Optimal Tracking Control for Multi-player Non-Zero-Sum Games of Continuous-Time Linear Systems with Unknown Dynamics
Zhen Huang, Yidong Tu, Shuping He · 2022 13th Asian Control Conference (ASCC) · 2022
In this paper, a novel online reinforcement learning (RL) algorithm is presented to solve the optimal tracking control (OTC) problem of non-zero-sum (NZS) games for multi-player systems. We first build the augmented system, and then derive the N augmented coupled game algebraic Riccati equations (CGARE). In addition, a online policy iteration (PI) approach is proposed to solve CGARE without requiring any knowledge of the system dynamics. Finally, the effectiveness of our proposed approach is illustrated by numerical simulation.