Temporal Difference-Based Policy Iteration for Optimal Control of Stochastic Systems

Kang Cheng (), Shumin Fei (), Kanjian Zhang (), Xiaomei Liu () and Haikun Wei ()
Additional contact information
Kang Cheng: Southeast University
Shumin Fei: Southeast University
Kanjian Zhang: Southeast University
Xiaomei Liu: Southeast University
Haikun Wei: Southeast University

Journal of Optimization Theory and Applications, 2014, vol. 163, issue 1, No 8, 165-180

Abstract: Abstract In this paper, a unified policy iteration approach is presented for the optimal control problem of stochastic system with discounted average cost and continuous state space. The approach consists of temporal difference learning-based potential function approximation algorithms and performance difference formula-based policy improvement. The approximation algorithms are derived by solving the Poisson equation-based fixed-point equation, which can be viewed as continuous versions of least squares policy evaluation algorithm and least squares temporal difference algorithm. The simulations are provided to illustrate the effectiveness of the approach.

Keywords: Optimal control; Performance potential; Temporal difference; Policy iteration (search for similar items in EconPapers)
Date: 2014
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://link.springer.com/10.1007/s10957-013-0418-1 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:joptap:v:163:y:2014:i:1:d:10.1007_s10957-013-0418-1

Ordering information: This journal article can be ordered from
http://www.springer. ... cs/journal/10957/PS2

DOI: 10.1007/s10957-013-0418-1

Access Statistics for this article

Journal of Optimization Theory and Applications is currently edited by Franco Giannessi and David G. Hull

More articles in Journal of Optimization Theory and Applications from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().