Volume 8, Issue 4 (Journal of Control, V.8, N.4 Winter 2015)
JoC 2015, 8(4): 15-30 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Tatari F, Naghibi-S M. Distributed Optimal Control of Nonlinear Differential Graphical Games based on Reinforcement Learning. JoC 2015; 8 (4) :15-30
URL: http://joc.kntu.ac.ir/article-1-176-en.html
URL: http://joc.kntu.ac.ir/article-1-176-en.html
1- Ferdowsi university of Mashhad
Abstract: (9706 Views)
This paper introduces continuous time nonlinear differential graphical games and proposes an online distributed optimal control algorithm to solve them. In differential graphical games, each agent error dynamics and performance index depend on its neighbors’ information. The proposed online distributed policy iteration algorithm solves the cooperative coupled Hamilton-Jacobi equations. In this algorithm which is based on reinforcement learning, each agent uses an actor-critic neural network structure where the weights of these neural networks are tuned synchronously. While all actor-critic networks are learning, closed loop stability and convergence to optimal control laws are guaranteed. Finally simulation results demonstrate the validity and performance of the proposed algorithm.
Keywords: Artificial neural networks, Nonlinear differential graphical games, Optimal control, Reinforcement learning.
Type of Article: Research paper |
Subject:
Special
Received: 2014/11/16 | Accepted: 2015/04/4 | Published: 2015/04/8
Received: 2014/11/16 | Accepted: 2015/04/4 | Published: 2015/04/8
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
