Optimal policies for constrained average-cost Markov decision processes

被引：0
|
作者：
Juan González-Hernández
César E. Villarreal
机构：
[1] Universidad Nacional Autónoma de México,Departamento de Probabilidad y Estadística, Instituto de Investigaciones en Matemáticas Aplicadas y en Sistemas
[2] Universidad Autónoma de Nuevo León,Posgrado en Ingeniería de Sistemas, Facultad de Ingeniería Mecánica y Eléctrica
[3] Ciudad Universitaria,undefined
来源：
TOP | 2011年 / 19卷
关键词：
Markov decision processes; Constraints; Stable measures; 90C40;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
We give mild conditions for the existence of optimal solutions for a Markov decision problem with average cost, under m constraints of the same kind, in Borel actions and states spaces. Moreover, there is an optimal policy that is a convex combination of at most m+1 deterministic policies.
引用
收藏
页码：107 / 120
页数：13
相关论文
共 50 条
  • [41] AVERAGE OPTIMAL STATIONARY POLICIES AND LINEAR-PROGRAMMING IN COUNTABLE SPACE MARKOV DECISION-PROCESSES
    LASSERRE, JB
    [J]. JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS, 1994, 183 (01) : 233 - 249
  • [42] A Rollout Algorithm for Multichain Markov Decision Processes with Average Cost
    Sun, Tao
    Zhao, Qianchuan
    Luh, Peter B.
    [J]. POSITIVE SYSTEMS, PROCEEDINGS, 2009, 389 : 151 - 162
  • [43] AVERAGE COST MARKOV DECISION-PROCESSES - OPTIMALITY CONDITIONS
    HERNANDEZLERMA, O
    HENNET, JC
    LASSERRE, JB
    [J]. JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS, 1991, 158 (02) : 396 - 406
  • [44] Constrained continuous-time Markov decision processes with average criteria
    Lanlan Zhang
    Xianping Guo
    [J]. Mathematical Methods of Operations Research, 2008, 67 : 323 - 340
  • [45] Constrained continuous-time Markov decision processes with average criteria
    Zhang, Lanlan
    Guo, Xianping
    [J]. MATHEMATICAL METHODS OF OPERATIONS RESEARCH, 2008, 67 (02) : 323 - 340
  • [46] AVERAGE COST OPTIMAL POLICIES FOR MARKOV CONTROL PROCESSES WITH BOREL STATE-SPACE AND UNBOUNDED COSTS
    HERNANDEZLERMA, O
    LASSERRE, JB
    [J]. SYSTEMS & CONTROL LETTERS, 1990, 15 (04) : 349 - 356
  • [47] The computation of average optimal policies in denumerable state Markov decision chains
    Sennott, LI
    [J]. ADVANCES IN APPLIED PROBABILITY, 1997, 29 (01) : 114 - 137
  • [48] Constrained Markov Decision Processes with Total Expected Cost Criteria
    Altman, Eitan
    Boularouk, Said
    Josselin, Didier
    [J]. PROCEEDINGS OF THE 12TH EAI INTERNATIONAL CONFERENCE ON PERFORMANCE EVALUATION METHODOLOGIES AND TOOLS (VALUETOOLS 2019), 2019, : 191 - 192
  • [49] Conditions for the uniqueness of optimal policies of discounted Markov decision processes
    Daniel Cruz-Suárez
    Raúl Montes-de-Oca
    Francisco Salem-Silva
    [J]. Mathematical Methods of Operations Research, 2004, 60 : 415 - 436
  • [50] Reinforcement Learning of Risk-Constrained Policies in Markov Decision Processes
    Brazdil, Tomas
    Chatterjee, Krishnendu
    Novotny, Petr
    Vahala, Jiri
    [J]. THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 9794 - 9801
12345