Title :
Robust Adaptive Dynamic Programming of Two-Player Zero-Sum Games for Continuous-Time Linear Systems
Author :
Yue Fu ; Jun Fu ; Tianyou Chai
Author_Institution :
State Key Lab. of Synthetical Autom. for Process Ind., Northeastern Univ., Shenyang, China
Abstract :
In this brief, an online robust adaptive dynamic programming algorithm is proposed for two-player zero-sum games of continuous-time unknown linear systems with matched uncertainties, which are functions of system outputs and states of a completely unknown exosystem. The online algorithm is developed using the policy iteration (PI) scheme with only one iteration loop. A new analytical method is proposed for convergence proof of the PI scheme. The sufficient conditions are given to guarantee globally asymptotic stability and suboptimal property of the closed-loop system. Simulation studies are conducted to illustrate the effectiveness of the proposed method.
Keywords :
PI control; asymptotic stability; closed loop systems; continuous time systems; dynamic programming; game theory; iterative methods; linear systems; uncertain systems; PI scheme; closed-loop system; continuous-time linear systems; continuous-time unknown linear systems; convergence proof; global asymptotic stability; iteration loop; online robust adaptive dynamic programming algorithm; policy iteration scheme; suboptimal property; two-player zero-sum games; uncertainty matching; Approximation algorithms; Closed loop systems; Convergence; Games; Heuristic algorithms; Linear systems; Robustness; Game algebraic Riccati equation (GARE); policy iterations (PIs); robust adaptive dynamic programming (ADP); two-player zero-sum (ZS) games; two-player zero-sum (ZS) games.;
Journal_Title :
Neural Networks and Learning Systems, IEEE Transactions on
DOI :
10.1109/TNNLS.2015.2461452
