Advanced Policy Learning Near-Optimal Regulation

被引：0
|
作者：
Ding Wang [1 ,2 ]
Xiangnan Zhong [1 ,3 ]
机构：
[1] IEEE
[2] the Faculty of Information Technology, Beijing University of Technology, and also with the Beijing Key Laboratory of Computational Intelligence and Intelligent System, Beijing University of Technology
[3] the Department of Electrical Engineering, University of North Texas
来源：
IEEE/CAA Journal of Automatica Sinica | 2019年 / 6卷 / 03期
基金：
中国国家自然科学基金;
关键词：
Adaptive critic algorithm; learning control; neural approximation; nonaffine dynamics; optimal regulation;
D O I：
暂无
中图分类号：
O232 [最优控制];
学科分类号：
摘要：
Designing advanced design techniques for feedback stabilization and optimization of complex systems is important to the modern control field. In this paper, a near-optimal regulation method for general nonaffine dynamics is developed with the help of policy learning. For addressing the nonaffine nonlinearity, a pre-compensator is constructed, so that the augmented system can be formulated as affine-like form. Different cost functions are defined for original and transformed controlled plants and then their relationship is analyzed in detail. Additionally, an adaptive critic algorithm involving stability guarantee is employed to solve the augmented optimal control problem. At last, several case studies are conducted for verifying the stability, robustness, and optimality of a torsional pendulum plant with suitable cost.
引用
收藏
页码：743 / 749
页数：7
相关论文
共 50 条
  • [31] Learning Near-Optimal Intrusion Responses Against Dynamic Attackers
    Hammar, Kim
    Stadler, Rolf
    IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT, 2024, 21 (01): : 1158 - 1177
  • [32] Near-Optimal Φ-Regret Learning in Extensive-Form Games
    Anagnostides, Ioannis
    Farina, Gabriele
    Sandholm, Tuomas
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 202, 2023, 202 : 814 - 839
  • [33] Near-optimal Trajectory Tracking in Quadcopters using Reinforcement Learning
    Engelhardt, Randal
    Velazquez, Alberto
    Sardarmehni, Tohid
    IFAC PAPERSONLINE, 2024, 58 (28): : 61 - 65
  • [34] Near-Optimal Representation Learning for Linear Bandits and Linear RL
    Hu, Jiachen
    Chen, Xiaoyu
    Jin, Chi
    Li, Lihong
    Wang, Liwei
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139
  • [35] Polynomial-time reinforcement learning of near-optimal policies
    Pivazyan, K
    Shoham, Y
    EIGHTEENTH NATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE (AAAI-02)/FOURTEENTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE (IAAI-02), PROCEEDINGS, 2002, : 205 - 210
  • [36] Selecting Near-Optimal Approximate State Representations in Reinforcement Learning
    Ortner, Ronald
    Maillard, Odalric-Ambrym
    Ryabko, Daniil
    Algorithmic Learning Theory (ALT 2014), 2014, 8776 : 140 - 154
  • [37] Near-optimal Bayesian active learning with correlated and noisy tests
    Chen, Yuxin
    Hassani, S. Hamed
    Krause, Andreas
    ELECTRONIC JOURNAL OF STATISTICS, 2017, 11 (02): : 4969 - 5017
  • [38] Near-optimal Bayesian Active Learning with Correlated and Noisy Tests
    Chen, Yuxin
    Hassani, S. Hamed
    Krause, Andreas
    ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 54, 2017, 54 : 223 - 231
  • [39] A Near-optimal Non-myopic Active Learning Method
    Zhao, Yue
    Yang, Guosheng
    Xu, Xiaona
    Ji, Qiang
    2012 21ST INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR 2012), 2012, : 1715 - 1718
  • [40] Caching in Dynamic Environments: A Near-Optimal Online Learning Approach
    Zhou, Shiji
    Wang, Zhi
    Hu, Chenghao
    Mao, Yinan
    Yan, Haopeng
    Zhang, Shanghang
    Wu, Chuan
    Zhu, Wenwu
    IEEE TRANSACTIONS ON MULTIMEDIA, 2023, 25 : 792 - 804
12345