A learning algorithm for discrete-time stochastic control

被引：11
|
作者：
Borkar, VS [1 ]
机构：
[1] Tata Inst Fundamental Res, Sch Technol & Comp Sci, Bombay 400005, Maharashtra, India
来源：
PROBABILITY IN THE ENGINEERING AND INFORMATIONAL SCIENCES | 2000年 / 14卷 / 02期
关键词：
D O I：
10.1017/S0269964800142081
中图分类号：
T [工业技术];
学科分类号：
08 ;
摘要：
A simulation-based algorithm for learning good policies for a discrete-time stochastic control process with unknown transition law is analyzed when the state and action spaces are compact subsets of Euclidean spaces. This extends the Q-learning scheme of discrete state/action problems along the lines of Baker [4]. Almost sure convergence is proved under suitable conditions.
引用
收藏
页码：243 / 258
页数：16
相关论文
共 50 条
  • [1] On a discrete-time stochastic learning control algorithm
    Saab, SS
    IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2001, 46 (08) : 1333 - 1336
  • [2] A discrete-time stochastic learning control algorithm
    Saab, SS
    IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2001, 46 (06) : 877 - 887
  • [3] A Discrete-Time Stochastic Iterative Learning Control Algorithm for a Class of Nonlinear Systems
    Saab, S. S.
    CONTROL AND INTELLIGENT SYSTEMS, 2005, 33 (02) : 95 - 101
  • [4] A ROLLOUT CONTROL ALGORITHM FOR DISCRETE-TIME STOCHASTIC SYSTEMS
    Malikopoulos, Andreas A.
    PROCEEDINGS OF THE ASME DYNAMIC SYSTEMS AND CONTROL CONFERENCE 2010, VOL 2, 2010, : 711 - 717
  • [5] Discrete-time Stochastic Iterative Learning Control: A Brief Survey
    Shen, Dong
    Xiong, Gang
    PROCEEDINGS OF THE 10TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION (WCICA 2012), 2012, : 2624 - 2629
  • [6] Compositional Reinforcement Learning for Discrete-Time Stochastic Control Systems
    Lavaei, Abolfazl
    Perez, Mateo
    Kazemi, Milad
    Somenzi, Fabio
    Soudjani, Sadegh
    Trivedi, Ashutosh
    Zamani, Majid
    IEEE OPEN JOURNAL OF CONTROL SYSTEMS, 2023, 2 : 425 - 438
  • [7] An integrated optimal control algorithm for discrete-time nonlinear stochastic system
    Kek, Sie Long
    Teo, Kok Lay
    Ismail, A. A. Mohd
    INTERNATIONAL JOURNAL OF CONTROL, 2010, 83 (12) : 2536 - 2545
  • [8] Iterative Learning Control Design for Discrete-Time Stochastic Switched Systems
    Pakshin, P. V.
    Emelianova, J. P.
    AUTOMATION AND REMOTE CONTROL, 2020, 81 (11) : 2011 - 2025
  • [9] Iterative Learning Control Design for Discrete-Time Stochastic Switched Systems
    P. V. Pakshin
    J. P. Emelianova
    Automation and Remote Control, 2020, 81 : 2011 - 2025
  • [10] Iterative Learning Control for Discrete-time Stochastic Systems with Quantized Information
    Dong Shen
    Yun Xu
    IEEE/CAAJournalofAutomaticaSinica, 2016, 3 (01) : 59 - 67
12345