国際会議Proceedings - 倉重　健太郎

21. Action selection using priority for each task -Realization of effective processing by dynamical update of priority-

    Takuya Masaki, Kentarou Kurashige，Proceedings of 2017 6th International Conference on Informatics, Electronics and Vision & 2017 7th International Symposium in Computational Medical and Health Technology，IEEE，2017年09月，Himeji, Hyogo

    

22. A Study for effectiveness of Dimensionality Reduction for State-action Pair Prediction -Training set reduction using Tendency-

    Masashi Sugimoto, Naoya Iwamoto, Robert Johnston, Keizo Kanazawa, Yukinori Misaki, Kentarou Kurashige，Proceedings of the Third International Conference on Electronics and Software Science (ICESS2017)，(頁 19 ～ 28)，2017年08月，Takamatsu, Japan

    

23. Application and Performance Evaluation of a Lifting Device with Alternating Rotation Hoist

    Hanchao Li, Daisuke Harada, Naohiko Hanajima, Hidekazu Kajiwara, Kentaro Kurashige, Yoshinori Fujihira, Masato Mizukami，Proc. of 2016 IEEE/SICE International Symposium on System Integration，(頁 385 ～ 390)，Article Number:, pp.385-390,December 13-15,2016,Sapporo,Japan,DOI:10.1109/SII.2016.7844029,ISSN:2474-2325,E-ISBN: 9，IEEE，2016年12月，Sapporo

    

24. A STUDY OF EFFECTIVENESS OF DYNAMICALLY VARYING SAMPLING RATE FOR STATE-ACTION PAIR PREDICTION

    Masashi Sugimoto, Naoya Iwamoto, Robert W. Johnston, Keizo Kanazawa, Yukinori Misaki, Kentarou Kurashige，Proceedings of the International Conference on Electronics and Software Science，(頁 79 ～ 87)，SDIWC，2016年11月，Takamatsu, Japan

    

25. IoT-aware Context Respectful Counseling Agent

    Yukiko Yamamoto, Tetsuo Shinozaki, Setsuo Tsuruta, Kentarou Kurashige, Rainer Knauf，Proceedings of the IEEE International conference on systems,man,and cybernetics，(頁 4729 ～ 4736)，IEEE，2016年10月，Budapest, Hungary

    

26. Action Learning to Single Robot Using MARL with Repeated Consultation: Realization of Repeated Consultation Interruption for the Adaptation to Environmental Change

    Yoh TAKADA, Kentarou KURASHIGE，Intelligent Robotics and Applications, Proceedings, Part II，(頁 371 ～ 382)，Springer International Publishing，2016年08月，Tokyo, Japan

    

27. Action selection using each task priority:Realization of asynchrony action selection and update priorities

    Takuya Masaki, Kentarou Kurashige，2016 Joint 8th International Conference on Soft Computing and Intelligent Systems and 2016 17th International Symposium on Advanced Intelligent Systems，(頁 908 ～ 911)，IEEE，2016年08月，Sapporo, Hokkaido

    

28. Effective action selection under multi task by ignoring tasks and limiting tasks

    Takuya Masaki, Kentarou Kurashige，Proceedings of World Automation Congress 2016，(頁 1 ～ 6)，Article Number:1570248406，2016年08月，Puerto Rico

    

29. Nodding Behavioral Context Respectful Counseling Agent

    Yukiko Yamamoto, Tetsuo Shinozaki, Setsuo Tsuruta, Kentarou Kurashige, Rainer Knauf，Proceedings of World Automation Congress 2016，(頁 1 ～ 6)，Article Number:1570277693，2016年08月，Puerto Rico

    

30. A Study on the Deciding an Action Based on the Future Probabilistic Distribution

    Masashi SUGIMOTO, Kentarou KURASHIGE，Intelligent Robotics and Applications, Proceedings, Part II，(頁 383 ～ 394)，Springer International Publishing，2016年08月，Tokyo, Japan

    

31. The Proposal for Compensation to the Action of Motion Control based on the Prediction of State-action Pair

    Masashi Sugimoto, Kentarou Kurashige，Proceedings of the International Conference on Electronics and SoftwareScience，(頁 35 ～ 84)，CD-ROM，2015年07月，Takamatsu, Japan

    

32. Action Learning to single robot using MAS -A proposal of Agents action decision method based repeated consultation-

    Shuhei Chiba, Kentarou Kurashige，Proceedings of the 10th Asian Control Conference，IEEE，2015年05月，Kota Kinabalu, Malaysia

    

33. Teaching a series of actions by the universal evaluations of each sensory information

    Kentarou Kurashige, Kaoru Nikaido，2015 IEEE Congress on Evolutionary Computation，(頁 2341 ～ 2346)，IEEE，2015年05月，Sendai, Japan

    

34. The Proposal for Real-time Sequential-decision for Optimal Action using Flexible-weight Coefficient based on the State-Action Pair

    Masashi Sugimoto, Kentarou Kurashige，2015 IEEE Congress on Evolutionary Computation，(頁 544 ～ 551)，IEEE，2015年05月，Sendai, Japan

    

35. Self-generation of reward in reinforcement learning by universal rules of interaction with the external environment'

    Kentarou Kurashige, Kaoru Nikaido，2014 IEEE Symposium on Robotic Intelligence in Informationally Structured Space Proceedings，(頁 92 ～ 97)，IEEE，2014年12月，Orlando, Florida, U.S.A.

    

36. Real-time Sequentially Decision for Optimal Action using Prediction of the State-Action Pair

    Masashi Sugimoto, Kentarou Kurashige，Proceedings of 2014 International Symposium on Micro-NanoMechatronics and Human Science，(頁 199 ～ 204)，IEEE，2014年11月，Nagoya, Japan

    

37. Self-Generation of reward by moderate-based index in reinforcement learning

    Kentarou Kurashige, Kaoru Nikaido，The International Workshop on Advanced Computational Intelligence and Intelligent Informatics 2014(IWACIII2014)，(頁 IWACIII2014-03 ～ )，2014年02月，Fukui

    

38. Control of exploration and exploitation using information content'

    Nodoka Shibuya, Kentarou Kurashige，The Nineteenth International Symposium on Artificial Life and Robotics 2014 (AROB 19th 2014)，(頁 48 ～ 51)，ISAROB，2014年01月，Beppu

    

39. Self-Generation of Reward by Sensor Input in Reinforcement Learning

    Kaoru Nikaido, Kentarou Kurashige，2013 Second International Conference on Robot, Vision and Signal Processing，(頁 270 ～ 273)，IEEE，2013年12月，Kitakyushu

    

40. The Proposalfor Deciding Effective Action using Prediction of Internal Robot State Based on Internal State and Action

    Masashi Sugimoto, Kentarou Kurashige，Proceedings of 2013 International Symposium on Micro-NanoMechatronics and Human Science，(頁 221 ～ 226)，2013年11月，Nagoya