A variational formula for risk-sensitive reward
Optimization and Control
2015-01-06 v1 Information Theory
math.IT
Probability
Abstract
We derive a variational formula for the optimal growth rate of reward in the infinite horizon risk-sensitive control problem for discrete time Markov decision processes with compact metric state and action spaces, extending a formula of Donsker and Varadhan for the Perron-Frobenius eigenvalue of a positive operator. This leads to a concave maximization formulation of the problem of determining this optimal growth rate.
Keywords
Cite
@article{arxiv.1501.00676,
title = {A variational formula for risk-sensitive reward},
author = {Venkatachalam Anantharam and Vivek Shripad Borkar},
journal= {arXiv preprint arXiv:1501.00676},
year = {2015}
}
Comments
35 pages