A VECTOR MINIMUM SUPERHARMONIC APPROACH TO SOLVING INFINITE-HORIZON DISCOUNTED MARKOV DECISION-PROCESSES

被引：0

作者：

WHITE, DJ

机构：

来源：

JOURNAL OF THE OPERATIONAL RESEARCH SOCIETY | 1992年 / 43卷 / 11期

关键词：

DECISION; MARKOV PROCESSES; VECTOR MINIMUM; SUPERHARMONICS;

D O I：

暂无

中图分类号：

C93 [管理学];

学科分类号：

12 ; 1201 ; 1202 ; 120202 ;

摘要：

In this paper a new algorithm is provided for obtaining approximately optimal policies for infinite-horizon discounted Markov decision processes. In addition, some of the properties of the algorithm are established. The algorithm is based upon the fact that the optimal value function is the unique vector minimum function within the superharmonic set.

引用

页码：1095 / 1102

页数：8

共 50 条

[21] Solution and forecast horizons for infinite-horizon nonhornogeneous Markov decision processes
Cheevaprawatdomrong, Torpong
Schochetman, Irwin E.
Smith, Robert L.
Garcia, Alfredo
MATHEMATICS OF OPERATIONS RESEARCH, 2007, 32 (01) : 51 - 72
[22] Approximate robust policy iteration for discounted infinite-horizon Markov decision processes with uncertain stationary parametric tiransition matrices
Li, Baohua
Si, Jennie
2007 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-6, 2007, : 2052 - 2057
[23] Belief Function Model for Reliable Optimal Set Estimation of Transition Matrices in Discounted Infinite-Horizon Markov Decision Processes
Li, Baohua
Si, Jennie
2011 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2011, : 1214 - 1221
[24] A SECONDARY APPROACH TO THE DISCOUNTED MODEL IN SEMI-MARKOV DECISION-PROCESSES
DONG, ZQ
SONG, JS
KEXUE TONGBAO, 1988, 33 (06): : 448 - 454
[25] Learning Infinite-Horizon Average-Reward Markov Decision Processes with Constraints
Chen, Liyu
Jain, Rahul
Luo, Haipeng
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
[26] MINIMIZING A THRESHOLD PROBABILITY IN DISCOUNTED MARKOV DECISION-PROCESSES
WHITE, DJ
JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS, 1993, 173 (02) : 634 - 646
[27] Zero-sum infinite-horizon discounted piecewise deterministic Markov games
Huang, Yonghui
Lian, Zhaotong
Guo, Xianping
MATHEMATICAL METHODS OF OPERATIONS RESEARCH, 2023, 97 (02) : 179 - 205
[28] Zero-sum infinite-horizon discounted piecewise deterministic Markov games
Yonghui Huang
Zhaotong Lian
Xianping Guo
Mathematical Methods of Operations Research, 2023, 97 : 179 - 205
[29] Economic MPC of Markov Decision Processes: Dissipativity in undiscounted infinite-horizon optimal control
Gros, Sebastien
Zanon, Mario
AUTOMATICA, 2022, 146
[30] SEPARABLE VALUE-FUNCTIONS FOR INFINITE HORIZON AVERAGE REWARD MARKOV DECISION-PROCESSES
WHITE, DJ
JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS, 1989, 144 (02) : 450 - 465

← 1 2 3 4 5 →