Average Cost Dynamic Programming Equations For Controlled Markov Chains With Partial Observations
Author:
- V. S. Borkar.VBV. S. Borkar.
- 1 January 2000
- journal article
- Published by Society for Industrial & Applied Mathematics (SIAM) in SIAM Journal on Control and Optimization
- Vol. 39 (3) , 673-681
Abstract
The value function for the average cost control of a class of partially observed Markov chains is derived as the "vanishing discount limit," in a suitable sense, of the value functions for the corresponding discounted cost problems. The limiting procedure is justified by bounds derived using a simple coupling argument.Keywords
This publication has 10 references indexed in Scilit:
- Further Topics on Discrete-Time Markov Control Processes1999
- Probability Theory1995
- White-Noise Representations in Stochastic Realization TheorySIAM Journal on Control and Optimization, 1993
- Discrete-Time Controlled Markov Processes with Average Cost Criterion: A SurveySIAM Journal on Control and Optimization, 1993
- Ergodic control of partially observed Markov processes with equivalent transition probabilitiesApplicationes Mathematicae, 1993
- On the average cost optimality equation and the structure of optimal policies for partially observable Markov decision processesAnnals of Operations Research, 1991
- Remarks on the existence of solutions to the average cost optimality equation in Markov decision processesSystems & Control Letters, 1990
- Optimal Control for Partially Observed DiffusionsSIAM Journal on Control and Optimization, 1982
- Optimal Infinite-Horizon Undiscounted Control of Finite Probabilistic SystemsSIAM Journal on Control and Optimization, 1980
- Survey of Measurable Selection TheoremsSIAM Journal on Control and Optimization, 1977