Title : ( Distributed learning algorithm for non-linear differential graphical games )
Authors: Farzaneh Tatari , Mohammad Bagher Naghibi Sistani , Kyriakos G. Vamvoudakis ,
Full TextAbstract
This paper introduces differential graphical games for continuous-time non-linear systems and proposes an online adaptive learning framework. The error dynamics and the user-defined performance indices of each agent depend only on local information and the proposed cooperative learning algorithm learns the solution to the cooperative coupled Hamilton–Jacobi equations. In the proposed algorithm, each one of the agents uses an actor/critic neural network (NN) structure with appropriate tuning laws in order to guarantee closed-loop stability and convergence of the policies to the Nash equilibrium. Finally, a simulation example verifies the effectiveness of the proposed approach.
Keywords
, Adaptive optimal control, consensus, distributed control, multi-player games, neural networks, non-linear graphical games, reinforcement learning.
@article{paperid:1054196,
author = {Tatari, Farzaneh and Naghibi Sistani, Mohammad Bagher and Kyriakos G. Vamvoudakis},
title = {Distributed learning algorithm for non-linear differential graphical games},
journal = {Transactions of the Institute of Measurement and Control},
year = {2017},
volume = {39},
number = {2},
month = {January},
issn = {0142-3312},
pages = {173--182},
numpages = {9},
keywords = {Adaptive optimal control; consensus; distributed control; multi-player games; neural networks; non-linear graphical games; reinforcement learning.},
}
%0 Journal Article
%T Distributed learning algorithm for non-linear differential graphical games
%A Tatari, Farzaneh
%A Naghibi Sistani, Mohammad Bagher
%A Kyriakos G. Vamvoudakis
%J Transactions of the Institute of Measurement and Control
%@ 0142-3312
%D 2017
