学会等発表 - 倉重 健太郎

分割表示  91 件中 61 - 80 件目  /  全件表示 >>
  1. 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),2014年02月,Fukui,日本国

  2. 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),ISAROB,The Nineteenth International Symposium on Artificial Life and Robotics 2014 (AROB 19th 2014),(頁 48-51),2014年01月,Beppu,日本国

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

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

  4. The Proposal for Deciding Effective Action using Prediction of Internal Robot State Based on Internal State and Action

    Masashi Sugimoto, Kentarou Kurashige,International Symposium onMicro-NanoMechatronics and Human Science,IEEE,proceedings of International Symposium on Micro-NanoMechatronics and Human Science,(頁 221-226),2013年11月,Nagoya,日本国

  5. The Proposal for Prediction of Internal Robot State Based on Internal State and Action

    Masashi Sugimoto, Kentarou Kurashige,IWACIII2013,Japan SOciety for Fuzzy Theory and intelligent informatics (SOFT),Proc. of IWACIII2013 CD-ROM,2013年10月,Shanghai,中華人民共和国

  6. Proposal of learning method which selects objectives based on the state

    Hironori Miura, Kentarou Kurashige,2013 IEEE Workshop on Robotic Intelligence in Informationally StructuredSpace at2013 IEEE Symposium Series on Computational Intelligence(RiiSS at SSCI),IEEE,Proceedings of 2013 IEEE Workshop on Robotic Intelligence in Informationally Structured Space at 2013 IEEE Symposium Series on Computational Intelligence(RiiSS at SSCI),(頁 119-124),2013年04月,Singapore,シンガポール共和国

  7. Reduction of state space on reinforcement learning by sensor selection

    Yasutaka Kishima, Kentarou Kurashige,2012 International Symposium on Micro-NanoMechatronics and Human Science(MSH2012&Micro-Nano Global COE),IEEE,Proceedings of 2012 International Symposium on Micro-NanoMechatronics and Human Science(MSH2012&Micro-Nano Global COE),(頁 138-143),2012年11月,Nagoya,日本国

  8. Estimate of current state based on experience in POMDP for Reinforcement Learning

    Yoshiki Miyazaki, Kentarou Kurashige,the seventeenth InternationalSymposium on Artificial Life and Robotics,Organizing Committee of International Symposium on Artificial Life and Robotics,Proceedings ofthe seventeenth International Symposium on Artificial Life and Robotics,2012年01月,Beppu,日本国

  9. Reduction of learning space by making a choice of sensor information

    Yasutaka Kishima, Kentarou Kurashige, Toshinobu Numata,the seventeenth International Symposiumon Artificial Life and Robotics,Organizing Committee of International Symposium on Artificial Life and Robotics,Proceedings of the seventeenth International Symposium on Artificial Life and Robotics,2012年01月,Beppu,日本国

  10. Proposal of method "Motion Space" to express movement of the robot

    Naoki Kitayama, Kentarou Kurashige,IWACIII2011,Japan SOciety for Fuzzy Theory and intelligent informatics (SOFT),Proc. of IWACIII2011 CD-ROM,2011年11月,Suzhou,中華人民共和国

  11. Suggestion of Probabilistic Reward-Independent Knowledgefor Dynamic Environment in Reinforcement Learning

    NodokaShibuya, Yoshiki Miyazaki, Kentarou Kurashige,2011 Int. Symp. on Micro-NanoMechatronics and Human Science,IEEE,2011 Int. Symp. on Micro-NanoMechatronics and Human Science CD-ROM,2011年11月,Nagoya,日本国

  12. 学生による授業の枠をこえたデモンストレーション発表会AcaDemoSについて

    畑中雅彦,開発技術研究会平成22年度研究発表会,開発技術研究会,開発技術研究会平成22年度研究発表会講演要旨集,2010年12月,北海道・室蘭市

  13. Use of reward - independent knowledge on reinforcement learning for dynamic environment

    YoshikiMiyazaki and Kentarou Kurashige,The International Conference on Advanced Computer Science and Information Systems,Faculty fo Computer Science Universitas Indonesia,Proc. of the International Conference on Advanced Computer Science and Information Systems,2010年11月20日,Bali,インドネシア共和国

  14. THE GROWTH OF INDIVIDUAL INTELLIGENCE IN GROUPS OF AGENTS BYAUTONOMOUS SELECTION OF OTHERS TO COMMUNICATE TO

    Yasutaka Kishima, Kentarou Kurashige,WAC 2010,IEEE SMC Society,WAC 2010 Congress CD-ROM,2010年09月,Kobe, Japan,日本国

  15. Use of the knowledge which is independence on reward in Reinforcement Learning

    Yoshiki Miyazaki, Kentarou Kurashige,2009 IEEE International Symposium on Computational Intelligencein Robotics and Automation,IEEE,Proc. of International Symposium on Computational Intelligence in Robotics and Automation,2009年12月15日,Daejeon, Korea,大韓民国

  16. 教示における動きの汎化

    池田憲弘, 倉重健太郎,HAIシンポジウム2009,人工知能学会,HAIシンポジウム2009(CD-ROM),(頁 2D-2),2009年12月04日,東京都・東京工業大学大岡山キャンパス西9号館

  17. 複数教員の多角的な指導による学生懇話会の試み (第3報)

    畑中雅彦,開発技術研究会平成20年度研究発表会,開発技術研究会,開発技術研究会平成20年度研究発表会講演要旨集,(頁 39-40),2008年12月,北海道・室蘭市

  18. A RELATIONSHIP BETWEEN ABILITY OF PERCEPTION AND LEARNING EFFICIENCY

    Yukiko Onoue, Kentarou Kurashige,WAC 2008,IEEE SMC Society, IEEE Systems Council,WAC 2008 Congress CD-ROM,2008年09月28日,Hawaii, USA,アメリカ合衆国

  19. Growth ofindividual intelligence using communication

    Yasutaka Kishima, Kentarou Kurashige,SCIS&ISIS 2008,Japan SOciety for Fuzzy Theory and intelligent informatics (SOFT),SCIS&ISIS 2008(CD-ROM),2008年09月17日,Nagoya, Japan,日本国

  20. Therobotlearning by using sense of pain

    Kentarou Kurashige, Yukiko Onoue,The Third International Symposium on Humanized Systems,Japan Society for the Promotion of Science,Japan Society of Kansei Engineering,Muroran Institute of Technology,Proceedings of International Symposium on Humanized Systems 2007,2007年09月13日,Japan, Muroran,日本国

このページの先頭へ▲