Linear programming solvers for Markov Decision Processes

被引：12
|
作者：
Bello, Diego [1 ]
Riano, German [1 ]
机构：
[1] Univ Los Andes, COPA, Bogota, Colombia
来源：
2006 IEEE SYSTEMS AND INFORMATION ENGINEERING DESIGN SYMPOSIUM | 2006年
关键词：
D O I：
10.1109/SIEDS.2006.278719
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This paper describes linear programming solvers for Markov Decision Processes, as an extension to the JMDP program. JMDP is an object-oriented framework to model and solve Markov Decision Processes (MDP) programmed in Java. The developed solvers work for the Discounted Cost and Average Cost criteria. Our solvers are compared with existing Value Iteration and Policy Iteration solvers.
引用
收藏
页码：90 / +
页数：2
相关论文
共 50 条
  • [31] Multilinear and Integer Programming for Markov Decision Processes with Imprecise Probabilities
    Shirota Filho, Ricardo
    Cozman, Fabio Gagliardi
    Trevizan, Felipe Werndl
    de Campos, Cassio Polpo
    de Barros, Leliane Nunes
    ISIPTA 07-PROCEEDINGS OF THE FIFTH INTERNATIONAL SYMPOSIUM ON IMPRECISE PROBABILITY:THEORIES AND APPLICATIONS, 2007, : 395 - +
  • [32] Risk-averse dynamic programming for Markov decision processes
    Ruszczynski, Andrzej
    MATHEMATICAL PROGRAMMING, 2010, 125 (02) : 235 - 261
  • [33] Risk-averse dynamic programming for Markov decision processes
    Andrzej Ruszczyński
    Mathematical Programming, 2010, 125 : 235 - 261
  • [34] A Generalized Reduced Linear Program for Markov Decision Processes
    Lakshminarayanan, Chandrashekar
    Bhatnagar, Shalabh
    PROCEEDINGS OF THE TWENTY-NINTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2015, : 2722 - 2728
  • [35] Singularly perturbed linear programs and Markov decision processes
    Avrachenkov, Konstantin
    Filar, Jerzy A.
    Gaitsgory, Vladimir
    Stillman, Andrew
    OPERATIONS RESEARCH LETTERS, 2016, 44 (03) : 297 - 301
  • [36] Improved Algorithms for Misspecified Linear Markov Decision Processes
    Vial, Daniel
    Parulekar, Advait
    Shakkottai, Sanjay
    Srikant, R.
    INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 151, 2022, 151
  • [37] Linear Programming for Large-Scale Markov Decision Problems
    Abbasi-Yadkori, Yasin
    Bartlett, Peter L.
    Malek, Alan
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 32 (CYCLE 2), 2014, 32 : 496 - 504
  • [38] Linear Programming Approximations for Markov Control Processes in Metric Spaces
    Onésimo Hernández-Lerma
    Jean B. Lasserre
    Acta Applicandae Mathematica, 1998, 51 : 123 - 139
  • [39] Linear programming approximations for Markov control processes in metric spaces
    Acta Appl Math, 2 (123-129):
  • [40] Linear programming approximations for Markov control processes in metric spaces
    Hernandez-Lerma, O
    Lasserre, JB
    ACTA APPLICANDAE MATHEMATICAE, 1998, 51 (02) : 123 - 139
12345