Distributionally robust chance constrained Markov decision process with Kullback-Leibler divergence
Optimization and Control
2023-08-01 v2
Abstract
This paper considers the distributionally robust chance constrained Markov decision process with random reward and ambiguous reward distribution. We consider individual and joint chance constraint cases with Kullback-Leibler divergence based ambiguity sets centered at elliptical distributions or elliptical mixture distributions, respectively. We derive tractable reformulations of the distributionally robust individual chance constrained Markov decision process problems and design a new hybrid algorithm based on the sequential convex approximation and line search method for the joint case. We carry out numerical tests with a machine replacement problem.
Cite
@article{arxiv.2305.02167,
title = {Distributionally robust chance constrained Markov decision process with Kullback-Leibler divergence},
author = {Tian Xia and Jia Liu and Abdel Lisser},
journal= {arXiv preprint arXiv:2305.02167},
year = {2023}
}