Asymptotic properties of two time-scale stochastic approximation algorithms with constant step sizes

被引：0
|
作者：
Tadic, VB [1 ]
Meyn, SP [1 ]
机构：
[1] Univ Melbourne, Dept Elect & Elect Engn, Parkville, Vic 3010, Australia
来源：
PROCEEDINGS OF THE 2003 AMERICAN CONTROL CONFERENCE, VOLS 1-6 | 2003年
关键词：
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
Asymptotic properties of two time-scale stochastic approximation algorithms with constant step sizes are analyzed in this paper. The analysis is carried out for the algorithms with additive noise, as well as for the algorithms with non-additive noise. The algorithms with additive noise are considered for the case where the noise is state-dependent and admits the decomposition as a sum of a martingale difference sequence and a telescoping sequence. The algorithms with non-additive noise are analyzed for the case where the noise satisfies uniform or strong mixing conditions, as well as for the case where the noise is a Markov chain controlled by the algorithm states.
引用
收藏
页码：4426 / 4431
页数：6
相关论文
共 50 条
  • [1] Diffusion approximation for two time-scale stochastic approximation algorithms with constant step sizes
    Tadic, VB
    2004 43RD IEEE CONFERENCE ON DECISION AND CONTROL (CDC), VOLS 1-5, 2004, : 4187 - 4192
  • [2] On the robustness of two time-scale stochastic approximation algorithms
    Tadic, VB
    2004 43RD IEEE CONFERENCE ON DECISION AND CONTROL (CDC), VOLS 1-5, 2004, : 5334 - 5339
  • [3] Almost sure convergence of two time-scale stochastic approximation algorithms
    Tadic, VB
    PROCEEDINGS OF THE 2004 AMERICAN CONTROL CONFERENCE, VOLS 1-6, 2004, : 3802 - 3807
  • [4] New stochastic approximation algorithms with adaptive step sizes
    Zi Xu
    Yu-Hong Dai
    Optimization Letters, 2012, 6 : 1831 - 1846
  • [5] New stochastic approximation algorithms with adaptive step sizes
    Xu, Zi
    Dai, Yu-Hong
    OPTIMIZATION LETTERS, 2012, 6 (08) : 1831 - 1846
  • [6] Two time-scale stochastic approximation for constrained stochastic optimization and constrained Markov decision problems
    Tadic, VB
    Doucet, A
    Singh, S
    PROCEEDINGS OF THE 2003 AMERICAN CONTROL CONFERENCE, VOLS 1-6, 2003, : 4736 - 4741
  • [7] Non-Asymptotic Analysis for Two Time-scale TDC with General Smooth Function Approximation
    Wang, Yue
    Zou, Shaofeng
    Zhou, Yi
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [8] Stochastic approximation algorithms with constant step size whose average is cooperative
    Benaïm, M
    Hirsch, MW
    ANNALS OF APPLIED PROBABILITY, 1999, 9 (01): : 216 - 241
  • [9] THE COSMICAL CONSTANT AND THE TIME-SCALE
    MCVITTIE, GC
    JOURNAL OF THE SOCIETY FOR INDUSTRIAL AND APPLIED MATHEMATICS, 1962, 10 (04): : 756 - 767
  • [10] ASYMPTOTIC PROPERTIES OF DISTRIBUTED AND COMMUNICATING STOCHASTIC-APPROXIMATION ALGORITHMS
    KUSHNER, HJ
    YIN, G
    SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 1987, 25 (05) : 1266 - 1290
12345