Role of Externally Provided Randomness in Stochastic Teams and Zero-sum Team Games

Abstract: Stochastic team decision problem is extensively studied in literature and the existence of optimal solution is obtained in recent literature. The value of information in statistical problem and decision theory is classical problem. Much of earlier does not qualitatively describe role of externally provided private and common randomness in stochastic team problem and team vs team zero sum game. In this paper, we study the role of extrenally provided private or common randomness in stochastic team decision. We make observation that the randomness independent of environment does not benefit either team but randomness dependent on environment benefit teams and decreases the expected cost function. We also studied LQG team game with special information structure on private or common randomness. We extend these study to problem team vs team zero sum game. We show that if a game admits saddle point solution, then private or common randomness independent of environment does not benefit either team. We also analyze the scenario when a team with having more information than other team which is dependent on environment and game has saddle point solution, then team with more information benefits. This is also illustrated numerically for LQG team vs team zero sum game. Finally, we show for discrete team vs team zero sum game that private randomness independent of environment benefits team when there is no saddle point condition. Role of common randomness is discussed for discrete game.