A Version of the Euler Equation in Discounted Markov Decision Processes

被引:2
|
作者
Cruz-Suarez, H. [1 ]
Zacarias-Espinoza, G. [1 ]
Vazquez-Guevara, V. [1 ]
机构
[1] Benemerita Univ Autonoma Puebla, Fac Ciencias Fis Matemat, CU, Puebla 72570, PUE, Mexico
关键词
UNCERTAINTY; GROWTH;
D O I
10.1155/2012/103698
中图分类号
O29 [应用数学];
学科分类号
070104 ;
摘要
This paper deals with Markov decision processes (MDPs) on Euclidean spaces with an infinite horizon. An approach to study this kind of MDPs is using the dynamic programming technique (DP). Then the optimal value function is characterized through the value iteration functions. The paper provides conditions that guarantee the convergence of maximizers of the value iteration functions to the optimal policy. Then, using the Euler equation and an envelope formula, the optimal solution of the optimal control problem is obtained. Finally, this theory is applied to a linear-quadratic control problem in order to find its optimal policy.
引用
收藏
页数:16
相关论文
共 50 条
  • [11] A note on deterministic approximation of discounted Markov decision processes
    Cruz-Suarez, Hugo
    Gordienko, Evgueni
    Montes-de-Oca, Raul
    APPLIED MATHEMATICS LETTERS, 2009, 22 (08) : 1252 - 1256
  • [12] Constrained discounted Markov decision processes and Hamiltonian Cycles
    Feinberg, EA
    MATHEMATICS OF OPERATIONS RESEARCH, 2000, 25 (01) : 130 - 140
  • [13] Constrained discounted Markov decision processes and Hamiltonian cycles
    Feinberg, EA
    PROCEEDINGS OF THE 36TH IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-5, 1997, : 2821 - 2826
  • [14] Discounted Markov Decision Processes via Time Aggregation
    Arruda, Edilson F.
    Fragoso, Marcelo D.
    2016 EUROPEAN CONTROL CONFERENCE (ECC), 2016, : 2578 - 2583
  • [15] Stochastic approximations of constrained discounted Markov decision processes
    Dufour, Francois
    Prieto-Rumeau, Tomas
    JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS, 2014, 413 (02) : 856 - 879
  • [16] Hierarchical algorithms for discounted and weighted Markov decision processes
    M. Abbad
    C. Daoui
    Mathematical Methods of Operations Research, 2003, 58 : 237 - 245
  • [17] Limits of multi-discounted Markov decision processes
    Gimbert, Hugo
    Zielonka, Wieslaw
    22ND ANNUAL IEEE SYMPOSIUM ON LOGIC IN COMPUTER SCIENCE, PROCEEDINGS, 2007, : 89 - +
  • [18] Decision roll and horizon roll processes in infinite horizon discounted Markov decision processes
    White, DJ
    MANAGEMENT SCIENCE, 1996, 42 (01) : 37 - 50
  • [19] The Discounted Euler Equation: A Note
    McKay, Alisdair
    Nakamura, Emi
    Steinsson, Jon
    ECONOMICA, 2017, 84 (336) : 820 - 831
  • [20] Discounted Deterministic Markov Decision Processes and Discounted All-Pairs Shortest Paths
    Madani, Omid
    Thorup, Mikkel
    Zwick, Uri
    ACM TRANSACTIONS ON ALGORITHMS, 2010, 6 (02)