H∞追従性能補償器を備えたリアルタイム強化学習制御システム

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2012/06/01

タイトル(英語): A Real-time Reinforcement Learning Control System with H∞ Tracking Performance Compensator

著者名: 内山　祥吾（山口大学大学院理工学研究科），大林　正直（山口大学大学院理工学研究科），呉本　尭（山口大学大学院理工学研究科），小林　邦和（山口大学大学院理工学研究科）

著者名(英語): Shogo Uchiyama (Graduate School of Science Engineering, Yamaguchi University), Masanao Obayashi (Graduate School of Science Engineering, Yamaguchi University), Takashi Kuremoto (Graduate School of Science Engineering, Yamaguchi University), Kunikazu Kobayashi (Graduate School of Science Engineering, Yamaguchi University)

キーワード: 強化学習，ロバスト制御，H∞制御，ロバスト強化学習，リアルタイム　　reinforcement learning，robust control，H∞control，robust reinforcement learning，real-time

要約(英語): Robust control theory generally guarantees robustness and stability of the closed-loop system. It however requires a mathematical model of the system to design the control system. It therefore can't often deal with nonlinear systems due to difficulty of modeling of the system. On the other hand, reinforcement learning methods can deal with nonlinear systems without any mathematical model. It however usually doesn't guarantee the stability of the system control. In this paper, we propose a "Real-time Reinforcement Learning Control System (RRLCS)" through combining reinforcement learning to treat unknown nonlinear systems and robust control theory to guarantee the robustness and stability of the system. Moreover, we analyze the stability of the proposed system using H∞ tracking performance and Lyapunov function. Finally, through the computer simulation for controlling an inverted pendulum system, we show the effectiveness of the proposed method.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.132 No.6 （2012） 特集：データ指向型モデリング/予測/制御

本誌掲載ページ: 1008-1015 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/132/6/132_1008/_article/-char/ja/