Reinforcement learning for linear continuous-time systems: An incremental learning approach

Research output: Contribution to journalArticle

Abstract

In this paper, we introduce a novel reinforcement learning (RL) scheme for linear continuous-time dynamical systems. Different from traditional batch learning algorithms, an incremental learning approach is developed, which provides a more efficient way to tackle the on-line learning problem in real-world applications. We provide concrete convergence and robust analysis on this incremental-learning algorithm. An extension to solving robust optimal control problems is also given. Two simulation examples are also given to illustrate the effectiveness of our theoretical result.

Original languageEnglish (US)
Article number8651896
Pages (from-to)433-440
Number of pages8
JournalIEEE/CAA Journal of Automatica Sinica
Volume6
Issue number2
DOIs
StatePublished - Mar 1 2019

    Fingerprint

Keywords

  • Adaptive optimal control
  • robust dynamic programming
  • value iteration (VI)

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Information Systems
  • Artificial Intelligence

Cite this