A policy improvement method in constrained stochastic dynamic programming

被引：9
|
作者：
Chang, Hyeong Soo [1 ]
机构：
[1] Sogang Univ, Dept Comp Sci & Engn, Seoul 121742, South Korea
[2] Sogang Univ, Program Integrated Biotechnol, Seoul 121742, South Korea
来源：
IEEE TRANSACTIONS ON AUTOMATIC CONTROL | 2006年 / 51卷 / 09期
关键词：
constrained Markov decision process; dynamic programming; policy improvement; policy iteration;
D O I：
10.1109/TAC.2006.880801
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
This note presents a formal method of improving a given base-policy such that the performance of the resulting policy is no worse than that of the base-policy at all states in constrained stochastic dynamic programming. We consider finite horizon and discounted infinite horizon cases. The improvement method induces a policy iteration-type algorithm that converges to a local optimal policy.
引用
收藏
页码：1523 / 1526
页数：4
相关论文
共 50 条
  • [41] Hybrid solution method for dynamic programming equations for MDOF stochastic systems
    Bratus', A
    Dimentberg, M
    Iourtchenko, D
    Noori, M
    DYNAMICS AND CONTROL, 2000, 10 (01) : 107 - 116
  • [42] Risk neutral and risk averse Stochastic Dual Dynamic Programming method
    Shapiro, Alexander
    Tekaya, Wajdi
    da Costa, Joari Paulo
    Soares, Murilo Pereira
    EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2013, 224 (02) : 375 - 391
  • [43] A STOCHASTIC MULTIOBJECTIVE DYNAMIC-PROGRAMMING METHOD WITH APPLICATION TO ENERGY MODELING
    MOLNAR, S
    SZIDAROVSZKY, F
    LECTURE NOTES IN CONTROL AND INFORMATION SCIENCES, 1986, 84 : 601 - 609
  • [44] A METHOD FOR APPROXIMATE SOLUTIONS TO STOCHASTIC DYNAMIC PROGRAMMING PROBLEMS USING EXPECTATIONS
    NORMAN, JM
    WHITE, DJ
    OPERATIONS RESEARCH, 1968, 16 (02) : 296 - &
  • [45] Constrained portfolio optimization with discrete variables: An algorithmic method based on dynamic programming
    Jezeie, Fereshteh Vaezi
    Sadjadi, Seyed Jafar
    Makui, Ahmad
    PLOS ONE, 2022, 17 (07):
  • [46] The Dynamic Programming Method of Stochastic Differential Game for Functional Forward-Backward Stochastic System
    Ji, Shaolin
    Sun, Chuanfeng
    Wei, Qingmeng
    MATHEMATICAL PROBLEMS IN ENGINEERING, 2013, 2013
  • [47] Optimization of powertrain operating policy for feasibility assessment and calibration: Stochastic dynamic programming approach
    Kolmanovsky, I
    Siverguina, I
    Lygoe, B
    PROCEEDINGS OF THE 2002 AMERICAN CONTROL CONFERENCE, VOLS 1-6, 2002, 1-6 : 1425 - 1430
  • [48] A stochastic dynamic programming model for the optimal policy mix of the carbon tax and decarbonization subsidy
    Li, Yuhan
    Su, Xiaoshan
    Bai, Manying
    JOURNAL OF ENVIRONMENTAL MANAGEMENT, 2024, 353
  • [49] Policy search by dynamic programming
    Bagnell, JA
    Kakade, S
    Ng, AY
    Schneider, J
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 16, 2004, 16 : 831 - 838
  • [50] MULTISTAGE STOCHASTIC DECOMPOSITION: A BRIDGE BETWEEN STOCHASTIC PROGRAMMING AND APPROXIMATE DYNAMIC PROGRAMMING
    Sen, Suvrajeet
    Zhou, Zhihong
    SIAM JOURNAL ON OPTIMIZATION, 2014, 24 (01) : 127 - 153
12345