首页
学术期刊
论文检测
AIGC检测
热点
更多
数据
OPTIMAL AVERAGE VALUE CONVERGENCE IN NONHOMOGENEOUS MARKOV DECISION-PROCESSES
被引:13
|
作者
:
PARK, YS
论文数:
0
引用数:
0
h-index:
0
机构:
UNIV MICHIGAN,DEPT IND & OPERAT ENGN,ANN ARBOR,MI 48109
UNIV MICHIGAN,DEPT IND & OPERAT ENGN,ANN ARBOR,MI 48109
PARK, YS
[
1
]
BEAN, JC
论文数:
0
引用数:
0
h-index:
0
机构:
UNIV MICHIGAN,DEPT IND & OPERAT ENGN,ANN ARBOR,MI 48109
UNIV MICHIGAN,DEPT IND & OPERAT ENGN,ANN ARBOR,MI 48109
BEAN, JC
[
1
]
SMITH, RL
论文数:
0
引用数:
0
h-index:
0
机构:
UNIV MICHIGAN,DEPT IND & OPERAT ENGN,ANN ARBOR,MI 48109
UNIV MICHIGAN,DEPT IND & OPERAT ENGN,ANN ARBOR,MI 48109
SMITH, RL
[
1
]
机构
:
[1]
UNIV MICHIGAN,DEPT IND & OPERAT ENGN,ANN ARBOR,MI 48109
来源
:
JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS
|
1993年
/ 179卷
/ 02期
关键词
:
D O I
:
10.1006/jmaa.1993.1367
中图分类号
:
O29 [应用数学];
学科分类号
:
070104 ;
摘要
:
We address the undiscounted nonhomogeneous Markov decision process with average reward criterion and prove two structural results. First, we establish equivalence of this problem to a discounted Markov decision process by means of an ergodic coefficient embedded in the original problem. Second, we prove, for the original problem, that the optimal finite horizon average values converge to the infinite horizon optimal average value under an ergodic condition. © 1993 Academic Press, Inc.
引用
收藏
页码:525 / 536
页数:12
相关论文
共 50 条
[41]
A UNIFIED APPROACH TO ADAPTIVE-CONTROL OF AVERAGE REWARD MARKOV DECISION-PROCESSES
HUBNER, G
论文数:
0
引用数:
0
h-index:
0
机构:
UNIV HAMBURG,INST MATH STOCHASTIK,D-2000 HAMBURG 13,FED REP GER
UNIV HAMBURG,INST MATH STOCHASTIK,D-2000 HAMBURG 13,FED REP GER
HUBNER, G
OR SPEKTRUM,
1988,
10
(03)
: 161
-
166
[42]
FUNCTIONAL-CHARACTERIZATION FOR AVERAGE COST MARKOV DECISION-PROCESSES WITH DOEBLINS CONDITIONS
KURANO, M
论文数:
0
引用数:
0
h-index:
0
KURANO, M
COMPUTERS & MATHEMATICS WITH APPLICATIONS,
1991,
21
(11-12)
: 57
-
63
[43]
RECURSIVE ADAPTIVE-CONTROL OF MARKOV DECISION-PROCESSES WITH THE AVERAGE REWARD CRITERION
CAVAZOSCADENA, R
论文数:
0
引用数:
0
h-index:
0
机构:
INST POLITECN NACL,CINVESTAV,DEPT MATH,MEXICO CITY 07000,DF,MEXICO
INST POLITECN NACL,CINVESTAV,DEPT MATH,MEXICO CITY 07000,DF,MEXICO
CAVAZOSCADENA, R
HERNANDEZLERMA, O
论文数:
0
引用数:
0
h-index:
0
机构:
INST POLITECN NACL,CINVESTAV,DEPT MATH,MEXICO CITY 07000,DF,MEXICO
INST POLITECN NACL,CINVESTAV,DEPT MATH,MEXICO CITY 07000,DF,MEXICO
HERNANDEZLERMA, O
APPLIED MATHEMATICS AND OPTIMIZATION,
1991,
23
(02):
: 193
-
207
[44]
REAL APPLICATIONS OF MARKOV DECISION-PROCESSES
WHITE, DJ
论文数:
0
引用数:
0
h-index:
0
机构:
Manchester Univ, Manchester, Engl, Manchester Univ, Manchester, Engl
WHITE, DJ
INTERFACES,
1985,
15
(06)
: 73
-
83
[45]
ISOTONE POLICIES FOR THE VALUE-ITERATION METHOD FOR MARKOV DECISION-PROCESSES
WHITE, DJ
论文数:
0
引用数:
0
h-index:
0
机构:
UNIV MANCHESTER,DEPT DECIS THEORY,MANCHESTER M13 9PL,LANCS,ENGLAND
UNIV MANCHESTER,DEPT DECIS THEORY,MANCHESTER M13 9PL,LANCS,ENGLAND
WHITE, DJ
OR SPEKTRUM,
1984,
6
(04)
: 223
-
227
[46]
THE DETERMINATION OF APPROXIMATELY OPTIMAL POLICIES IN MARKOV DECISION-PROCESSES BY THE USE OF BOUNDS
WHITE, DJ
论文数:
0
引用数:
0
h-index:
0
WHITE, DJ
JOURNAL OF THE OPERATIONAL RESEARCH SOCIETY,
1982,
33
(03)
: 253
-
259
[47]
Optimal Approximation of Average Reward Markov Decision Processes
Y. F. Sapronov
论文数:
0
引用数:
0
h-index:
0
机构:
Moscow Institute of Physics and Technology,
Moscow Institute of Physics and Technology,
Y. F. Sapronov
N. E. Yudin
论文数:
0
引用数:
0
h-index:
0
机构:
Higher School of Economics University,undefined
Moscow Institute of Physics and Technology,
N. E. Yudin
Computational Mathematics and Mathematical Physics,
2025,
65
(3)
: 567
-
581
[48]
SUFFICIENT STATISTICS FOR MARKOV DECISION-PROCESSES
BATHER, JA
论文数:
0
引用数:
0
h-index:
0
机构:
UNIV SUSSEX,BRIGHTON,E SUSSEX,ENGLAND
UNIV SUSSEX,BRIGHTON,E SUSSEX,ENGLAND
BATHER, JA
ADVANCES IN APPLIED PROBABILITY,
1978,
10
(02)
: 307
-
308
[49]
MARKOV DECISION-PROCESSES - PUTERMAN,ML
ORMAN, A
论文数:
0
引用数:
0
h-index:
0
ORMAN, A
INTERFACES,
1995,
25
(02)
: 93
-
94
[50]
MARKOV DECISION-PROCESSES WITH MULTIPLE COSTS
GHOSH, MK
论文数:
0
引用数:
0
h-index:
0
机构:
Tata Institute of Fundamental Research, Bangalore Centre
GHOSH, MK
OPERATIONS RESEARCH LETTERS,
1990,
9
(04)
: 257
-
260
←
1
2
3
4
5
→