A Modified Value Iteration Algorithm for Discounted Markov Decision Processes

被引：1

作者：

Chafik, Sanaa ^{[1
]}

Daoui, Cherki ^{[1
]}

机构：

[1] Univ Sultan Moulay Slimane, Lab Informat Proc & Decis Support, Beni Mellal, Morocco

来源：

JOURNAL OF ELECTRONIC COMMERCE IN ORGANIZATIONS | 2015年 / 13卷 / 03期

关键词：

Discounted Reward Criterion; Markov Decision Processes; Open MP; Parallelizing; Value Iteration Algorithm;

D O I：

10.4018/JECO.2015070104

中图分类号：

F [经济];

学科分类号：

02 ;

摘要：

As many real applications need a large amount of states, the classical methods are intractable for solving large Markov Decision Processes. The decomposition technique basing on the topology of each state in the associated graph and the parallelization technique are very useful methods to cope with this problem. In this paper, the authors propose a Modified Value Iteration algorithm, adding the parallelism technique. They test their implementation on artificial data using an Open MP that offers a significant speed-up.

引用

页码：47 / 57

页数：11

共 50 条

[1] A NEW PARALLELIZED OF HIERARCHICAL VALUE ITERATION ALGORITHM FOR DISCOUNTED MARKOV DECISION PROCESSES
Nachaoui, Mourad
Chafik, Sanae
Daoui, Cherki
[J]. DISCRETE AND CONTINUOUS DYNAMICAL SYSTEMS-SERIES S, 2022,
[2] THE CONVERGENCE OF VALUE-ITERATION IN DISCOUNTED MARKOV DECISION-PROCESSES
WHITE, DJ
SCHERER, WT
[J]. JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS, 1994, 182 (02) : 348 - 360
[3] Uniform convergence of value iteration policies for discounted Markov decision processes
Cruz-Suarez, Daniel
Montes-De-Oca, Raul
[J]. BOLETIN DE LA SOCIEDAD MATEMATICA MEXICANA, 2006, 12 (01): : 133 - 148
[4] Topological Value Iteration Algorithm for Markov Decision Processes
Dai, Peng
Goldsmith, Judy
[J]. 20TH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2007, : 1860 - 1865
[5] Value Iteration and Action ε-Approximation of Optimal Policies in Discounted Markov Decision Processes
Montes-De-Oca, Raul
Lemus-Rodriguez, Enrique
[J]. RECENT ADVANCES IN APPLIED MATHEMATICS, 2009, : 213 - +
[6] MONOTONE VALUE-ITERATION FOR DISCOUNTED FINITE MARKOV DECISION-PROCESSES
WHITE, DJ
[J]. JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS, 1985, 109 (02) : 311 - 324
[7] An optimistic value iteration for mean-variance optimization in discounted Markov decision processes
Ma, Shuai
Ma, Xiaoteng
Xia, Li
[J]. RESULTS IN CONTROL AND OPTIMIZATION, 2022, 8
[8] COMPUTATIONAL COMPARISON OF VALUE-ITERATION ALGORITHMS FOR DISCOUNTED MARKOV DECISION-PROCESSES
THOMAS, LC
HARLEY, R
LAVERCOMBE, AC
[J]. OPERATIONS RESEARCH LETTERS, 1983, 2 (02) : 72 - 76
[9] SERIAL AND PARALLEL VALUE-ITERATION ALGORITHMS FOR DISCOUNTED MARKOV DECISION-PROCESSES
ARCHIBALD, TW
MCKINNON, KIM
THOMAS, LC
[J]. EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 1993, 67 (02) : 188 - 203
[10] The complexity of Policy Iteration is exponential for discounted Markov Decision Processes
Hollanders, Romain
Delvenne, Jean-Charles
Jungers, Raphael M.
[J]. 2012 IEEE 51ST ANNUAL CONFERENCE ON DECISION AND CONTROL (CDC), 2012, : 5997 - 6002

← 1 2 3 4 5 →