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

[31] Discounted Markov decision processes with fuzzy costs
Semmouri, Abdellatif
Jourhmane, Mostafa
Belhallaj, Zineb
[J]. ANNALS OF OPERATIONS RESEARCH, 2020, 295 (02) : 769 - 786
[32] Discounted cost Markov decision processes with a constraint
Wakuta, K
[J]. PROBABILITY IN THE ENGINEERING AND INFORMATIONAL SCIENCES, 1998, 12 (02) : 177 - 187
[33] ON CONVERGENCE OF VALUE ITERATION FOR A CLASS OF TOTAL COST MARKOV DECISION PROCESSES
Yu, Huizhen
[J]. SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 2015, 53 (04) : 1982 - 2016
[34] Advantage Based Value Iteration for Markov Decision Processes with Unknown Rewards
Alizadeh, Pegah
Chevaleyre, Yann
Levy, Francois
[J]. 2016 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2016, : 3837 - 3844
[35] THE VARIANCE OF DISCOUNTED MARKOV DECISION-PROCESSES
SOBEL, MJ
[J]. JOURNAL OF APPLIED PROBABILITY, 1982, 19 (04) : 794 - 802
[36] Value Iteration for Average Cost Markov Decision Processes in Borel Spaces
Zhu, Quanxin
Guo, Xianping
[J]. APPLIED MATHEMATICS RESEARCH EXPRESS, 2005, (02) : 61 - 76
[37] Approximate Value Iteration for Risk-Aware Markov Decision Processes
Yu, Pengqian
Haskell, William B.
Xu, Huan
[J]. IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2018, 63 (09) : 3135 - 3142
[38] ASYNCHRONOUS VALUE ITERATION FOR MARKOV DECISION PROCESSES WITH CONTINUOUS STATE SPACES
Yang, Xiangyu
Hu, Jian-Qiang
Hu, Jiaqiao
Peng, Yijie
[J]. 2020 WINTER SIMULATION CONFERENCE (WSC), 2020, : 2856 - 2866
[39] Generalized Second-Order Value Iteration in Markov Decision Processes
Kamanchi, Chandramouli
Diddigi, Raghuram Bharadwaj
Bhatnagar, Shalabh
[J]. IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2022, 67 (08) : 4241 - 4247
[40] AsyncQVI: Asynchronous-Parallel Q-Value Iteration for Discounted Markov Decision Processes with Near-Optimal Sample Complexity
Zeng, Yibo
Feng, Fei
Yin, Wotao
[J]. INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 108, 2020, 108 : 713 - 722

← 1 2 3 4 5 →