Adaptive Learning Based Output-Feedback Optimal Control of CT Two-Player Zero-Sum Games

被引：17

作者：

Zhao, Jun ^{[1
]}

Lv, Yongfeng ^{[2
]}

Zhao, Ziliang ^{[3
]}

机构：

[1] Shandong Univ Sci & Technol, Coll Mech & Elect Engn, Qingdao 266590, Peoples R China

[2] Taiyuan Univ Technol, Coll Elect & Power Engn, Taiyuan 030024, Peoples R China

[3] Shandong Univ Sci & Technol, Coll Transportat, Qingdao 266590, Peoples R China

来源：

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS | 2022年 / 69卷 / 03期

基金：

中国国家自然科学基金;

关键词：

Games; Optimal control; Adaptive learning; Game theory; Cost function; Observers; Estimation error; Output-feedback optimal control; adaptive learning; zero-sum games; SYSTEMS;

D O I：

10.1109/TCSII.2021.3112050

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Although optimal control with full state-feedback has been well studied, online solving output-feedback optimal control problem is difficult, in particular for learning online Nash equilibrium solution of the continuous-time (CT) two-player zero-sum differential games. For this purpose, we propose an adaptive learning algorithm to address this trick problem. A modified game algebraic Riccati equation (MGARE) is derived by tailoring its state-feedback control counterpart. An adaptive online learning method is proposed to approximate the solution to the MGARE through online data, where two operations (i.e., vectorization and Kronecker's product) can be adopted to reconstruct the MGARE. Only system output information is needed to implement developed learning algorithm. Simulation results are carried out to exemplify the proposed control and learning method.

引用

页码：1437 / 1441

页数：5

共 50 条

[21] Finite Horizon Stochastic Optimal Control of Nonlinear Two-Player Zero-Sum Games under Communication Constraint
Xu, Hao
Jagannathan, S.
PROCEEDINGS OF THE 2014 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2014, : 239 - 244
[22] A Generalized Minimax Q-Learning Algorithm for Two-Player Zero-Sum Stochastic Games
Diddigi, Raghuram Bharadwaj
Kamanchi, Chandramouli
Bhatnagar, Shalabh
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2022, 67 (09) : 4816 - 4823
[23] The Lagging Anchor Algorithm: Reinforcement Learning in Two-Player Zero-Sum Games with Imperfect Information
Fredrik A. Dahl
Machine Learning, 2002, 49 : 5 - 37
[24] Learning Extensive-Form Perfect Equilibria in Two-Player Zero-Sum Sequential Games
Bernasconi, Martino
Marchesi, Alberto
Trovo, Francesco
INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 238, 2024, 238
[25] A Meta-evolutionary Learning Algorithm for Opponent Adaptation in Two-player Zero-sum Games
Wu Z.
Li K.
Xu H.
Xing J.-L.
Zidonghua Xuebao/Acta Automatica Sinica, 2022, 48 (10): : 2462 - 2473
[26] The lagging anchor algorithm: Reinforcement learning in two-player zero-sum games with imperfect information
Dahl, FA
MACHINE LEARNING, 2002, 49 (01) : 5 - 37
[27] Equilibrium payoffs in repeated two-player zero-sum games of finite automata
Baskov, O. V.
INTERNATIONAL JOURNAL OF GAME THEORY, 2019, 48 (02) : 423 - 431
[28] An LP Approach for Solving Two-Player Zero-Sum Repeated Bayesian Games
Li, Lichun
Langbort, Cedric
Shamma, Jeff
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2019, 64 (09) : 3716 - 3731
[29] A METHOD TO SOLVE TWO-PLAYER ZERO-SUM MATRIX GAMES IN CHAOTIC ENVIRONMENT
Khalifa, Hamiden Abd El-Wahed
Kumar, Pavan
INDEPENDENT JOURNAL OF MANAGEMENT & PRODUCTION, 2021, 12 (01): : 115 - 126
[30] Provably Efficient Policy Optimization for Two-Player Zero-Sum Markov Games
Zhao, Yulai
Tian, Yuandong
Lee, Jason D.
Du, Simon S.
INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 151, 2022, 151

← 1 2 3 4 5 →