Infinite time linear quadratic stackelberg game problem for unknown stochastic discrete‐time systems via adaptive dynamic programming approach

In this paper, we propose an adaptive dynamic programming (ADP) approach to solve the infinite horizon linear quadratic (LQ) Stackelberg game problem for unknown stochastic discrete‐time systems with multiple decision makers. Firstly, the stochastic LQ Stackelberg game problem is converted into the...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Asian journal of control Ročník 23; číslo 2; s. 937 - 948
Hlavní autori: Liu, Xikui, Liu, Ruirui, Li, Yan
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Hoboken Wiley Subscription Services, Inc 01.03.2021
Predmet:
adaptive dynamic programming
Adaptive systems
Algorithms
Artificial neural networks
Back propagation networks
back propagation neural network
Discrete time systems
Dynamic programming
Games
Iterative methods
Neural networks
Stackelberg game
stochastic discrete‐time systems
ISSN:1561-8625, 1934-6093
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:In this paper, we propose an adaptive dynamic programming (ADP) approach to solve the infinite horizon linear quadratic (LQ) Stackelberg game problem for unknown stochastic discrete‐time systems with multiple decision makers. Firstly, the stochastic LQ Stackelberg game problem is converted into the deterministic problem by system transformation. Next, a value iteration ADP approach is put forword and the convergence is given. Thirdly, in order to implement the iterative method, back propagation neural network (BPNN) is chosen to design model network, critic network and action network to approximate the unknown systems, objective functions and Stackelberg strategies. Finally, simulation results show that the algorithm is effective.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1561-8625
1934-6093
DOI:10.1002/asjc.2276