Average optimality for risk-sensitive control with general state space

Abstract

This paper deals with discrete-time Markov control processes on a general state space. A long-run risk-sensitive average cost criterion is used as a performance measure. The one-step cost function is nonnegative and possibly unbounded. Using the vanishing discount factor approach, the optimality inequality and an optimal stationary strategy for the decision maker are established.

arXiv commentPublished at http://dx.doi.org/10.1214/105051606000000790 in the Annals of Applied Probability (http://www.imstat.org/aap/) by the Institute of Mathematical Statistics (http://www.imstat.org)

Cited by in corpus (9)

• Zero-sum Risk-Sensitive Stochastic Games
• Markov Decision Processes with Risk-Sensitive Criteria: An Overview
• Infinite horizon risk-sensitive control of diffusions without any blanket stability assumptions
• Average-Cost Optimality Results for Borel-Space Markov Decision Processes with Universally Measurable Policies
• Risk-sensitive control of continuous time Markov chains
• Continuous-time Markov decision processes under the risk-sensitive average cost criterion
• Continuous-time Markov decision processes with exponential utility
• On Strategic Measures and Optimality Properties in Discrete-Time Stochastic Control with Universally Measurable Policies
• Time-inconsistent Risk-sensitive Equilibrium for Countable-stated Markov Decision Processes