Acrobot control by learning the switching of multiple controllers

Junichiro Yoshimoto, Masaya Nishimura, Yoichi Tokita, Shin Ishii

Research output: Contribution to journalArticlepeer-review

31 Citations (Scopus)

Abstract

Reinforcement learning (RL) has been applied to constructing controllers for nonlinear systems in recent years. Since RL methods do not require an exact dynamics model of the controlled object, they have a higher flexibility and potential for adaptation to uncertain or nonstationary environments than methods based on traditional control theory. If the target system has a continuous state space whose dynamic characteristics are nonlinear, however, RL methods often suffer from unstable learning processes. For this reason, it is difficult to apply RL methods to control tasks in the real world. In order to overcome the disadvantage of RL methods, we propose an RL scheme combining multiple controllers, each of which is constructed based on traditional control theory. We then apply it to a swinging-up and stabilizing task of an acrobot with a limited torque, which is a typical but difficult task in the field of nonlinear control theory. Our simulation result showed that our method was able to realize stable learning and to achieve fairly good control.

Original languageEnglish
Pages (from-to)67-71
Number of pages5
JournalArtificial Life and Robotics
Volume9
Issue number2
DOIs
Publication statusPublished - 05-2005
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Biochemistry, Genetics and Molecular Biology(all)
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Acrobot control by learning the switching of multiple controllers'. Together they form a unique fingerprint.

Cite this