Policy iteration for average cost Markov control processes on Borel spaces

被引:15
|
作者
HernandezLerma, O [1 ]
Lasserre, JB [1 ]
机构
[1] CNRS,LAAS,F-31077 TOULOUSE,FRANCE
关键词
(discrete-time) Markov control processes; average cost; policy iteration (aka Howard's algorithm);
D O I
10.1023/A:1005781013253
中图分类号
O29 [应用数学];
学科分类号
070104 ;
摘要
This paper studies the policy iteration algorithm (PIA) for average cost Markov control processes on Borel spaces. Two classes of MCPs are considered. One of them allows some restricted-growth unbounded cost functions and compact control constraint sets; the other one requires strictly unbounded costs and the control constraint sets may be non-compact. For each of these classes, the PIA yields, under suitable assumptions, the optimal (minimum) cost, an optimal stationary control policy, and a solution to the average cost optimality equation.
引用
收藏
页码:125 / 154
页数:30
相关论文
共 50 条
  • [21] Markov Decision Processes on Borel Spaces with Total Cost and Random Horizon
    Cruz-Suarez, Hugo
    Ilhuicatzi-Roldan, Rocio
    Montes-de-Oca, Raul
    JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS, 2014, 162 (01) : 329 - 346
  • [22] Constrained Markov control processes in Borel spaces: the discounted case
    Onésimo Hernández-Lerma
    Juan González-Hernández
    Mathematical Methods of Operations Research, 2000, 52 : 271 - 285
  • [23] Markov Decision Processes on Borel Spaces with Total Cost and Random Horizon
    Hugo Cruz-Suárez
    Rocio Ilhuicatzi-Roldán
    Raúl Montes-de-Oca
    Journal of Optimization Theory and Applications, 2014, 162 : 329 - 346
  • [24] AVERAGE COST OPTIMAL POLICIES FOR MARKOV CONTROL PROCESSES WITH BOREL STATE-SPACE AND UNBOUNDED COSTS
    HERNANDEZLERMA, O
    LASSERRE, JB
    SYSTEMS & CONTROL LETTERS, 1990, 15 (04) : 349 - 356
  • [26] Policy Iteration for Decentralized Control of Markov Decision Processes
    Bernstein, Daniel S.
    Amato, Christopher
    Hansen, Eric A.
    Zilberstein, Shlomo
    JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH, 2009, 34 : 89 - 132
  • [27] New Average Optimality Conditions for Semi-Markov Decision Processes in Borel Spaces
    Qingda Wei
    Xianping Guo
    Journal of Optimization Theory and Applications, 2012, 153 : 709 - 732
  • [28] New Average Optimality Conditions for Semi-Markov Decision Processes in Borel Spaces
    Wei, Qingda
    Guo, Xianping
    JOURNAL OF OPTIMIZATION THEORY AND APPLICATIONS, 2012, 153 (03) : 709 - 732
  • [30] Toward an Optimized Value Iteration Algorithm for Average Cost Markov Decision Processes
    Arruda, Edilson F.
    Ourique, Fabricio
    Almudevar, Anthony
    49TH IEEE CONFERENCE ON DECISION AND CONTROL (CDC), 2010, : 930 - 934