コンテンツメニュー
publish year2005 - 2009 keywordreinforcement learning school大学院理工学研究科（工学）
publish year
2005 - 2009 7
keyword
reinforcement learning 7 actor-critic 2 sliding mode control 2 swarm behavior 2 TD-error 1 actor-critic algorithm 1 autonomous robot 1 chaotic neural network 1 eligibility 1 goal-exploration problem 1 hierarchical memory structure 1 immune network 1 inverted pendulum 1 inverted pendulum control problem 1 maze search problem 1 meta-learning 1 meta-parameter 1 multi-agent system 1 neuro-fuzzy net 1 neuro-fuzzy system 1 robust 1 robustness 1 semi-Markov decision process 1 state variable filter 1
Show More
Show Less
resource type
conference paper 4 journal article 3
school
大学院理工学研究科（工学） 7
Result 7 Items
Id (<span class="translation_missing" title="translation missing: en.view.desc">Desc</span>)
A robust reinforcement learning system using sliding mode control with variable filters
Proceedings of International Automatic Control Conference Volume 2009
Creators : Obayashi Masanao | Yamada Katsumi | Kuremoto Takashi | Kobayashi Kunikazu Date Issued : 2009-11
A meta-learning method based on temporal difference error
Lecture notes in computer science Volume 5863
Creators : Kobayashi Kunikazu | Mizoue Hiroyuki | Kuremoto Takashi | Obayashi Masanao Publishers : Springer Date Issued : 2009
An improved internal model for swarm formation and adaptive swarm behavior acquisition
Journal of circuits, systems, and computers Volume 18 Issue 8
Creators : Kuremoto Takashi | Yamano Yuki | Obayashi Masanao | Kobayashi Kunikazu Publishers : World Scientific Date Issued : 2009-12
A reinforcement learning system with chaotic neural neworks-based adaptive hierarchical memory structure for autonomous robots
Proceedings of the International Conference on Control, Automation and Systems Volume 2008
Creators : Obayashi Masanao | Narita Kenichiro | Kuremoto Takashi | Kobayashi Kunikazu Date Issued : 2008
A neuro-fuzzy learning system for adaptive swarm behaviors dealing with continuous state space
Lecture notes in computer science Volume 5227
Creators : Kuremoto Takashi | Obayashi Masanao | Kobayashi Kunikazu | Adachi Hirotaka | Yoneda Kentaro Publishers : Springer Date Issued : 2008
A reinforcement learning method based on immune network adapted to semi Markov decision process
Proceedings of the international symposium on artificial life and robotics Volume 13
Creators : Kogawa Nagahisa | Obayashi Masanao | Kobayashi Kunikazu | Kuremoto Takashi Date Issued : 2008
A robust reinforcement learning using concept of sliding mode control
Proceedings of the international symposium on artificial life and robotics Volume 13
Creators : Obayashi M. | Nakahara N. | Kuremoto T. | Kobayashi K. Date Issued : 2008
Related Creatrors
Kuremoto Takashi 7 Obayashi Masanao 7 Kobayashi Kunikazu 7
Yamaguchi Univ. Library
〒753-8511　1677-1 Yoshida, Yamaguchi, Yamaguchi

E-Mail: yunoca@yamaguchi-u.ac.jp
Copyright（C）2006-2018 Yamaguchi University Library. All Rights Reserved.