Multiple-environment MDPs (MEMDPs) capture finite sets of MDPs that share the states but differ in the transition dynamics. These models form a proper subclass of partially observable MDPs (POMDPs). We consider the synthesis of policies that robustly satisfy an almost-sure reachability property in MEMDPs, that is, one policy that satisfies a property for all environments. For POMDPs, deciding the existence of robust policies is an EXPTIME-complete problem. In this paper, we show that this problem is PSPACE-complete for MEMDPs, while the policies in general require exponential memory. We exploit the theoretical results to develop and implement an algorithm that shows promising results in synthesizing robust policies for various benchmarks.
@article{arxiv.2301.11296,
title = {Robust Almost-Sure Reachability in Multi-Environment MDPs},
author = {Marck van der Vegt and Nils Jansen and Sebastian Junges},
journal= {arXiv preprint arXiv:2301.11296},
year = {2024}
}