A Novel Distributed Optimal Adaptive Control Algorithm for Nonlinear Multi-Agent Differential Graphical Games

Majid Mazouchi

doi:10.1109/JAS.2017.7510784

A Novel Distributed Optimal Adaptive Control Algorithm for Nonlinear Multi-Agent Differential Graphical Games

2018-01-01

57

PRE

AI

M

Majid Mazouchi

M

Mohammad Bagher Naghibi Sistani *

S

Seyed Kamal Hosseini Sani

DOI：10.1109/JAS.2017.7510784

原文链接

原文求助

摘要

En 中文

In this paper, an online optimal distributed learning algorithm is proposed to solve leader-synchronization problem of nonlinear multi-agent differential graphical games. Each player approximates its optimal control policy using a single-network approximate dynamic programming (ADP) where only one critic neural network (NN) is employed instead of typical actor-critic structure composed of two NNs. The proposed distributed weight tuning laws for critic NNs guarantee stability in the sense of uniform ultimate boundedness (UUB) and convergence of control policies to the Nash equilibrium. In this paper, by introducing novel distributed local operators in weight tuning laws, there is no more requirement for initial stabilizing control policies. Furthermore, the overall closed-loop system stability is guaranteed by Lyapunov stability analysis. Finally, Simulation results show the effectiveness of the proposed algorithm.

Keyword:

Approximate dynamic programming (ADP)

distributed control

neural networks (NNs)

nonlinear differential graphical games

optimal control

A Novel Distributed Optimal Adaptive Control Algorithm for Nonlinear Multi-Agent Differential Graphical Games

摘要

AI总结

期刊

机构

引用论文