Nonzero-sum games using actor-critic neural networks: A dynamic event-triggered adaptive dynamic programming

• Published in: Information sciences Vol. 662; p. 120236
• Main Authors: Shen, Hao, Li, Ziwei, Wang, Jing, Cao, Jinde
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.03.2024
• Subjects: Actor-critic neural networks; Adaptive dynamic programming; Dynamic event-triggered mechanism; Nonzero-sum games; Nonzero-sum games; Actor-critic neural networks; Adaptive dynamic programming; Dynamic event-triggered mechanism
• ISSN: 0020-0255; 1872-6291
• DOI: 10.1016/j.ins.2024.120236

This paper mainly investigates the nonzero-sum games of nonlinear systems with unmatched uncertainty by using actor-critic neural networks. To handle the unmatched components, an auxiliary system with a modified value function is constructed, which transforms the robust stabilization issue into the optimal control issue. Then, a novel dynamic event-triggering condition is designed to further save bandwidth via introducing a dynamic variable. In addition, the actor-critic algorithm is employed in adaptive dynamic programming to achieve Nash equilibrium, which is tuned together with the control policy. By constructing appropriate Lyapunov functions, a criterion is established to ensure that the considered system is uniformly ultimately bounded. Finally, the effectiveness of the developed strategy is demonstrated by an example.