Kaneko Tomoyuki 金子知適

… Alternative Names

KANEKO Tomoyuki 金子知適

Less

Researcher Number	00345068
Other IDs
Affiliation (Current)	2025: 東京大学, 大学院総合文化研究科, 教授
Affiliation (based on the past Project Information) *help	2022 – 2023: 東京大学, 大学院総合文化研究科, 教授 2021: 東京大学, 大学院総合文化研究科, 准教授 2016 – 2020: 東京大学, 大学院情報学環・学際情報学府, 准教授 2015: 東京大学, 大学院情報学環, 准教授 2012 – 2014: 東京大学, 総合文化研究科, 准教授 … More 2011 – 2012: 東京大学, 大学院・総合文化研究科, 准教授 2010: 東京大学, 大学院・総合文化研究科, 助教 2007 – 2008: The University of Tokyo, 大学院・総合文化研究科, 助教 2005 – 2006: 東京大学, 大学院総合文化研究科, 助手 2002 – 2005: 東京大学, 大学院・総合文化研究科, 助手 Less
Review Section/Research Field	Principal Investigator Intelligent informatics / Medium-sized Section 62:Applied informatics and related fields / Entertainment and game informatics 1 / Basic Section 62040:Entertainment and game informatics-related Except Principal Investigator Intelligent informatics / Science and Engineering
Keywords	Principal Investigator ゲームプログラミング / 機械学習 / 人工知能 / ゲーム情報学 / 探索 / アルゴリズム / 深層強化学習 / 並列計算 / 機構学習 / データマイニング … More / 詰将棋 / 学習 / df-pn / 人工知 … More Except Principal Investigator aspect / non-wellfounded set / reflective calculation / Galois lattice / state transition rules / knowledge acquisition / dynamic evaluator / evaluation functions / アスペクト / 自己反映計算 / 知識獲得 / 動的評価器 / 評価関数 / モデル化 / 機械学習 / 非有基的集合 / ガロア東 / 状態遷移規則 / feature / 非有基的構造 / ガロア束 / 局面遷移規則 / requirements specification / type system / aspect-oriented programming / model checking / reuse / high reliability / component / software / Webサービス / 要求仕様 / 型システム / アスペクト指向 / モデル検査 / 再利用 / 高信頼性 / コンポーネント / ソフトウェア Less

Onto generalization of reinforcement learning agents through diversity and understanding of environmentsPrincipal Investigator
- Principal Investigator
  
  Kaneko Tomoyuki
- Project Period (FY)
  2021 – 2023
- Research Category
  
  Grant-in-Aid for Scientific Research (B)
- Review Section
  
  Basic Section 62040:Entertainment and game informatics-related
- Research Institution
  The University of Tokyo
Deep reinforcement learning in multi-player imperfect-information gamesPrincipal Investigator
- Principal Investigator
  
  Kaneko Tomoyuki
- Project Period (FY)
  2021 – 2023
- Research Category
  
  Grant-in-Aid for Challenging Research (Exploratory)
- Review Section
  
  Medium-sized Section 62:Applied informatics and related fields
- Research Institution
  The University of Tokyo
deep reinforcement learning for imperfect and multi-player environmentsPrincipal Investigator
- Principal Investigator
  
  Kaneko Tomoyuki
- Project Period (FY)
  2018 – 2021
- Research Category
  
  Grant-in-Aid for Challenging Research (Exploratory)
- Review Section
  
  Medium-sized Section 62:Applied informatics and related fields
- Research Institution
  The University of Tokyo
Machine learning and distributed game-tree search in gamesPrincipal Investigator
- Principal Investigator
  
  KANEKO TOMOYUKI
- Project Period (FY)
  2016 – 2018
- Research Category
  
  Grant-in-Aid for Scientific Research (B)
- Research Field
  
  Entertainment and game informatics 1
- Research Institution
  The University of Tokyo
Explanation of positional evaluation by computer programsPrincipal Investigator
- Principal Investigator
  
  Kaneko Tomoyuki
- Project Period (FY)
  2013 – 2015
- Research Category
  
  Grant-in-Aid for Scientific Research (C)
- Research Field
  
  Entertainment and game informatics 1
- Research Institution
  The University of Tokyo
Decision support with search and machine learning techniquesPrincipal Investigator
- Principal Investigator
  
  KANEKO Tomoyuki
- Project Period (FY)
  2010 – 2012
- Research Category
  
  Grant-in-Aid for Young Scientists (B)
- Research Field
  
  Intelligent informatics
- Research Institution
  The University of Tokyo
Automated acquisition of empirical knowledge and its application to search techniquesPrincipal Investigator
- Principal Investigator
  
  KANEKO Tomoyuki
- Project Period (FY)
  2007 – 2008
- Research Category
  
  Grant-in-Aid for Young Scientists (B)
- Research Field
  
  Intelligent informatics
- Research Institution
  The University of Tokyo
Wide Range Application of Status Evaluation Function
- Principal Investigator
  
  KAWAI Satoru
- Project Period (FY)
  2005 – 2006
- Research Category
  
  Grant-in-Aid for Scientific Research (C)
- Research Field
  
  Intelligent informatics
- Research Institution
  The University of Tokyo
アルゴリズムに応じた知識獲得手法の研究Principal Investigator
- Principal Investigator
  
  金子知適
- Project Period (FY)
  2004 – 2006
- Research Category
  
  Grant-in-Aid for Young Scientists (B)
- Research Field
  
  Intelligent informatics
- Research Institution
  The University of Tokyo
Acquisition of Evaluation Function of high precision by Learning
- Principal Investigator
  
  KAWAI Satoru
- Project Period (FY)
  2003 – 2004
- Research Category
  
  Grant-in-Aid for Scientific Research (C)
- Research Field
  
  Intelligent informatics
- Research Institution
  The University of Tokyo
High Reliability Component-Based Software Engineering
- Principal Investigator
  
  TAMAI Tetsuo
- Project Period (FY)
  2001 – 2005
- Research Category
  
  Grant-in-Aid for Scientific Research on Priority Areas
- Review Section
  
  Science and Engineering
- Research Institution
  The University of Tokyo

[Book] コンピュータ将棋の進歩 6--プロ棋士に並ぶ--2012
- Author(s)
  保木邦仁, 金子知適, 大槻知史, 鶴岡慶雅, 伊藤毅志, 岸本章宏, 松原仁
- Total Pages
  144
- Publisher
  共立出版
- Data Source
  KAKENHI-PROJECT-22700136
[Book] 人間に勝つコンピュータ将棋の作り方2012
- Author(s)
  瀧澤武信，松原仁，小谷善行，鶴岡慶雅，山下宏，金子知適，保木邦仁，伊藤毅志，竹内章，篠田正人，古作登，橋本剛
- Total Pages
  304
- Publisher
  技術評論社
- Data Source
  KAKENHI-PROJECT-22700136
[Journal Article] Curiosity-driven exploration for cooperative multi-agent reinforcement learning2023
- Author(s)
  Xu and Kaneko
- Journal Title
  
  IEEE ijcnn
  
  Volume: -
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-21K19816
[Journal Article] DEIR: Efficient and robust exploration through discriminative-model-based episodic intrinsic rewards2023
- Author(s)
  Wan and Tang and Tian and Kaneko
- Journal Title
  
  IJCAI
  
  Volume: ijcai.2023 Pages: 4289-4298
- DOI
  10.24963/ijcai.2023/477
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-21K19816, KAKENHI-PROJECT-21H03570
[Journal Article] Curiosity-driven exploration for cooperative multi-agent reinforcement learning2023
- Author(s)
  Xu and Kaneko
- Journal Title
  
  IEEE international joint conference on neural networks
  
  Volume: IJCNN54540.2023 Pages: 1-8
- DOI
  10.1109/ijcnn54540.2023.10191336
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-21K19816, KAKENHI-PROJECT-21H03570
[Journal Article] Curiosity-driven exploration for cooperative multi-agent reinforcement learning2023
- Author(s)
  Xu and Kaneko
- Journal Title
  
  IEEE ijcnn
  
  Volume: -
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-21H03570
[Journal Article] Improving counterfactual regret minimization agents training in card game cheat using ordered abstraction2022
- Author(s)
  Yi and Kaneko
- Journal Title
  
  Advances in computer games 2021
  
  Volume: - Pages: 3-13
- DOI
  10.1007/978-3-031-11488-5_1
- ISBN
  9783031114878, 9783031114885
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-21K19816
[Journal Article] 3x3盤面の2048の完全解析と強化学習の研究2022
- Author(s)
  山下金子中屋敷
- Journal Title
  
  第27回ゲームプログラミングワークショップ
  
  Volume: - Pages: 34-41
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-21H03570
[Journal Article] Learning strategies for imperfect information board games using depth-limited counterfactual regret minimization and belief state2022
- Author(s)
  Chen and Kaneko
- Journal Title
  
  IEEE international conference on games
  
  Volume: - Pages: 486-493
- DOI
  10.1109/cog51982.2022.9893713
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-21K19816, KAKENHI-PROJECT-21H03570
[Journal Article] 3x3盤面の2048の完全解析と強化学習の研究2022
- Author(s)
  山下金子中屋敷
- Journal Title
  
  第27回ゲームプログラミングワークショップ
  
  Volume: - Pages: 34-41
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-21K19816
[Journal Article] Local coordination in multi-agent reinforcement learning2021
- Author(s)
  F. Xu and T. Kaneko
- Journal Title
  
  International conference on technologies and applications of artificial intelligence
  
  Volume: -
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-21H03570
[Journal Article] Improve counterfactual regret minimization agents training by setting limitations of numbers of steps in games2021
- Author(s)
  C. Yi and T. Kaneko
- Journal Title
  
  26th game programming workshop
  
  Volume: - Pages: 117-123
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-21K19816
[Journal Article] Residual network for deep reinforcement learning with attention mechanism2021
- Author(s)
  H. Zhu and T. Kaneko
- Journal Title
  
  J. Inf. Sci. Eng.
  
  Volume: - Pages: 517-533
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-21H03570
[Journal Article] ついたて王手どうぶつしょうぎの提案とCFRによる戦略の学習2021
- Author(s)
  中屋敷金子
- Journal Title
  
  第26回ゲームプログラミングワークショップ
  
  Volume: - Pages: 34-41
- NAID
  170000185756
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-21K19816
[Journal Article] Maximum entropy reinforcement learning in two-player perfect information games2021
- Author(s)
  T. Nakayashiki and T. Kaneko
- Journal Title
  
  IEEE SSCI
  
  Volume: - Pages: 1-8
- DOI
  10.1109/ssci50451.2021.9659991
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-21H03570
[Journal Article] ついたて王手どうぶつしょうぎの提案とCFRによる戦略の学習2021
- Author(s)
  中屋敷金子
- Journal Title
  
  第26回ゲームプログラミングワークショップ
  
  Volume: - Pages: 34-41
- NAID
  170000185756
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-18K19832
[Journal Article] Prediction of werewolf players by sentiment analysis of game dialogue in japanese2021
- Author(s)
  Y. Sun and T. Kaneko
- Journal Title
  
  26th game programming workshop
  
  Volume: - Pages: 186-191
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-21K19816
[Journal Article] Improving counterfactual regret minimization agents training in card game cheat using ordered abstraction2021
- Author(s)
  C. Yi and T. Kaneko
- Journal Title
  
  Advances in computers and games
  
  Volume: -
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-18K19832
[Journal Article] Prediction of werewolf players by sentiment analysis of game dialogue in japanese2021
- Author(s)
  Y. Sun and T. Kaneko
- Journal Title
  
  26th game programming workshop
  
  Volume: - Pages: 186-191
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-18K19832
[Journal Article] Hierarchical advantage for reinforcement learning in parameterized action space2021
- Author(s)
  Z. Hu and T. Kaneko
- Journal Title
  
  IEEE international conference on games
  
  Volume: - Pages: 1-8
- DOI
  10.1109/cog52621.2021.9619068
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-18K19832, KAKENHI-PROJECT-21H03570
[Journal Article] Local coordination in multi-agent reinforcement learning2021
- Author(s)
  F. Xu and T. Kaneko
- Journal Title
  
  International conference on technologies and applications of artificial intelligence
  
  Volume: -
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-18K19832
[Journal Article] Local coordination in multi-agent reinforcement learning2021
- Author(s)
  F. Xu and T. Kaneko
- Journal Title
  
  International conference on technologies and applications of artificial intelligence
  
  Volume: -
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-21K19816
[Journal Article] 2048 への方策勾配法の適用2021
- Author(s)
  山下金子
- Journal Title
  
  第26回ゲームプログラミングワークショップ
  
  Volume: - Pages: 179-185
- NAID
  170000185730
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-21H03570
[Journal Article] Improving counterfactual regret minimization agents training in card game cheat using ordered abstraction2021
- Author(s)
  C. Yi and T. Kaneko
- Journal Title
  
  Advances in computers and games
  
  Volume: -
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-21K19816
[Journal Article] Improve counterfactual regret minimization agents training by setting limitations of numbers of steps in games2021
- Author(s)
  C. Yi and T. Kaneko
- Journal Title
  
  26th game programming workshop
  
  Volume: - Pages: 117-123
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-18K19832
[Journal Article] 逆転の余地を考慮した評価関数の設計とどうぶつしょうぎによる評価2020
- Author(s)
  中屋敷金子
- Journal Title
  
  第25回ゲームプログラミングワークショップ
  
  Volume: 978-4-907626-46-4 C3804 Pages: 22-29
- NAID
  170000184517
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-18K19832
[Journal Article] Diverse exploration via infomax options2020
- Author(s)
  Kanagawa and Kaneko
- Journal Title
  
  Arxiv
  
  Volume: 978-4-907626-46-4 C3804 Pages: 1-21
- Open Access
- Data Source
  KAKENHI-PROJECT-18K19832
[Journal Article] Evaluation of loss function for stable policy learning in dobutsu shogi2020
- Author(s)
  Nakayashiki and Kaneko
- Journal Title
  
  International conference on technologies and applications of artificial intelligence
  
  Volume: N/A Pages: 175-180
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-18K19832
[Journal Article] 離散行動空間における soft actor-critic の評価2020
- Author(s)
  合田金子
- Journal Title
  
  第25回ゲームプログラミングワークショップ
  
  Volume: 978-4-907626-46-4 C3804 Pages: 175-180
- NAID
  170000184494
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-18K19832
[Journal Article] Ceramic: A research environment based on the multi-player strategic board game azul2020
- Author(s)
  Gendre and Kaneko
- Journal Title
  
  25th game programming workshop
  
  Volume: 978-4-907626-46-4 C3804 Pages: 155-160
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-18K19832
[Journal Article] Playing catan with cross-dimensional neural network2020
- Author(s)
  Gendre and Kaneko
- Journal Title
  
  ICONIP
  
  Volume: 12533 Pages: 580-592
- DOI
  10.1007/978-3-030-63833-7_49
- ISBN
  9783030638320, 9783030638337
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-18K19832
[Journal Article] Rogue-Gym: A New Challenge for Generalization in Reinforcement Learning2019
- Author(s)
  Yuji Kanagawa and Tomoyuki Kaneko
- Journal Title
  
  IEEE Conference on Games
  
  Volume: 19013855 Pages: 1-8
- DOI
  10.1109/cig.2019.8848075
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-18K19832
[Journal Article] RankNet for evaluation functions of the game of Go2019
- Author(s)
  Yusaku Mandai and Tomoyuki Kaneko
- Journal Title
  
  ICGA Journal
  
  Volume: 41(2) Issue: 2 Pages: 78-91
- DOI
  10.3233/icg-190108
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-18K19832
[Journal Article] Deep Residual Attention Reinforcement Learning2019
- Author(s)
  Hanhua Zhu and Tomoyuki Kaneko
- Journal Title
  
  International Conference on Technologies and Applications of Artificial Intelligence
  
  Volume: 19279615 Pages: 1-6
- DOI
  10.1109/taai48200.2019.8959896
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-18K19832
[Journal Article] Acquiring Strategies for the Board Game Geister by Regret Minimization2019
- Author(s)
  Chen Chen and Tomoyuki Kaneko
- Journal Title
  
  International Conference on Technologies and Applications of Artificial Intelligence
  
  Volume: 19279608 Pages: 1-6
- DOI
  10.1109/taai48200.2019.8959878
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-18K19832
[Journal Article] Application of Deep-RL with Sample-Efficient Method in Mini-games of StarCraft II2019
- Author(s)
  Zhejie Hu and Tomoyuki Kaneko
- Journal Title
  
  International Conference on Technologies and Applications of Artificial Intelligence
  
  Volume: 19279598 Pages: 1-6
- DOI
  10.1109/taai48200.2019.8959866
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-18K19832
[Journal Article] Computer Shogi Tournaments and Techniques2019
- Author(s)
  Tomoyuki Kaneko and Takenobu Takizawa
- Journal Title
  
  IEEE Transactions on Games
  
  Volume: 11(3) Issue: 3 Pages: 267-274
- DOI
  10.1109/tg.2019.2939259
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-18K19832
[Journal Article] LSTM の初期状態の学習による DRQN の改善2018
- Author(s)
  Oh Hyunwoo 金子知適
- Journal Title
  
  第23回ゲームプログラミングワークショップ
  
  Volume: -
- NAID
  170000178493
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-18K19832
[Journal Article] Reinforcement Learning with Effective Exploitation of Experiences on Mini-Games of StarCraft II2018
- Author(s)
  ZheJie Hu and Tomoyuki Kaneko
- Journal Title
  
  The 23rd Game Programming Workshop
  
  Volume: -
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-18K19832
[Journal Article] 人狼エージェントにおける深層Qネットワークの応用2018
- Author(s)
  王天鶴金子知適
- Journal Title
  
  第23回ゲームプログラミングワークショップ
  
  Volume: -
- NAID
  170000178462
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-16H02927
[Journal Article] ローグライクゲームによる強化学習ベンチマーク環境Rogue-Gymの提案2018
- Author(s)
  金川裕司金子知適
- Journal Title
  
  第23回ゲームプログラミングワークショップ
  
  Volume: -
- NAID
  170000178478
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-16H02927
[Journal Article] An Alternative Multitask Training for Evaluation Functions in the Game of Go2018
- Author(s)
  Yusaku Mandai and Tomoyuki Kaneko
- Journal Title
  
  IEEE Technologies and Applications of Artificial Intelligence
  
  Volume: - Pages: 132-135
- DOI
  10.1109/taai.2018.00037
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-16H02927, KAKENHI-PROJECT-17J09685
[Journal Article] LSTM の初期状態の学習による DRQN の改善2018
- Author(s)
  Oh Hyunwoo 金子知適
- Journal Title
  
  第23回ゲームプログラミングワークショップ
  
  Volume: -
- NAID
  170000178493
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-16H02927
[Journal Article] Counterfactual Regret Minimization for the Board Game Geister2018
- Author(s)
  Chen Chen and Tomoyuki Kaneko
- Journal Title
  
  The 23rd Game Programming Workshop
  
  Volume: -
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-18K19832
[Journal Article] Reinforcement Learning with Effective Exploitation of Experiences on Mini-Games of StarCraft II2018
- Author(s)
  ZheJie Hu and Tomoyuki Kaneko
- Journal Title
  
  The 23rd Game Programming Workshop
  
  Volume: -
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-16H02927
[Journal Article] 階層を考慮した模倣学習と強化学習の組み合わせ2018
- Author(s)
  藤村悠太朗金子知適
- Journal Title
  
  第23回ゲームプログラミングワークショップ
  
  Volume: -
- NAID
  170000178482
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-16H02927
[Journal Article] Comparison of Loss Functions for Training of Deep Neural Networks in Shogi2018
- Author(s)
  Hanhua Zhu and Tomoyuki Kaneko
- Journal Title
  
  IEEE Technologies and Applications of Artificial Intelligence
  
  Volume: - Pages: 18-23
- DOI
  10.1109/taai.2018.00014
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-16H02927
[Journal Article] Application of Deep Reinforcement Learning in Werewolf Game Agents2018
- Author(s)
  Tianhe Wang and Tomoyuki Kaneko
- Journal Title
  
  IEEE Technologies and Applications of Artificial Intelligence
  
  Volume: - Pages: 28-33
- DOI
  10.1109/taai.2018.00016
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-18K19832, KAKENHI-PROJECT-16H02927
[Journal Article] Deep Recurrent Q-Network with Truncated History2018
- Author(s)
  Hyunwoo Oh and Tomoyuki Kaneko
- Journal Title
  
  IEEE Technologies and Applications of Artificial Intelligence
  
  Volume: - Pages: 34-39
- DOI
  10.1109/taai.2018.00017
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-18K19832, KAKENHI-PROJECT-16H02927
[Journal Article] Heterogeneous Multi-Task Learning of Evaluation Functions for Chess and Shogi2018
- Author(s)
  Shanchuan Wan and Tomoyuki Kaneko
- Journal Title
  
  ICONIP 2018
  
  Volume: 3 Pages: 347-358
- DOI
  10.1007/978-3-030-04182-3_31
- ISBN
  9783030041816, 9783030041823
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-16H02927
[Journal Article] Learning of Evaluation Functions via Self-Play Enhanced by Checkmate Search2018
- Author(s)
  Taichi Nakayashiki and Tomoyuki Kaneko
- Journal Title
  
  IEEE Technologies and Applications of Artificial Intelligence
  
  Volume: - Pages: 126-131
- DOI
  10.1109/taai.2018.00036
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-16H02927
[Journal Article] Playing the Flappy Bird with Reinforcement Learning Algorithms2018
- Author(s)
  Hanhua Zhu and Tomoyuki Kaneko
- Journal Title
  
  The 23rd Game Programming Workshop
  
  Volume: -
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-18K19832
[Journal Article] 囲碁ニューラルネットワークの判断根拠の可視化2018
- Author(s)
  万代悠作金子知適
- Journal Title
  
  第23回ゲームプログラミングワークショップ
  
  Volume: -
- NAID
  170000178461
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-16H02927
[Journal Article] Playing the Flappy Bird with Reinforcement Learning Algorithms2018
- Author(s)
  Hanhua Zhu and Tomoyuki Kaneko
- Journal Title
  
  The 23rd Game Programming Workshop
  
  Volume: -
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-16H02927
[Journal Article] 人狼エージェントにおける深層Qネットワークの応用2018
- Author(s)
  王天鶴金子知適
- Journal Title
  
  第23回ゲームプログラミングワークショップ
  
  Volume: -
- NAID
  170000178462
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-18K19832
[Journal Article] Building Evaluation Functions for Chess and Shogi with Uniformity Regularization Networks2018
- Author(s)
  Shanchuan Wan and Tomoyuki Kaneko
- Journal Title
  
  IEEE Conference on Computational Intelligence and Games 2018
  
  Volume: - Pages: 1-8
- DOI
  10.1109/cig.2018.8490455
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-16H02927
[Journal Article] Counterfactual Regret Minimization for the Board Game Geister2018
- Author(s)
  Chen Chen and Tomoyuki Kaneko
- Journal Title
  
  The 23rd Game Programming Workshop
  
  Volume: -
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-16H02927
[Journal Article] 将棋用ニューラルネットワークへの顕著性抽出手法の適用2018
- Author(s)
  中屋敷太一金子知適
- Journal Title
  
  第23回ゲームプログラミングワークショップ
  
  Volume: -
- NAID
  170000178460
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-16H02927
[Journal Article] ローグライクゲームによる強化学習ベンチマーク環境Rogue-Gymの提案2018
- Author(s)
  金川裕司金子知適
- Journal Title
  
  第23回ゲームプログラミングワークショップ
  
  Volume: -
- NAID
  170000178478
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-18K19832
[Journal Article] Pos2Pos: Automatic Position-to-Position Translation in Chess-Like Games2018
- Author(s)
  Shanchuan Wan and Tomoyuki Kaneko
- Journal Title
  
  The 23rd Game Programming Workshop
  
  Volume: -
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-16H02927
[Journal Article] GVG-AI のための Monte Carlo Tree Search の改善に関する研究2017
- Author(s)
  OH HYUNWOO, 金子知適
- Journal Title
  
  ゲームプログラミングワークショップ予稿集
  
  Volume: - Pages: 56-63
- NAID
  170000176049
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-16H02927
[Journal Article] Imitation Learning for Playing Shogi Based on Generative Adversarial Networks Technologies and Applications of Artificial Intelligence2017
- Author(s)
  Shanchuan Wan and Tomoyuki Kaneko
- Journal Title
  
  Technologies and Applications of Artificial Intelligence
  
  Volume: -
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-16H02927
[Journal Article] 強化学習を用いた評価関数の作成手法の信頼性の分析2017
- Author(s)
  嶽　俊太郎, 金子知適
- Journal Title
  
  ゲームプログラミングワークショップ予稿集
  
  Volume: - Pages: 250-257
- NAID
  170000176079
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-16H02927
[Journal Article] 局面の組合せを用いた囲碁評価関数の学習2017
- Author(s)
  万代悠作, 金子知適
- Journal Title
  
  ゲームプログラミングワークショップ予稿集
  
  Volume: - Pages: 8-14
- NAID
  170000176042
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-16H02927
[Journal Article] Estimating the maximum expected value through upper confidence bound of likelihood. Technologies and Applications of Artificial Intelligence2017
- Author(s)
  Takahisa Imagawa and Tomoyuki Kaneko
- Journal Title
  
  Technologies and Applications of Artificial Intelligence
  
  Volume: -
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-16H02927
[Journal Article] モンテカルロ木探索における状態価値の推定方法の改善2017
- Author(s)
  今川孝久, 金子知適
- Journal Title
  
  ゲームプログラミングワークショップ予稿集
  
  Volume: - Pages: 34-41
- NAID
  170000176046
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-16H02927
[Journal Article] LinUCB Applied to Monte Carlo Tree Search2016
- Author(s)
  Y. Mandai and T. Kaneko
- Journal Title
  
  Theoretical Computer Science
  
  Volume: 644(6) Pages: 114-126
- DOI
  10.1016/j.tcs.2016.06.035
- NAID
  170000087238
- Peer Reviewed / Acknowledgement Compliant
- Data Source
  KAKENHI-PROJECT-16H02927
[Journal Article] 確率的勾配降下法を用いたLinUCT のスケーラビリティの改善2016
- Author(s)
  万代悠作, 金子知適
- Journal Title
  
  情報処理学会論文誌
  
  Volume: 57(11) Pages: 2328-2336
- NAID
  170000131089
- Peer Reviewed / Acknowledgement Compliant
- Data Source
  KAKENHI-PROJECT-16H02927
[Journal Article] Monte Carlo Tree Search with Robust Exploration2016
- Author(s)
  T. Imagawa and T. Kaneko
- Journal Title
  
  Computers and Games 2016
  
  Volume: LNCS
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-25330432
[Journal Article] Monte Carlo Tree Search with Robust Exploration2016
- Author(s)
  T. Imagawa and T. Kaneko
- Journal Title
  
  LNCS, Computers and Games
  
  Volume: 10068 Pages: 34-46
- DOI
  10.1007/978-3-319-50935-8_4
- ISBN
  9783319509341, 9783319509358
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-16H02927, KAKENHI-PROJECT-16J07455
[Journal Article] Learning of Evaluation Functions to Realize Playing Styles in Shogi2016
- Author(s)
  S. Omori and T. Kaneko
- Journal Title
  
  LNCS, PRICAI
  
  Volume: 9810 Pages: 367-379
- DOI
  10.1007/978-3-319-42911-3_31
- ISBN
  9783319429106, 9783319429113
- Acknowledgement Compliant
- Data Source
  KAKENHI-PROJECT-16H02927
[Journal Article] Improved LinUCT and Its Evaluation on Incremental Random-Feature Tree2016
- Author(s)
  Y. Mandai and T. Kaneko
- Journal Title
  
  IEEE Computational Intelligence and Games
  
  Volume: 2325-4289 Pages: 1-8
- DOI
  10.1109/cig.2016.7860440
- Peer Reviewed / Acknowledgement Compliant
- Data Source
  KAKENHI-PROJECT-16H02927
[Journal Article] 将棋の棋譜の指し手から意図を読みとる2015
- Author(s)
  金子知適
- Journal Title
  
  情報学環紀要
  
  Volume: 89 Pages: 119-122
- Open Access
- Data Source
  KAKENHI-PROJECT-25330432
[Journal Article] Enhancements in Monte Carlo Tree Search Algorithms for Biased Game Trees2015
- Author(s)
  T. Imagawa and T. Kaneko
- Journal Title
  
  the 2015 IEEE Conference on Computational Intelligence and Games
  
  Volume: LNCS Pages: 43-50
- DOI
  10.1109/cig.2015.7317924
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-25330432
[Journal Article] Parameter-Free Tree Style Pipeline in Asynchronous Parallel Game-Tree Search2015
- Author(s)
  S. Yokoyama, T. Kaneko, and T. Tetsuro
- Journal Title
  
  The 14th International Conference on Advances in Computer and Games
  
  Volume: LNCS Pages: 210-222
- DOI
  10.1007/978-3-319-27992-3_19
- ISBN
  9783319279916, 9783319279923
- Peer Reviewed / Acknowledgement Compliant
- Data Source
  KAKENHI-PROJECT-25330432
[Journal Article] LinUCB Applied to Monte Carlo Tree Search2015
- Author(s)
  Y. Mandai and T. Kaneko
- Journal Title
  
  The 14th International Conference on Advances in Computer and Games
  
  Volume: LNCS Pages: 41-52
- DOI
  10.1007/978-3-319-27992-3_5
- NAID
  170000087238
- ISBN
  9783319279916, 9783319279923
- Peer Reviewed / Acknowledgement Compliant
- Data Source
  KAKENHI-PROJECT-25330432
[Journal Article] Estimating Ratings of Computer Players by the Evaluation Scores and Principal Variations in Shogi2015
- Author(s)
  S. Takeuchi and T. Kaneko
- Journal Title
  
  2nd International Conference on Computational Science and Intelligence
  
  Volume: LNCS Pages: 85-90
- DOI
  10.1109/acit-csi.2015.23
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-25330432
[Journal Article] 二人ゲームプレイヤのPrior knowledgeを用いたUCTによる個性の実現手法と評価2014
- Author(s)
  志水翔, 金子知適
- Journal Title
  
  第19回ゲームプログラミングワークショップ
  
  Volume: IPSJ Symposium Series 2014
- NAID
  170000087240
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-25330432
[Journal Article] Large-Scale Optimization for Evaluation Functions with Minimax Search2014
- Author(s)
  K. Hoki and T. Kaneko
- Journal Title
  
  Journal of Artificial Intelligence Research
  
  Volume: 49 Pages: 527-568
- DOI
  10.1613/jair.4217
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-25330432, KAKENHI-PROJECT-25730212
[Journal Article] 局面の局所的な類似性を利用したモンテカルロ木探索の効率化2014
- Author(s)
  志水翔，金子知適
- Journal Title
  
  情報処理学会論文誌
  
  Volume: 55(11) Pages: 2362-2369
- NAID
  110009550125
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-25330432
[Journal Article] 難しさが手番で異なる局面でのモンテカルロ木探索の性能の改善2014
- Author(s)
  今川孝久，金子知適
- Journal Title
  
  情報処理学会論文誌
  
  Volume: 55(11) Pages: 2353-2361
- NAID
  170000078726
- Peer Reviewed / Open Access
- Data Source
  KAKENHI-PROJECT-25330432
[Journal Article] 将棋の自動解説の試み2014
- Author(s)
  金子知適
- Journal Title
  
  情報処理
  
  Volume: 55(8) Pages: 857-857
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-25330432
[Journal Article] 多数の計算機を活用したゲーム木探索技術の進歩 --三浦弘行八段とGPS将棋との対局を振り返って--2013
- Author(s)
  金子知適, 田中哲朗
- Journal Title
  
  情報処理
  
  Volume: 54(9) Pages: 914-922
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-25330432
[Journal Article] 局面の局所的な類似性を利用したモンテカルロ木探索の効率化2013
- Author(s)
  志水翔, 金子知適
- Journal Title
  
  ゲームプログラミングワークショップ 2013予稿集
  
  Volume: 2013 Pages: 130-133
- NAID
  110009550125
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-25330432
[Journal Article] Parallel Dovetailing and Its Application to Depth-First Proof-Number Search.2013
- Author(s)
  Kunihito Hoki, Tomoyuki Kaneko, Akihiro Kishimoto and Takeshi Ito
- Journal Title
  
  ICGA Journal
  
  Volume: 36(1) Pages: 22-36
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-25330432
[Journal Article] 難しさが手番で異なる局面でのモンテカルロ木探索の性能の改善2013
- Author(s)
  今川孝久, 金子知適
- Journal Title
  
  ゲームプログラミングワークショップ 2013予稿集
  
  Volume: 2013 Pages: 162-169
- NAID
  170000078726
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-25330432
[Journal Article] コンピュータ将棋の評価関数と棋譜を教師とした機械学習2012
- Author(s)
  金子知適
- Journal Title
  
  人工知能学会誌
  
  Volume: 27(1) Pages: 75-82
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22700136
[Journal Article] コンピュータ将棋の評価関数と棋譜を教師とした機械学習.2012
- Author(s)
  金子知適
- Journal Title
  
  人工知能学会誌
  
  Volume: 27(1) Pages: 75-82
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22700136
[Journal Article] 最善手の予測に基づくゲーム木探索の分散並列実行2012
- Author(s)
  金子知適, 田中哲朗
- Journal Title
  
  情報処理学会論文誌
  
  Volume: 53(11)
- NAID
  110009486868
- Data Source
  KAKENHI-PROJECT-22700136
[Journal Article] GPS将棋とテキストプロトコルによる大規模将棋ソフトウェアの組み立て2012
- Author(s)
  金子知適,田中哲朗
- Journal Title
  
  コンピュータソフトウェア
  
  Volume: 29(1) Pages: 75-81
- NAID
  10030021274
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22700136
[Journal Article] 最善手の予測に基づくゲーム木探索の分散並列実行2012
- Author(s)
  金子知適,田中哲朗
- Journal Title
  
  情報処理学会論文誌
  
  Volume: 53(11) Pages: 2517-2524
- NAID
  110009486868
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22700136
[Journal Article] コンピュータ将棋を用いた棋譜の自動解説と評価2012
- Author(s)
  金子知適
- Journal Title
  
  情報処理学会論文誌
  
  Volume: 53(11) Pages: 2525-2532
- NAID
  110009486870
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22700136
[Journal Article] コンピュータ将棋を用いた棋譜の自動解説と評価2012
- Author(s)
  金子知適
- Journal Title
  
  情報処理学会論文誌
  
  Volume: 53(11)
- NAID
  110009486870
- Data Source
  KAKENHI-PROJECT-22700136
[Journal Article] あから2010勝利への道:4.清水女流王将vsあから2010:コンピュータの思考過程を追う2011
- Author(s)
  鶴岡慶雅, 金子知適, 山下宏, 保木邦仁
- Journal Title
  
  情報処理
  
  Volume: Vol.52,No.2 Pages: 175-180
- NAID
  110008507309
- Data Source
  KAKENHI-PROJECT-22700136
[Journal Article] あから2010勝利への道:2.あから2010のシステム設計と操作概要2011
- Author(s)
  金子知適,横山大作,小幡拓弥,山下宏
- Journal Title
  
  情報処理
  
  Volume: Vol.52,No.2 Pages: 162-169
- NAID
  110008507307
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22700136
[Journal Article] Evaluation of GameTree SearchMethods by Game Records2010
- Author(s)
  S.; Kaneko, T.; Yamaguchi, K
- Journal Title
  
  IEEE Transactions on ComputationalIntelligence and AI in Games
  
  Volume: 2(4) Pages: 288-302
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22700136
[Journal Article] 最善手の予測に基づくゲーム木探索の分散並列実行2010
- Author(s)
  金子知適, 田中哲朗
- Journal Title
  
  情報処理学会ゲームプログラミングワークショップ
  
  Volume: 15 Pages: 126-133
- NAID
  110009486868
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22700136
[Journal Article] Evaluation of Game Tree Search Methods by Game Records2010
- Author(s)
  Takeuchi, S.; Kaneko, T.; Yamaguchi, K.
- Journal Title
  
  IEEE Transactions on Computational Intelligence and AI in Games
  
  Volume: 2(4) Pages: 288-302
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22700136
[Journal Article] 新規節点で固定深さの探索を行うdf-pnの拡張2010
- Author(s)
  金子知適, 田中哲朗, 山口和紀, 川合慧
- Journal Title
  
  情報処理学会論文誌
  
  Volume: 51(11) Pages: 2040-2047
- NAID
  110007970805
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22700136
[Journal Article] 新規節点で固定深さの探索を行うdf-pnの拡張2010
- Author(s)
  金子知適,田中哲朗,山口和紀,川合慧
- Journal Title
  
  情報処理学会論文誌
  
  Volume: Vol.51,No.11 Pages: 2040-2047
- NAID
  110007970805
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22700136
[Journal Article] Parallel Depth First Proof Number Search2010
- Author(s)
  T.Kaneko
- Journal Title
  
  Association for Advancement of Artificial Intelligence(AAAI)
  
  Volume: 24 Pages: 95-100
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22700136
[Journal Article] コンピュータ将棋の不遜な挑戦:4大規模クラスタシステムでの実行-GPS 将棋の試み-2010
- Author(s)
  金子知適
- Journal Title
  
  情報処理
  
  Volume: 51(8) Pages: 1008-1015
- NAID
  110007681773
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22700136
[Journal Article] 将棋の棋譜を利用した, 大規模な評価関数の調整2008
- Author(s)
  金子, 他
- Journal Title
  
  第13回ゲーム・プログラミングワークショップ予稿集 11
  
  Pages: 152-159
- NAID
  170000080354
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19700129
[Journal Article] 将棋の棋譜を利用した,大規模な評価関数の調整2008
- Author(s)
  金子知適,山口和紀
- Journal Title
  
  第13回ゲーム・プログラミングワークショップ
  
  Pages: 152-159
- NAID
  170000080354
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19700129
[Journal Article] Evaluation of Monte Carlo Tree Search and the Application to Go2008
- Author(s)
  S. Takeuchi, T. Kaneko and K. Yamaguchi
- Journal Title
  
  IEEE Symposium on Computational Intelligence and Games (CIG 08)
  
  Pages: 191-198
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19700129
[Journal Article] 棋譜データにおける勝率を利用したモンテカルロ木探索の性能評価手法2008
- Author(s)
  竹内聖悟,金子知適,山口和紀
- Journal Title
  
  第13回ゲーム・プログラミングワークショップ
  
  Pages: 9-16
- NAID
  170000080328
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19700129
[Journal Article] 駒の関係を利用した将棋の評価関数の学習2007
- Author(s)
  金子, 他
- Journal Title
  
  情報処理学会論文誌 48
  
  Pages: 3438-3445
- NAID
  110006530805
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19700129
[Journal Article] 兄弟節点の比較に基づく評価関数の調整2007
- Author(s)
  金子知適
- Journal Title
  
  第12回ゲーム・プログラミングワークショップ
  
  Pages: 9-16
- NAID
  170000080295
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19700129
[Journal Article] 勝率に基づく評価関数の評価と最適化2007
- Author(s)
  竹内聖悟,金子知適,林芳樹,山口和紀,川合慧
- Journal Title
  
  情報処理学会論文誌 Vol. 48 No. 11
  
  Pages: 3446-3454
- NAID
  110006530806
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19700129
[Journal Article] DFUCTの囲碁への応用について2007
- Author(s)
  吉本晴洋,岸本章宏,金子知適,美添一樹
- Journal Title
  
  第12回ゲーム・プログラミングワークショップ
  
  Pages: 30-35
- NAID
  170000080298
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19700129
[Journal Article] Visualization and Adjustment of Evaluation Functions Based on Evaluation Values and Win Probability2007
- Author(s)
  S. Takeuchi, T. Kaneko, K. Yamaguchi and S. Kawai
- Journal Title
  
  Twenty-Second Conference on Artificial Intelligence (AAAI07)
  
  Pages: 858-863
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19700129
[Journal Article] 情報量に基づく探索制御手法--チェスにおけるSingular Extensionへの応用--2007
- Author(s)
  竹内聖悟,金子知適,山口和紀
- Journal Title
  
  第12回ゲーム・プログラミングワークショップ
  
  Pages: 52-59
- NAID
  170000080301
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19700129
[Journal Article] マーティンミュラー.証明数と反証数を用いたλ探索2007
- Author(s)
  副田俊介、美添一樹、岸本章宏、金子知適、田中哲朗
- Journal Title
  
  情報処理学会論文誌 Vol. 48 No. 11
  
  Pages: 3455-3462
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19700129
[Journal Article] 駒の関係を利用した将棋の評価関数の学習2007
- Author(s)
  金子知適,田中哲朗,山口和紀,川合慧
- Journal Title
  
  情報処理学会論文誌 Vol. 48 No. 11
  
  Pages: 3438-3445
- NAID
  110006530805
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-19700129
[Journal Article] Dual Lambda Search and its Application to Shogi Endgames2006
- Author(s)
  Soeda, S., Kaneko, T., Tanaka, T.
- Journal Title
  
  Advances in Computer Games, LNCS 4250, Springer-Verlag 4250
  
  Pages: 126-139
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-17500086
[Journal Article] Monte Carlo Go Has a Way to Go2006
- Author(s)
  Yoshimoto, H., Yoshizoe, K., Kaneko, T., Kishimoto, A, Taura, K.
- Journal Title
  
  21st National Conf. on Artificial Intelligence (AAAI-06) 21
  
  Pages: 1070-1075
- Data Source
  KAKENHI-PROJECT-17500086
[Journal Article] 勝率と評価値の歪みに基づく評価関数調整法-将棋における進行度差の評価-2006
- Author(s)
  竹内聖悟, 林芳樹, 金子知適, 川合慧
- Journal Title
  
  第11回ゲーム・プログラミングワークショップ,情報処理学会 11
  
  Pages: 56-63
- NAID
  170000080269
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-17500086
[Journal Article] Adjustment of Evaluation Functions Based on Relation Between Static Values and Win Ratios -- Evaluation of Safety Difference Between Both Kings in Shogi --2006
- Author(s)
  Takeuchi, S., Hayashi, Y., Kaneko, T., Kawai, S.
- Journal Title
  
  11th Game Programming Workshop of IPSJ 11
  
  Pages: 56-63
- NAID
  170000080269
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-17500086
[Journal Article] ゲーム情報学とゲーム情報学研究会2006
- Author(s)
  金子知適
- Journal Title
  
  情報処理 47(12)
  
  Pages: 1378-1379
- Data Source
  KAKENHI-PROJECT-16700130
[Journal Article] Monte Carlo Go Has a Way to Go2006
- Author(s)
  Yoshimoto, H., Yoshizoe, K., Kaneko, T., Kishimoto, A., Taura, K.
- Journal Title
  
  21st National Conf. on Artificial Intelligence (AAA I-06) 21
  
  Pages: 1070-1075
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-17500086
[Journal Article] 勝率と評価値の歪みに基づく評価関数調整法 --将棋における進行度差の評価--、2006
- Author(s)
  竹内聖悟, 林芳樹, 金子知適, 川合慧
- Journal Title
  
  第11回ゲーム・プログラミングワークショップ,情報処理学会 11
  
  Pages: 56-63
- NAID
  170000080269
- Data Source
  KAKENHI-PROJECT-17500086
[Journal Article] Dual Lambda Search and its Application to Shogi Endgames2006
- Author(s)
  Soeda, S., Kaneko, T., Tanaka, T.
- Journal Title
  
  Advances in Computer Games, LNCS 4250 (Springer-Verlag) 4250
  
  Pages: 126-139
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-17500086
[Journal Article] Monte Carlo Go Has A Way to Go2006
- Author(s)
  Yoshimoto, H., Yoshizoe, K., Kaneko, T., Kishimoto, A., Taura, K.
- Journal Title
  
  21st National Conf.on Artificial Intelligence (AAAI-06) 21
  
  Pages: 1070-1075
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-17500086
[Journal Article] 新規節点で深さ優先探索を利用するdf-pnアルゴリズム2005
- Author(s)
  金子他
- Journal Title
  
  第10回ゲーム・プログラミングワークショップ 15
  
  Pages: 1-8
- Data Source
  KAKENHI-PROJECT-16700130
[Journal Article] 新規節点で深さ優先探索を利用するdf-pnアルゴリズム2005
- Author(s)
  金子知適
- Journal Title
  
  第10回ゲーム・プログラミングワークショップ
  
  Pages: 1-8
- Data Source
  KAKENHI-PROJECT-17500086
[Journal Article] 棋譜に基づく詰めろの指標2004
- Author(s)
  竹内, 金子, 川合
- Journal Title
  
  第9回ゲームプログラミングワークショップ
  
  Pages: 48-53
- NAID
  170000080213
- Data Source
  KAKENHI-PROJECT-16700130
[Journal Article] Towards Evaluation of Shogi Endgames with Speed of Attack2004
- Author(s)
  S.Soeda, T.Kaneko, T.Tanaka
- Journal Title
  
  The 9th Game Programming Workshop
  
  Pages: 125-128
- NAID
  170000080229
- Data Source
  KAKENHI-PROJECT-16700130
[Journal Article] 詰将棋におけるdf-ph^+探索のための,展開後の証明数と反証数を予測する評価関数2004
- Author(s)
  金子, 田中, 山口, 川合
- Journal Title
  
  第9回ゲームプログラミングワークショップ
  
  Pages: 14-21
- Data Source
  KAKENHI-PROJECT-16700130
[Journal Article] Evaluation Functions for df-pn^+ in Shogi based on Prediction of Proof and Disproof Numbers after Expansion2004
- Author(s)
  Kaneko, T., Tanaka, T., Yamaguchi, K., Kawai, S.
- Journal Title
  
  The 9^<th> Game Programming Workshop IPSJ
  
  Pages: 14-21
- NAID
  170000080208
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-15500084
[Journal Article] 詰将棋におけるdf-pn+探索のための,展開後の証明数と反証数を予測する評価関数2004
- Author(s)
  金子知適
- Journal Title
  
  情報処理学会第9回ゲームプログラミングワークショップ 9
  
  Pages: 14-21
- NAID
  170000080208
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15500084
[Journal Article] 駒の関係を利用した将棋の評価関数2003
- Author(s)
  金子知適
- Journal Title
  
  第8回ゲーム・プログラミングワークショップ
  
  Pages: 14-21
- NAID
  170000080180
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-13224013
[Journal Article] Automated Identification of Patterns in Evaluation Functions2003
- Author(s)
  Kaneko, T., Yamaguchi, K., Kawai, S.
- Journal Title
  
  Advances in Computer Games Many Games, Many Challenges
  
  Pages: 279-298
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-15500084
[Journal Article] Automated Identification of Patterns in Evaluation Functions2003
- Author(s)
  Kaneko, T.
- Journal Title
  
  Advances in Computer Games Many Games, Many Challenges
  
  Pages: 279-298
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15500084
[Journal Article] Evaluation Functions Based on Pairs of Pieces2003
- Author(s)
  Kaneko, T., Tanaka, T., Yamaguchi, K., Kawai, S.
- Journal Title
  
  The 8^<th> Game Programming Workshop IPSJ
  
  Pages: 14-21
- NAID
  170000080180
- Description
  「研究成果報告書概要(欧文)」より
- Data Source
  KAKENHI-PROJECT-15500084
[Journal Article] 将棋プログラムにおける棋譜を利用した囲いの評価2003
- Author(s)
  金子知適
- Journal Title
  
  夏のプログラミングシンポジウム予稿集
  
  Pages: 63-70
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-13224013
[Journal Article] 駒の関係を利用した将棋の評価関数2003
- Author(s)
  金子知適
- Journal Title
  
  情報処理学会第8回ゲームプログラミングワークショップ 8
  
  Pages: 14-21
- NAID
  170000080180
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-15500084
[Journal Article] Automated Identification of Pattern in Evaluation Functions for General Game Players2003
- Author(s)
  Tomoyuki Kaneko
- Journal Title
  
  Proceedings of the 10th ADVANCES IN COMPUTER GAMES CONFERENCE
  
  Pages: 279-298
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-13224013
[Journal Article] Pattern Selection Problem for Automatically Generating Evaluation Functions for General Game Player2002
- Author(s)
  Tomoyuki Kaneko
- Journal Title
  
  Proceedings of the 7th Game Programming Workshop
  
  Pages: 28-35
- NAID
  170000080155
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-13224013
[Journal Article] ゲームプログラムのためのパターン型評価関数の自動生成法2002
- Author(s)
  金子知適
- Journal Title
  
  情報処理学会論文誌 43・10
  
  Pages: 3040-3047
- NAID
  110002771157
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-13224013
[Journal Article] 述語論理で表された特徴関数の,ネットワーク型局面評価器への自動変換2002
- Author(s)
  金子知適
- Journal Title
  
  電子情報通信学会論文誌 J85-D-1
  
  Pages: 1074-1082
- NAID
  110004066686
- Description
  「研究成果報告書概要(和文)」より
- Data Source
  KAKENHI-PROJECT-13224013
[Journal Article] 将棋の棋譜を利用した大規模な評価関数の学習
- Author(s)
  金子知適, 山口和紀
- Journal Title
  
  情報処理学会論文誌
  
  Volume: Vol.51,No.12 Pages: 2141-2148
- NAID
  110007970815
- Peer Reviewed
- Data Source
  KAKENHI-PROJECT-22700136
[Presentation] 将棋における変則ルール「将棋 81 万」の提案と深層強化学習への応用2023
- Author(s)
  出村金子
- Organizer
  第28回ゲームプログラミングワークショップ
- Data Source
  KAKENHI-PROJECT-21H03570
[Presentation] 4x3 盤面の 2048 の完全解析2023
- Author(s)
  山下金子
- Organizer
  第28回ゲームプログラミングワークショップ
- Data Source
  KAKENHI-PROJECT-21H03570
[Presentation] 4x3 盤面の 2048 の完全解析2023
- Author(s)
  山下金子
- Organizer
  第28回ゲームプログラミングワークショップ
- Data Source
  KAKENHI-PROJECT-21K19816
[Presentation] 将棋における変則ルール「将棋 81 万」の提案と深層強化学習への応用2023
- Author(s)
  出村金子
- Organizer
  第28回ゲームプログラミングワークショップ
- Data Source
  KAKENHI-PROJECT-21K19816
[Presentation] ProcgenBenchmark における汎化性能を高める強化学習2020
- Author(s)
  徐金子
- Organizer
  第25回ゲームプログラミングワークショップ
- Data Source
  KAKENHI-PROJECT-18K19832
[Presentation] Application of dream to the board game geister2020
- Author(s)
  Chen and Kaneko
- Organizer
  25th game programming workshop
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-18K19832
[Presentation] Training japanese mahjong agent with two dimension feature representation2020
- Author(s)
  Honghai and Kaneko
- Organizer
  25th game programming workshop
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-18K19832
[Presentation] Improve counterfactual regret minimization for card game cheat2020
- Author(s)
  Yi and Kaneko
- Organizer
  25th game programming workshop
- Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-18K19832
[Presentation] スタークラフト II のミニゲームにおけるマルチタスク強化学習2019
- Author(s)
  徐凡超金子知適
- Organizer
  第24回ゲームプログラミングワークショップ
- Data Source
  KAKENHI-PROJECT-18K19832
[Presentation] Improving Mahjong Agent by Predicting Types of Yaku2019
- Author(s)
  Long Honghai and Tomoyuki Kaneko
- Organizer
  The 24th Game Programming Workshop
- Data Source
  KAKENHI-PROJECT-18K19832
[Presentation] Training Agents with Long-range Information in Deep Reinforcement Learning2019
- Author(s)
  Hanhua Zhu and Tomoyuki Kaneko
- Organizer
  The 24th Game Programming Workshop
- Data Source
  KAKENHI-PROJECT-18K19832
[Presentation] Counterfactual Regret Minimisation for playing the multiplayer bluffing dice game Dudo2019
- Author(s)
  Quentin Gendre and Tomoyuki Kaneko
- Organizer
  The 24th Game Programming Workshop
- Data Source
  KAKENHI-PROJECT-18K19832
[Presentation] An Extension of Counterfactual Regret Minimization for Multiplayer Card Games2019
- Author(s)
  Yu Cao and Tomoyuki Kaneko
- Organizer
  The 24th Game Programming Workshop
- Data Source
  KAKENHI-PROJECT-18K19832
[Presentation] Enhancing Sample Efficiency of Deep Reinforcement Learning to Master the Mini-games of StarCraft II2019
- Author(s)
  ZheJie Hu and Tomoyuki Kaneko
- Organizer
  The 24th Game Programming Workshop
- Data Source
  KAKENHI-PROJECT-18K19832
[Presentation] どうぶつしょうぎを用いた AlphaZero の手法の調査2019
- Author(s)
  中屋敷太一金子知適
- Organizer
  第24回ゲームプログラミングワークショップ
- Data Source
  KAKENHI-PROJECT-18K19832
[Presentation] Utilizing History Information in Acquiring Strategies for Board Game Geister by Deep Counterfactual Regret Minimization2019
- Author(s)
  Chen Chen and Tomoyuki Kaneko
- Organizer
  The 24th Game Programming Workshop
- Data Source
  KAKENHI-PROJECT-18K19832
[Presentation] Back Prediction in the Game of Go2019
- Author(s)
  Tang Jiachen and Tomoyuki Kaneko
- Organizer
  The 24th Game Programming Workshop
- Data Source
  KAKENHI-PROJECT-18K19832
[Presentation] Performance of Counterfactual Regret Minimization with Self-Confirming Equilibrium2019
- Author(s)
  Cheng Yi and Tomoyuki Kaneko
- Organizer
  The 24th Game Programming Workshop
- Data Source
  KAKENHI-PROJECT-18K19832
[Presentation] 様々な学習戦略と学習環境におけるHybrid Reward Architectureの性能の評価2018
- Author(s)
  藤村悠太朗金子知適
- Organizer
  人工知能学会全国大会
- Data Source
  KAKENHI-PROJECT-16H02927
[Presentation] Settlers of Catanにおけるマップ自動生成の研究2017
- Author(s)
  黄柱皓, 金子知適
- Organizer
  ゲームプログラミングワークショップ2017
- Data Source
  KAKENHI-PROJECT-16H02927
[Presentation] 将棋における勾配ブースティング木を用いた評価関数2017
- Author(s)
  渡辺敬介, 金子知適
- Organizer
  ゲームプログラミングワークショップ2017
- Data Source
  KAKENHI-PROJECT-16H02927
[Presentation] Style Transfer in Playing Shogi Based on Generative Adversarial Networks2017
- Author(s)
  Shanchuan Wan and Tomoyuki Kaneko
- Organizer
  ゲームプログラミングワークショップ2017
- Data Source
  KAKENHI-PROJECT-16H02927
[Presentation] Hybrid Reward Architecture を用いたリアルタイムな意思決定の改善2017
- Author(s)
  藤村悠太朗, 金子知適
- Organizer
  ゲームプログラミングワークショップ
- Data Source
  KAKENHI-PROJECT-16H02927
[Presentation] 人狼ゲームエージェントにおける行動選択手法の比較2017
- Author(s)
  王天鶴, 金子知適
- Organizer
  ゲームプログラミングワークショップ
- Data Source
  KAKENHI-PROJECT-16H02927
[Presentation] ゲーム木に基づく並列探索での下位局面の分担2016
- Author(s)
  横山秀, 金子知適
- Organizer
  ゲーム・プログラミングワークショップ 2016
- Place of Presentation
  箱根セミナーハウス(神奈川県・箱根)
- Year and Date
  2016-11-04
- Data Source
  KAKENHI-PROJECT-16H02927
[Presentation] Machine Learning of Evaluation Functions and Playing Styles in Shogi2016
- Author(s)
  T. Kaneko
- Organizer
  TCGA
- Place of Presentation
  台中(台湾)
- Year and Date
  2016-06-04
- Invited / Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-16H02927
[Presentation] 経験的知識と類似局面を用いた証明数探索の効率化2016
- Author(s)
  島野拓也, 金子知適
- Organizer
  ゲーム・プログラミングワークショップ 2016
- Place of Presentation
  箱根セミナーハウス(神奈川県・箱根)
- Year and Date
  2016-11-04
- Data Source
  KAKENHI-PROJECT-16H02927
[Presentation] UCT における Prior knowledge と方策学習を用いた個性の実現2016
- Author(s)
  渡辺順哉, 金子知適
- Organizer
  ゲーム・プログラミングワークショップ 2016
- Place of Presentation
  箱根セミナーハウス(神奈川県・箱根)
- Year and Date
  2016-11-04
- Data Source
  KAKENHI-PROJECT-16H02927
[Presentation] Machine Learning of Evaluation Functions and Playing Styles in Shogi2016
- Author(s)
  T. Kaneko
- Organizer
  JAIST Symposium on Game & Entertainment Technology & Its Application
- Place of Presentation
  JAIST (石川県能美市)
- Year and Date
  2016-02-10
- Invited / Int'l Joint Research
- Data Source
  KAKENHI-PROJECT-25330432
[Presentation] モンテカルロ木探索における子孫の勝敗確定時のプレイアウト結果の修正2016
- Author(s)
  今川孝久, 金子知適
- Organizer
  ゲーム・プログラミングワークショップ 2016
- Place of Presentation
  箱根セミナーハウス(神奈川県・箱根)
- Year and Date
  2016-11-04
- Data Source
  KAKENHI-PROJECT-16H02927
[Presentation] 将棋における棋風を学習するための棋譜分析の取り組み2015
- Author(s)
  大森翔太朗, 金子知適
- Organizer
  第20回ゲームプログラミングワークショップ
- Place of Presentation
  軽井沢学習研修所(長野県北佐久郡)
- Year and Date
  2015-11-06
- Data Source
  KAKENHI-PROJECT-25330432
[Presentation] モンテカルロ木探索を統合したプレイアウト方策の最適化2015
- Author(s)
  渡辺順哉, 美添一樹, 金子知適
- Organizer
  第20回ゲームプログラミングワークショップ
- Place of Presentation
  軽井沢学習研修所(長野県北佐久郡)
- Year and Date
  2015-11-06
- Data Source
  KAKENHI-PROJECT-25330432
[Presentation] 囲碁における LinUCT の性能評価2015
- Author(s)
  万代悠作, 金子知適
- Organizer
  第20回ゲームプログラミングワークショップ
- Place of Presentation
  軽井沢学習研修所(長野県北佐久郡)
- Year and Date
  2015-11-06
- Data Source
  KAKENHI-PROJECT-25330432
[Presentation] コンピュータ将棋はなぜ強いのか -その技術と進歩-2015
- Author(s)
  金子知適
- Organizer
  2015年自然科学研究教育センター・シンポジウム
- Place of Presentation
  慶應義塾大学 (神奈川県、横浜市)
- Year and Date
  2015-09-26
- Invited
- Data Source
  KAKENHI-PROJECT-25330432
[Presentation] 評価値を用いて展開制御したゲーム木に基づく並列探索2015
- Author(s)
  横山秀, 金子知適
- Organizer
  第20回ゲームプログラミングワークショップ
- Place of Presentation
  軽井沢学習研修所(長野県北佐久郡)
- Year and Date
  2015-11-06
- Data Source
  KAKENHI-PROJECT-25330432
[Presentation] Real Time Commentary System for Shogi2012
- Author(s)
  T. Kaneko
- Organizer
  1st Workshop on Games and NLP (GAMNLP-12)
- Place of Presentation
  Ishikawa Ongakudo (Kanazawa, Japan)
- Data Source
  KAKENHI-PROJECT-22700136
[Presentation] 本当に強い!-800台の探索GPWナイトセッション2012
- Author(s)
  金子知適
- Organizer
  第17回ゲームプログラミングワークショップ
- Place of Presentation
  箱根
- Data Source
  KAKENHI-PROJECT-22700136
[Presentation] 個性を持った将棋プログラムを目指してー強くするという目標を達成した後にー2012
- Author(s)
  松原仁, 保木邦仁, 伊藤毅志, 山下宏, 金子知適
- Organizer
  CEDEC2012
- Place of Presentation
  パシフィコ横浜 (横浜)
- Invited
- Data Source
  KAKENHI-PROJECT-22700136
[Presentation] RealTime Commentary System for hogiTomoyuki Kaneko2012
- Author(s)
  Tomoyuki Kaneko
- Organizer
  1st Workshop on Games and NLP (GAMNLP-12)
- Place of Presentation
  金沢
- Year and Date
  2012-02-03
- Data Source
  KAKENHI-PROJECT-22700136
[Presentation] Infinite Connect-Four is Solved: Draw.Yoshiaki Yamaguchi2012
- Author(s)
  Kazunori Yamaguchi, Tetsuro Tanaka and Tomoyuki Kaneko
- Organizer
  Advances in Computer Games
- Place of Presentation
  ティルブルフオランダ
- Data Source
  KAKENHI-PROJECT-22700136
[Presentation] 個性を持った将棋プログラムを目指してー強くするという目標を達成した後にーパネル松原仁2012
- Author(s)
  保木邦仁,伊藤毅志,山下宏金子知適 CEDEC2012
- Place of Presentation
  横浜
- Year and Date
  2012-08-20
- Data Source
  KAKENHI-PROJECT-22700136
[Presentation] 最高峰を目指すコンピュータ将棋第2011
- Author(s)
  金子知適
- Organizer
  52回プログラミング・シンポジウム
- Place of Presentation
  ニューウェルシティ湯河原
- Year and Date
  2011-01-08
- Data Source
  KAKENHI-PROJECT-22700136
[Presentation] The Global Landscape of Objective Functions for the Optimization of Shogi Piece Values with Game-TreeSearch2011
- Author(s)
  Kunihito Hoki and Tomoyuki Kaneko
- Organizer
  Advances in Computer Games
- Place of Presentation
  ティルブルフオランダ
- Data Source
  KAKENHI-PROJECT-22700136
[Presentation] Scalable Distributed Monte-CarloTree Search.Kazuki Yoshizoe2011
- Author(s)
  Akihiro Kishimoto, Tomoyuki Kaneko
- Organizer
  Haruhiro Yoshimoto and Yutaka Ishikawa. In Proceedings of the 4th Symposium on Combinatorial Search (SoCS'2011),pages 180-187
- Place of Presentation
  バルセロナスペイン
- Data Source
  KAKENHI-PROJECT-22700136
[Presentation] Analysis of Evaluation-Function Learning by Comparison of Sibling Nodes2011
- Author(s)
  T.Kaneko, K.Hoki
- Organizer
  Advances in Computer Games 13
- Place of Presentation
  Tirburg(オランダ)
- Year and Date
  2011-11-21
- Data Source
  KAKENHI-PROJECT-22700136
[Presentation] Analysis of Evaluation-FunctionLearning by Comparison of SiblingNodes2011
- Author(s)
  Tomoyuki Kaneko and Kunihito Hoki
- Organizer
  Advances in Computer Games
- Place of Presentation
  ティルブルフオランダ
- Data Source
  KAKENHI-PROJECT-22700136
[Presentation] Minimax探索最適化の関数形保木邦仁2010
- Author(s)
  金子知適
- Organizer
  第15回ゲームプログラミングワークショップ
- Place of Presentation
  箱根
- Data Source
  KAKENHI-PROJECT-22700136
[Presentation] 最善手の予測に基づくゲーム木探索の分散並列実行2010
- Author(s)
  金子知適,田中哲朗
- Organizer
  第15回ゲームプログラミングワークショップ
- Place of Presentation
  箱根
- Data Source
  KAKENHI-PROJECT-22700136
[Presentation] 将棋における2010
- Author(s)
  竹内聖悟,金子知適,山口和紀
- Organizer
  第15回ゲームプログラミングワークショップ
- Place of Presentation
  箱根
- Data Source
  KAKENHI-PROJECT-22700136
[Presentation] Parallel Depth First Proof NumberSearch2010
- Author(s)
  Tomoyuki Kaneko1
- Organizer
  Twenty-Fourth Conference on Artificial Intelligence (AAAI2010)
- Place of Presentation
  アトランタアメリカ
- Year and Date
  2010-07-04
- Data Source
  KAKENHI-PROJECT-22700136
[Presentation] コンピュータ将棋の挑戦-トッププロに追いつく日、追い越す日は来るのか?2010
- Author(s)
  金子知適
- Organizer
  第16回ビジュアリゼーションカンファレンス
- Place of Presentation
  東京
- Year and Date
  2010-11-05
- Data Source
  KAKENHI-PROJECT-22700136
[Presentation] チェスの棋譜を利用した評価関数の学習2010
- Author(s)
  山本一成,竹内聖悟,金子知適,保木邦仁
- Organizer
  第15回ゲームプログラミングワークショップ
- Place of Presentation
  箱根
- Data Source
  KAKENHI-PROJECT-22700136
[Presentation] 兄弟節点の比較に基づく評価関数の調整2007
- Author(s)
  金子, 他
- Organizer
  ゲーム・プログラミングワークショップ
- Place of Presentation
  箱根
- Data Source
  KAKENHI-PROJECT-19700129

1. MASUHARA Hidehiko (40280937)

# of Collaborated Projects: 3 results

# of Collaborated Products: 0 results
2. KAWAI Satoru (50011664)

# of Collaborated Projects: 2 results

# of Collaborated Products: 6 results
3. YAMAGUCHI Kazunori (80158097)

# of Collaborated Projects: 2 results

# of Collaborated Products: 3 results
4. TAMAI Tetsuo (60217172)

# of Collaborated Projects: 1 results

# of Collaborated Products: 0 results
5. SHIBAYAMA Etsuya (80162642)

# of Collaborated Projects: 1 results

# of Collaborated Products: 0 results
6. NAKAJIMA Shin (60350211)

# of Collaborated Projects: 1 results

# of Collaborated Products: 0 results
7. UBAYASHI Naoyasu (80372762)

# of Collaborated Projects: 1 results

# of Collaborated Products: 0 results
8. IGARASHI Atsushi (40323456)

# of Collaborated Projects: 1 results

# of Collaborated Products: 0 results
9. 青山幹雄 (40278073)

# of Collaborated Projects: 1 results

# of Collaborated Products: 0 results

Kaneko Tomoyuki 金子 知適

KANEKO Tomoyuki 金子 知適

Research Projects

Research Products

Co-Researchers

Onto generalization of reinforcement learning agents through diversity and understanding of environmentsPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

Deep reinforcement learning in multi-player imperfect-information gamesPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

deep reinforcement learning for imperfect and multi-player environmentsPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

Machine learning and distributed game-tree search in gamesPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

Explanation of positional evaluation by computer programsPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

Decision support with search and machine learning techniquesPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

Automated acquisition of empirical knowledge and its application to search techniquesPrincipal Investigator

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

Wide Range Application of Status Evaluation Function

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

アルゴリズムに応じた知識獲得手法の研究Principal Investigator

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

Acquisition of Evaluation Function of high precision by Learning

Principal Investigator

Project Period (FY)

Research Category

Research Field

Research Institution

High Reliability Component-Based Software Engineering

Principal Investigator

Project Period (FY)

Research Category

Review Section

Research Institution

[Book] コンピュータ将棋の進歩 6--プロ棋士に並ぶ--2012

Author(s)

Total Pages

Publisher

Data Source

[Book] 人間に勝つコンピュータ将棋の作り方2012

Author(s)

Total Pages

Publisher

Kaneko Tomoyuki 金子知適

KANEKO Tomoyuki 金子知適