A Bayesian Network Approach to Control of Networked Markov Decision Processes

The authors consider the problem of finding an optimal feedback controller for a networked Markov decision process. Specifically, they consider a network of interconnected subsystems, where each subsystem evolves as a Markov Decision Process (MDP). A subsystem is connected to its neighbors via links over which signals are delayed. They consider centralized control of such networked MDPs. The controller receives delayed state information from each of the subsystem, and it chooses control actions for all subsystems.