Mean-Variance Optimization in Markov Decision Processes
Machine Learning
2011-05-02 v1 Artificial Intelligence
Abstract
We consider finite horizon Markov decision processes under performance measures that involve both the mean and the variance of the cumulative reward. We show that either randomized or history-based policies can improve performance. We prove that the complexity of computing a policy that maximizes the mean reward under a variance constraint is NP-hard for some cases, and strongly NP-hard for others. We finally offer pseudopolynomial exact and approximation algorithms.
Cite
@article{arxiv.1104.5601,
title = {Mean-Variance Optimization in Markov Decision Processes},
author = {Shie Mannor and John Tsitsiklis},
journal= {arXiv preprint arXiv:1104.5601},
year = {2011}
}
Comments
A full version of an ICML 2011 paper