TY - JOUR
T1 - Event-Triggered ADP for Nonzero-Sum Games of Unknown Nonlinear Systems
AU - Zhao, Qingtao
AU - Sun, Jian
AU - Wang, Gang
AU - Chen, Jie
N1 - Publisher Copyright:
© 2012 IEEE.
PY - 2022/5/1
Y1 - 2022/5/1
N2 - For nonzero-sum (NZS) games of nonlinear systems, reinforcement learning (RL) or adaptive dynamic programming (ADP) has shown its capability of approximating the desired index performance and the optimal input policy iteratively. In this article, an event-triggered ADP is proposed for NZS games of continuous-time nonlinear systems with completely unknown system dynamics. To achieve the Nash equilibrium solution approximately, the critic neural networks and actor neural networks are utilized to estimate the value functions and the control policies, respectively. Compared with the traditional time-triggered mechanism, the proposed algorithm updates the neural network weights as well as the inputs of players only when a state-based event-triggered condition is violated. It is shown that the system stability and the weights' convergence are still guaranteed under mild assumptions, while occupation of communication and computation resources is considerably reduced. Meanwhile, the infamous Zeno behavior is excluded by proving the existence of a minimum inter-event time (MIET) to ensure the feasibility of the closed-loop event-triggered continuous-time system. Finally, a numerical example is simulated to illustrate the effectiveness of the proposed approach.
AB - For nonzero-sum (NZS) games of nonlinear systems, reinforcement learning (RL) or adaptive dynamic programming (ADP) has shown its capability of approximating the desired index performance and the optimal input policy iteratively. In this article, an event-triggered ADP is proposed for NZS games of continuous-time nonlinear systems with completely unknown system dynamics. To achieve the Nash equilibrium solution approximately, the critic neural networks and actor neural networks are utilized to estimate the value functions and the control policies, respectively. Compared with the traditional time-triggered mechanism, the proposed algorithm updates the neural network weights as well as the inputs of players only when a state-based event-triggered condition is violated. It is shown that the system stability and the weights' convergence are still guaranteed under mild assumptions, while occupation of communication and computation resources is considerably reduced. Meanwhile, the infamous Zeno behavior is excluded by proving the existence of a minimum inter-event time (MIET) to ensure the feasibility of the closed-loop event-triggered continuous-time system. Finally, a numerical example is simulated to illustrate the effectiveness of the proposed approach.
KW - Adaptive dynamic programming (ADP)
KW - event-triggered
KW - nonzero-sum (NZS) games
KW - reinforcement learning (RL)
UR - http://www.scopus.com/inward/record.url?scp=85104591441&partnerID=8YFLogxK
U2 - 10.1109/TNNLS.2021.3071545
DO - 10.1109/TNNLS.2021.3071545
M3 - Article
C2 - 33882002
AN - SCOPUS:85104591441
SN - 2162-237X
VL - 33
SP - 1905
EP - 1913
JO - IEEE Transactions on Neural Networks and Learning Systems
JF - IEEE Transactions on Neural Networks and Learning Systems
IS - 5
ER -