Mean-field risk sensitive control and zero-sum games for Markov chains
Probability
2018-01-26 v1 Optimization and Control
Abstract
We establish existence of controlled Markov chain of mean-field type with unbounded jump intensities by means of a fixed point argument using the Wasserstein distance. Using a Markov chain entropic backward SDE approach, we further suggest conditions for existence of an optimal control and a saddle-point for respectively a control problem and a zero-sum differential game associated with risk sensitive payoff functionals of mean-field type.
Keywords
Cite
@article{arxiv.1801.08413,
title = {Mean-field risk sensitive control and zero-sum games for Markov chains},
author = {Salah Eddine Choutri and Boualem Djehiche},
journal= {arXiv preprint arXiv:1801.08413},
year = {2018}
}
Comments
arXiv admin note: text overlap with arXiv:1606.04244