A note on policy algorithms for discounted Markov decision problems

被引：2

作者：

Ng, MK ^{[1
]}

机构：

[1] Univ Hong Kong, Dept Math, Pokfulam Rd, Hong Kong, Peoples R China

来源：

OPERATIONS RESEARCH LETTERS | 1999年 / 25卷 / 04期

关键词：

discounted Markov decision process; policy algorithm; matrices;

D O I：

10.1016/S0167-6377(99)00051-6

中图分类号：

C93 [管理学]; O22 [运筹学];

学科分类号：

070105 ; 12 ; 1201 ; 1202 ; 120202 ;

摘要：

In this note, we show that the evaluation phase in the policy iteration algorithm for the infinite horizon discounted Markov decision problem can be done in O(mN(2)) operations, where N is the number of states of the Markov decision process and m is the number of states in which the decision changes during the policy improvement phase. (C) 1999 Elsevier Science B.V. All rights reserved.

引用

页码：195 / 197

页数：3

共 50 条

[1] MODIFIED POLICY ITERATION ALGORITHMS FOR DISCOUNTED MARKOV DECISION PROBLEMS
PUTERMAN, ML
SHIN, MC
MANAGEMENT SCIENCE, 1978, 24 (11) : 1127 - 1137
[2] OPTIMIZATION OF DISCOUNTED MARKOV DECISION PROBLEMS
HASTINGS, NA
OPERATIONAL RESEARCH QUARTERLY, 1969, 20 (04) : 499 - &
[3] COMPUTATIONAL COMPARISON OF POLICY ITERATION ALGORITHMS FOR DISCOUNTED MARKOV DECISION PROCESSES.
Hartley, R.
Lavercombe, A.C.
Thomas, L.C.
1600, (13):
[4] COMPUTATIONAL COMPARISON OF POLICY ITERATION ALGORITHMS FOR DISCOUNTED MARKOV DECISION-PROCESSES
HARTLEY, R
LAVERCOMBE, AC
THOMAS, LC
COMPUTERS & OPERATIONS RESEARCH, 1986, 13 (04) : 411 - 420
[5] Hierarchical algorithms for discounted and weighted Markov decision processes
Abbad, M
Daoui, C
MATHEMATICAL METHODS OF OPERATIONS RESEARCH, 2003, 58 (02) : 237 - 245
[6] A note on deterministic approximation of discounted Markov decision processes
Cruz-Suarez, Hugo
Gordienko, Evgueni
Montes-de-Oca, Raul
APPLIED MATHEMATICS LETTERS, 2009, 22 (08) : 1252 - 1256
[7] Hierarchical algorithms for discounted and weighted Markov decision processes
M. Abbad
C. Daoui
Mathematical Methods of Operations Research, 2003, 58 : 237 - 245
[8] REWARD REVISION FOR DISCOUNTED MARKOV DECISION-PROBLEMS
WHITE, CC
THOMAS, LC
SCHERER, WT
OPERATIONS RESEARCH, 1985, 33 (06) : 1299 - 1315
[9] Primal-Dual Algorithms for Discounted Markov Decision Processes
Cogill, Randy
2015 EUROPEAN CONTROL CONFERENCE (ECC), 2015, : 260 - 265
[10] The complexity of Policy Iteration is exponential for discounted Markov Decision Processes
Hollanders, Romain
Delvenne, Jean-Charles
Jungers, Raphael M.
2012 IEEE 51ST ANNUAL CONFERENCE ON DECISION AND CONTROL (CDC), 2012, : 5997 - 6002

← 1 2 3 4 5 →