AU - Mazouchi, Majid
AU - Naghibi Sistani, Mohammad Bagher
AU - Hosseini Sani, Seyed Kamal
TI - Suboptimal Solution of Nonlinear Graphical Games Using Single Network Approximate Dynamic Programming
PT - JOURNAL ARTICLE
TA - joc-isice
JN - joc-isice
VO - 12
VI - 2
IP - 2
4099 - http://joc.kntu.ac.ir/article-1-382-en.html
4100 - http://joc.kntu.ac.ir/article-1-382-en.pdf
SO - joc-isice 2
ABĀ - In this paper, an online learning algorithm based on approximate dynamic programming is proposed to approximately solve the nonlinear continuous time differential graphical games with infinite horizon cost functions and known dynamics. In the proposed algorithm, every agent employs a critic neural network (NN) to approximate its optimal value and control policy and utilizes the proposed weight tuning laws to learn its critic NN optimal weights in an online fashion. Critic NN weight tuning laws containing a stabilizer switch guarantees the closed-loop system stability and the control policies convergence to the Nash equilibrium. In this algorithm, there is no requirement for any set of initial stabilizing control policies anymore. Furthermore, Lyapunov theory is employed to show uniform ultimate boundedness of the closedloop system. Finally, a simulation example is presented to illustrate the efficiency of the proposed algorithm.
CP - IRAN
IN - Khorasan Razavi, Mashhad, Vakilabad Highway, Ferdowsi University of Mashhad, Faculty of Engineering, Electrical Engineering Department
LG - eng
PB - joc-isice
PG - 13
PT - Research
YR - 2018