Shibuya Takeshi
- Articles
- Reinforcement Learning Method for Cases Where the State Observation Period Is Larger Than the Action Decision Period
Yotsukura Masaki; Shibuya Takeshi
Proceedings of the SICE Annual Conference 2018/pp.832-835, 2018-09 - Reinforcement Learning Focusing on Safe Exploration with Conscientious Demonstration
Miyamae Kengo; Shibuya Takeshi
Proceedings of the SICE Annual Conference 2018/pp.827-831, 2018-09 - パーシステントホモロジーを用いた画像の構図の位相的な特徴量
二神廉太郎; 澁谷 長史
電子情報通信学会論文誌 D/J101-D(5)/pp.769-779, 2018-05 - Development of Hammering Test Support System for Concrete Surface
萩原 恒樹; 山口 友之; 八十島 章; 澁谷 長史
The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec)/2017/pp.1P1-B06, 2017 - Real-Time Defect Detection Method without Training Data for Hammering Test Support System
Hagiwara Koki; Yasojima Akira; Shibuya Takeshi; Yamaguchi...
Proceedings of the IEEE/SICE International Symposium on System Integration/pp.205-209, 2019-01 - センサのむだ時間の大きさが周期的に変化する環境のための強化学習に関する基礎検討
四ツ倉昌輝; 澁谷 長史
第72回知的システム研究会(SIC2017-2)論文集/pp.5-6, 2017-12 - 部分的に等しい状態行動系列を持つデモンストレーションを利用した強化学習
宮前 研吾; 澁谷 長史
第72回知的システム研究会(SIC2017-2)論文集/pp.7-8, 2017-12 - 行動に一次遅れがかかる環境のための強化学習に関する一検討
渋沢 慎吾; 澁谷 長史
第71回知的システム研究会(SIC2017-1)論文集/pp.3-6, 2017-07 - 行動出力にむだ時間要素や一次遅れ要素を持つ環境のための強化学習に関する実験的検討
渋沢 慎吾; 澁谷 長史
第45回 知能システムシンポジウム資料/pp.C4-4_1-4, 2018-03 - 畳み込みニューラルネットワークを用いたドリルビットの異常音識別に関する基礎的検討
水野駿; 澁谷 長史; 川村洋平
電気学会研究会資料 システム研究会/pp.21-24, 2017-06 - Classification for Sequential Data Involving Human Trial and Error
Enoki Shintaro; Shibuya Takeshi; Yano Hiroaki
Proceedings of the SICE Annual Conference 2017/pp.1284-1289, 2017-09 - Reinforcement Learning in the Environment Where Optimal Action Value Function Is Partly Discontinuous
Shibusawa Shingo; Shibuya Takeshi
2016 55TH ANNUAL CONFERENCE OF THE SOCIETY OF INSTRUMENT AND CONTROL ENGINEERS OF JAPAN (SICE)/pp.1545-1550, 2016 - A Method Deciding Topological Relationship for Self-Organizing Maps by Persistent Homology Analysis
Futagami Rentaro; Shibuya Takeshi
2016 55TH ANNUAL CONFERENCE OF THE SOCIETY OF INSTRUMENT AND CONTROL ENGINEERS OF JAPAN (SICE)/pp.1064-1069, 2016 - Profit Sharing reducing the occurrences of accidents by predicted action-safety degree
Tamaru Junki; Shibuya Takeshi
2015 10TH ASIAN CONTROL CONFERENCE (ASCC)/pp.2468-2473, 2015-05 - A study of efficient reinforcement learning using the relative angle of two objects
Moriaki Onishi; Takeshi Shibuya
Proceedings on the 16th International Symposium on Advanced Intelligent Systems/pp.1091-1098, 2015-11 - Profit Sharing reducing the occurrences of accidents by predicted action-safety degree
Junki Tamaru; Shibuya Takeshi
Proceedings of the 10th Asian Control Conference 2015 (ASCC 2015)/pp.2468-2473, 2015-05 - Reinforcement learning with nonstationary reward depending on the episode
Shibuya Takeshi; Yasunobu Seiji
In Proceedings of the 2011 IEEE International Conference on Systems, Man, and Cybernetics/pp.2145-2150, 2011 - Space-time Support System using Simplified Time-Change Fuzzy Set
Xiang Liu; Takeshi Shibuya; Seiji Yasunobu
Proceedings of the 2013 Joint IFSA World Congress NAFIPS Annual Meeting (IFSA/NAFIPS)/pp.1502-1507, 2013-06 - Partially Observable Markov Decision Process and Reinforcement Learning
澁谷 長史
計測と制御/52(4)/pp.374-380, 2013-04 - リレー解説「強化学習の最近の発展」にあたって
牧野 貴樹; 澁谷 長史
計測と制御/52(1)/pp.64-67, 2013-01 - Effectiveness of a Game-Based Class for Interdisciplinary Energy Systems Education in Engineering Courses
Suzuki K.; Shibuya T.; Kanagawa T.
Sustainability Science/16/pp.523-539, 2021-02 - Space-time Fuzzy Inference and Applications using Simplified Time-Change Fuzzy Set
Xiang Liu; Takeshi Shibuya; Seiji Yasunobu
Proceedings of the 6th International Conference on Soft Computing and Intelligent Systems/pp.1606-1609, 2012-11 - Complex-valued Profit Sharing with Multiple Phase Changes
澁谷 長史; 島田 慎吾; 濱上 知樹
計測自動制御学会論文集 = Transactions of the Society of Instrument and Control Engineers/45(11)/pp.597-604, 2009-11 - Q-learning with Action Values in Complex Numbers
澁谷 長史; 濱上 知樹
The IEICE transactions on information and systems D/J91-D(5)/p.1286-1295, 2008-01 - A Substitute Target Learning-based Inverted Pendulum Swing-Up Control System
Syafiq Fauzi Kamarulzaman; Takeshi Shibuya; Seiji Yasunobu
Proc. of the 11th International Symposium on Advanced Intelligent Systems (SCIS&ISIS2010)/p.1-6, 2010-12 - more...
- Reinforcement Learning Method for Cases Where the State Observation Period Is Larger Than the Action Decision Period