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

页码：90 / +

页数：2

共 50 条

[41] Linear programming approximations for Markov control processes in metric spaces
Hernandez-Lerma, O
Lasserre, JB
PROCEEDINGS OF THE 36TH IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-5, 1997, : 2291 - 2292
[42] An infinite-dimensional linear programming algorithm for deterministic semi-markov decision processes on borel spaces
Klabjan, Diego
Adelman, Daniel
MATHEMATICS OF OPERATIONS RESEARCH, 2007, 32 (03) : 528 - 550
[43] LINEAR PROGRAMMING CONSIDERATIONS ON MARKOVIAN DECISION PROCESSES WITH NO DISCOUNTING
OSAKI, S
MINE, H
JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS, 1969, 26 (01) : 221 - &
[44] Time aggregated Markov decision processes via standard dynamic programming
Arruda, Edilson F.
Fragoso, Marcelo D.
OPERATIONS RESEARCH LETTERS, 2011, 39 (03) : 193 - 197
[45] A Dynamic Programming Algorithm for Decentralized Markov Decision Processes with a Broadcast Structure
Wu, Jeff
Lall, Sanjay
49TH IEEE CONFERENCE ON DECISION AND CONTROL (CDC), 2010, : 6143 - 6148
[46] Markov Decision Processes Specified by Probabilistic Logic Programming: Representation and Solution
Bueno, Thiago P.
Maua, Denis D.
de Barros, Leliane N.
Cozman, Fabio G.
PROCEEDINGS OF 2016 5TH BRAZILIAN CONFERENCE ON INTELLIGENT SYSTEMS (BRACIS 2016), 2016, : 337 - 342
[47] Standard Dynamic Programming Applied to Time Aggregated Markov Decision Processes
Arruda, Edilson F.
Fragoso, Marcelo D.
PROCEEDINGS OF THE 48TH IEEE CONFERENCE ON DECISION AND CONTROL, 2009 HELD JOINTLY WITH THE 2009 28TH CHINESE CONTROL CONFERENCE (CDC/CCC 2009), 2009, : 2576 - 2580
[48] On Dynamic Programming Decompositions of Static Risk Measures in Markov Decision Processes
Hau, Jia Lin
Delage, Erick
Ghavamzadeh, Mohammad
Petrik, Marek
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
[49] Answer set programming for non-stationary Markov decision processes
Ferreira, Leonardo A.
Bianchi, Reinaldo A. C.
Santos, Paulo E.
Lopez de Mantaras, Ramon
APPLIED INTELLIGENCE, 2017, 47 (04) : 993 - 1007
[50] Erratum to: Risk-averse dynamic programming for Markov decision processes
Andrzej Ruszczyński
Mathematical Programming, 2014, 145 : 601 - 604

← 1 2 3 4 5 →