Team Games Optimality Conditions of Distributed Stochastic Differential Decision Systems with Decentralized Noisy Information Structures

Abstract

We consider a team game reward, and we derive a stochastic Pontryagin's maximum principle for distributed stochastic differential systems with decentralized noisy information structures. Our methodology utilizes the semi martingale representation theorem, variational methods, and backward stochastic differential equations. Furthermore, we derive necessary and sufficient optimality conditions that characterize team and person-by-person optimality of decentralized strategies. Finally, we apply the stochastic maximum principle to several examples from the application areas of communications, filtering and control.