Communication and Control Co-design in Non-cooperative Games

摘要

In this article, we revisit a communication-control co-design problem for a class of two-player stochastic differential games on an infinite horizon. Each 'player' represents two active decision makers, namely a scheduler and a remote controller, which cooperate to optimize over a global objective while competing with the other player. Each player's scheduler can only intermittently relay state information to its respective controller due to associated cost/constraint to communication. The scheduler's policy determines the information structure at the controller, thereby affecting the quality of the control inputs. Consequently, it leads to the classical communication-control trade-off problem. A high communication frequency improves the control performance of the player on account of a higher communication cost, and vice versa. Under suitable information structures of the players, we first compute the Nash controller policies for both players in terms of the conditional estimate of the state. Consequently, we reformulate the problem of computing Nash scheduler policies (within a class of parametrized randomized policies) into solving for the steady-state solution of a generalized Sylvester equation. Since the above-mentioned reformulation involves infinite sum of powers of the policy parameters, we provide a projected gradient descent-based algorithm to numerically compute a Nash equilibrium using a truncated polynomial approximation. Finally, we demonstrate the performance of the Nash control and scheduler policies using extensive numerical simulations.