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
  • [31] Stochastic Differential Dynamic Programming
    Theodorou, Evangelos
    Tassa, Yuval
    Todorov, Emo
    2010 AMERICAN CONTROL CONFERENCE, 2010, : 1125 - 1132
  • [32] Equality Constrained Differential Dynamic Programming
    El Kazdadi, Sarah
    Carpentier, Justin
    Ponce, Jean
    2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021), 2021, : 8053 - 8059
  • [33] Constrained codon optimization by dynamic programming
    Pham, TD
    O'Connell, J
    Crane, DI
    PROCEEDINGS OF THE 2004 INTERNATIONAL SYMPOSIUM ON INTELLIGENT MULTIMEDIA, VIDEO AND SPEECH PROCESSING, 2004, : 153 - 156
  • [34] A dynamic programming approach to constrained portfolios
    Kraft, Holger
    Steffensen, Mogens
    EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2013, 229 (02) : 453 - 461
  • [35] Constrained Differential Dynamic Programming Revisited
    Aoyama, Yuichiro
    Boutselis, George
    Patel, Akash
    Theodorou, Evangelos A.
    2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021), 2021, : 9738 - 9744
  • [36] A RISK-CONSTRAINED STOCHASTIC DYNAMIC-PROGRAMMING APPROACH TO THE OPERATION PLANNING OF HYDROTHERMAL SYSTEMS
    NETO, TDA
    PEREIRA, MVF
    KELMAN, J
    IEEE TRANSACTIONS ON POWER APPARATUS AND SYSTEMS, 1985, 104 (02): : 273 - 279
  • [37] RISK-CONSTRAINED STOCHASTIC DYNAMIC PROGRAMMING APPROACH TO THE OPERATION PLANNING OF HYDROTHERMAL SYSTEMS.
    de A. Araripe Neto, Tristao
    Pereira, Mario V.F.
    Kelman, Jerson
    IEEE transactions on power apparatus and systems, 1985, PAS-104 (02): : 273 - 279
  • [38] STOCHASTIC DYNAMIC PROGRAMMING METHOD FOR CALCULATION OF OPTIMUM SHIP ROUTES.
    Khalilov, S.I.
    Soviet meteorology and hydrology, 1980, (11): : 88 - 90
  • [39] Foreign exchange trading and management with the stochastic dual dynamic programming method
    Reus, Lorenzo
    Alexander Sepulveda-Hurtado, Guillermo
    FINANCIAL INNOVATION, 2023, 9 (01)
  • [40] Foreign exchange trading and management with the stochastic dual dynamic programming method
    Lorenzo Reus
    Guillermo Alexander Sepúlveda-Hurtado
    Financial Innovation, 9
12345