Localization and a Distributed Local Optimal Solution Algorithm for a Class of Multi-Agent Markov Decision Processes

We consider discrete-time factorial Markov Decision Processes (MDPs) in multiple decision-makers environment for infinite horizon average reward criterion with a general joint reward structure but a factorial joint state transition structure. We introduce the “localization” concept that a global MDP is localized for each agent such that each agent needs to consider a local MDP defined only with its own state and action spaces. Based on that, we present a gradient-ascent like iterative distributed algorithm that converges to a local optimal solution of the global MDP. The solution is an autonomous joint policy in that each agent’s decision is based on only its local state.