Discounted Markov decision processes with utility constraints

Authors:
Yoshinobu Kadota;Masami Kurano;Masami Yasuda
Affiliations:
-;-;-
Venue:
Computers & Mathematics with Applications
Year:
2006

Citing 4
Cited 0

On Fan's minimax theorem

Mathematical Programming: Series A and B
Discounted MDP's: distribution functions and exponential utility maximization

SIAM Journal on Control and Optimization
Target-level criterion in Markov decision processes

Journal of Optimization Theory and Applications
Optimization by Vector Space Methods

Optimization by Vector Space Methods

Quantified Score

Hi-index	0.09

Visualization

Abstract

We consider utility-constrained Markov decision processes. The expected utility of the total discounted reward is maximized subject to multiple expected utility constraints. By introducing a corresponding Lagrange function, a saddle-point theorem of the utility constrained optimization is derived. The existence of a constrained optimal policy is characterized by optimal action sets specified with a parametric utility.