Policy iteration-mode monotone convergence of generalized policy iteration for discrete-time linear systems

Tae Yoon Chun, Jin Bae Park, Yoon Ho Choi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper presents the properties of policy iteration (PI)-mode monotone convergence and stability of generalized policy iteration (OPI) algorithms for discrete-time (DT) linear systems. OPI is one of the reinforcement learning based dynamic programming (DP) methods for solving optimal control problems, interacting policy evaluation and policy improvement steps. To deal with the convergence and stability of OPI, several equivalent equations are derived. Then, as a result, the PI-mode monotone convergence (one behaves like PI) and stability of OPI algorithm are proved under the some initial conditions which are closely related with Lyapunov approach. Finally, some numerical simulations are performed to verify the proposed convergence and stability properties.

Original languageEnglish
Title of host publicationICCAS 2013 - 2013 13th International Conference on Control, Automation and Systems
Pages454-458
Number of pages5
DOIs
Publication statusPublished - 2013
Event2013 13th International Conference on Control, Automation and Systems, ICCAS 2013 - Gwangju, Korea, Republic of
Duration: 2013 Oct 202013 Oct 23

Publication series

NameInternational Conference on Control, Automation and Systems
ISSN (Print)1598-7833

Other

Other2013 13th International Conference on Control, Automation and Systems, ICCAS 2013
Country/TerritoryKorea, Republic of
CityGwangju
Period13/10/2013/10/23

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Science Applications
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Policy iteration-mode monotone convergence of generalized policy iteration for discrete-time linear systems'. Together they form a unique fingerprint.

Cite this