tomoyuki Kaneko, Takenobu Takizawa (2019). Computer Shogi Tournaments and Techniques. IEEE Transactions on Games, Vol. 11

External Links

• Tomoyuki Kaneko's ICGA Tournaments
• Tomoyuki Kaneko - Homepage

References

Up one level