On the adaptive control of a class of partially observed Markov decision processes

Authors:
Shun-Pin Hsu;Dong-Ming Chuang;Ari Arapostathis
Affiliations:
National Chung-Hsing University, Electrical Engineering, Taichung, Taiwan;The University of Texas, Electrical & Computer Engineering, Austin, TX;The University of Texas, Electrical & Computer Engineering, Austin, TX
Venue:
ACC'09 Proceedings of the 2009 conference on American Control Conference
Year:
2009

Citing 7
Cited 0

Stochastic systems: estimation, identification and adaptive control

Stochastic systems: estimation, identification and adaptive control
Discrete-time controlled Markov processes with average cost criterion: a survey

SIAM Journal on Control and Optimization
Ergodic control of partially observed Markov chains

Systems & Control Letters
Adaptive Markov Control Processes

Adaptive Markov Control Processes
Dynamic Programming and Stochastic Control

Dynamic Programming and Stochastic Control
Stochastic Optimal Control: The Discrete-Time Case

Stochastic Optimal Control: The Discrete-Time Case
Dynamic Programming

Dynamic Programming

Quantified Score

Hi-index	0.00

Visualization

Abstract

We study the adaptive control problems of a class of discrete-time partially observed Markov decision processes whose transition kernels are parameterized by a unknown vector. Given a sequence of parameter estimates converging to the true value with probability 1, we propose an adaptive control policy and show that under some conditions this policy is self-optimizing in the long-run average sense.