Title :
Asymptotically Optimal Decentralized Control for a Class of Multi-Agent Systems
Author :
Li Tao ; Zhang Ji-feng
Author_Institution :
Acad. of Math. & Syst. Sci., Chinese Acad. of Sci., Beijing, China
Abstract :
The concept of asymptotic Nash-equilibria with respect to stochastic performance index is introduced, a decentralized control law is constructed for large population dynamic multi-agent systems (LPDMAS) with cost-coupled stochastic performance indexes by using the state aggregation method. By the limit probability theory, it is shown that the closed-loop system is almost surely uniformly stable, and the control law is asymptotically optimal.
Keywords :
asymptotic stability; closed loop systems; decentralised control; game theory; multi-agent systems; optimal control; performance index; probability; stochastic processes; asymptotic Nash-equilibria; asymptotically optimal decentralized control; closed-loop system; cost-coupled stochastic performance index; large population dynamic multiagent systems; limit probability theory; stability; state aggregation method; stochastic differential game; Artificial intelligence; Control systems; Distributed control; IEEE catalog; Iron; Mathematics; Multiagent systems; Optimal control; Performance analysis; Stochastic systems; Multi-Agent Systems; asymptotic Nash-equilibria; decentralized control; stochastic differential game; stochastic performance index;
Conference_Titel :
Control Conference, 2006. CCC 2006. Chinese
Conference_Location :
Harbin
Print_ISBN :
7-81077-802-1
DOI :
10.1109/CHICC.2006.280985
