By Topic

Potential-based online policy iteration algorithms for Markov decision processes

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Hai-Tao Fang ; Lab. of Syst. & Control, Acad. of Math. & Syst. Sci., Beijing, China ; Xi-Ren Cao

Performance potentials play a crucial role in performance sensitivity analysis and policy iteration of Markov decision processes. The potentials can be estimated on a single sample path of a Markov process. In this paper, we propose two potential-based online policy iteration algorithms for performance optimization of Markov systems. The algorithms are based on online estimation of potentials and stochastic approximation. We prove that with these two algorithms the optimal policy can be attained after a finite number of iterations. A simulation example is given to illustrate the main ideas and the convergence rates of the algorithms.

Published in:

Automatic Control, IEEE Transactions on  (Volume:49 ,  Issue: 4 )