Artificial Life and Robotics

, Volume 13, Issue 2, pp 526–530 | Cite as

A robust reinforcement learning using the concept of sliding mode control

  • M. Obayashi
  • N. Nakahara
  • T. Kuremoto
  • K. Kobayashi
Original Article

Abstract

In this article, we propose a new control method using reinforcement learning (RL) with the concept of sliding mode control (SMC). Some remarkable characteristics of the SMC method are good robustness and stability for deviations from control conditions. On the other hand, RL may be applicable to complex systems that are difficult to model. However, applying reinforcement learning to a real system has a serious problem, i.e., many trials are required for learning. We intend to develop a new control method with good characteristics for both these methods. To realize it, we employ the actor-critic method, a kind of RL, to unite with the SMC. We are able to verify the effectiveness of the proposed control method through a computer simulation of inverted pendulum control without the use of inverted pendulum dynamics. In particular, it is shown that the proposed method enables the RL to learn in fewer trials than the reinforcement learning method.

Key words

Robust Reinforcement learning Actor-critic Sliding mode control Inverted pendulum 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Morimoto J, Doya K (2005) Robust reinforcement learning. Neural Comput 17:335–359CrossRefMathSciNetGoogle Scholar
  2. 2.
    Sutton RS, Barto AG (1998) Reinforcement learning. An introduction. MIT Press, CambridgeGoogle Scholar
  3. 3.
    Koga M (2000) Numerical computation by MATX. Tokyo Denki University Press, TokyoGoogle Scholar

Copyright information

© International Symposium on Artificial Life and Robotics (ISAROB). 2009

Authors and Affiliations

  • M. Obayashi
    • 1
  • N. Nakahara
    • 1
  • T. Kuremoto
    • 1
  • K. Kobayashi
    • 1
  1. 1.Graduate School of Science and EngineeringYamaguchi UniversityUbe, YamaguchiJapan

Personalised recommendations