Central-limit approach to risk-aware Markov decision processes
Optimization and Control
2015-12-03 v1 Systems and Control
Abstract
Whereas classical Markov decision processes maximize the expected reward, we consider minimizing the risk. We propose to evaluate the risk associated to a given policy over a long-enough time horizon with the help of a central limit theorem. The proposed approach works whether the transition probabilities are known or not. We also provide a gradient-based policy improvement algorithm that converges to a local optimum of the risk objective.
Cite
@article{arxiv.1512.00583,
title = {Central-limit approach to risk-aware Markov decision processes},
author = {Pengqian Yu and Jia Yuan Yu and Huan Xu},
journal= {arXiv preprint arXiv:1512.00583},
year = {2015}
}
Comments
arXiv admin note: text overlap with arXiv:1403.6530 by other authors