Data-driven optimal tracking control of discrete-time multi-agent systems with two-stage policy iteration algorithm

Herein, a novel adaptive dynamic programming (ADP) algorithm is developed to solve the optimal tracking control problem of discrete-time multi-agent systems. Compared to the classical policy iteration ADP algorithm with two components, policy evaluation, and policy improvement, a two-stage policy it...

Celý popis

Podrobná bibliografie

Vydáno v:	Information sciences Ročník 481; s. 189 - 202
Hlavní autoři:	Peng, Zhinan, Zhao, Yiyi, Hu, Jiangping, Ghosh, Bijoy Kumar
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier Inc 01.05.2019
Témata:	Actor-critic networks Data-driven algorithm Multi-agent systems Optimal tracking control Two-stage policy iteration Actor-critic networks Optimal tracking control Two-stage policy iteration Data-driven algorithm Multi-agent systems
ISSN:	0020-0255, 1872-6291
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!