Some Remarks on the Variance in Markov Reward Processes

被引：0
|
作者：
Sladky, Karel [1 ]
机构：
[1] Acad Sci Czech Republic, Inst Informat Theory & Automat, Dept Econometr, CR-18208 Prague 8, Czech Republic
来源：
PROCEEDINGS OF THE 22ND INTERNATIONAL CONFERENCE ON MATHEMATICAL METHODS IN ECONOMICS 2004 | 2004年
关键词：
Markov reward processes with finite state space; expectation and variance of cumulative rewards;
D O I：
暂无
中图分类号：
F [经济];
学科分类号：
02 ;
摘要：
We consider Markov reward processes with finite state space both in discrete- and continuous-time setting. Explicit formulas for the second moment and variance of the cumulative (random) reward up to a given time point are obtained.
引用
收藏
页码：292 / 297
页数：6
相关论文
共 50 条
  • [31] Functional Reward Markov Decision Processes: Theory and Applications
    Weng, Paul
    Spanjaard, Olivier
    INTERNATIONAL JOURNAL ON ARTIFICIAL INTELLIGENCE TOOLS, 2017, 26 (03)
  • [32] CONVERGING MARKOV DECISION PROCESSES WITH MULTIPLICATIVE REWARD SYSTEM
    Fujita T.
    Bulletin of the Kyushu Institute of Technology - Pure and Applied Mathematics, 2023, 2023 (70): : 33 - 41
  • [33] Robust Average-Reward Markov Decision Processes
    Wang, Yue
    Velasquez, Alvaro
    Atia, George
    Prater-Bennette, Ashley
    Zou, Shaofeng
    THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 12, 2023, : 15215 - 15223
  • [34] Simulation-based optimization of Markov reward processes
    Marbach, Peter
    Tsitsiklis, John N.
    Proceedings of the IEEE Conference on Decision and Control, 1998, 3 : 2698 - 2703
  • [35] Average-Reward Decentralized Markov Decision Processes
    Petrik, Marek
    Zilberstein, Shlomo
    20TH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2007, : 1997 - 2002
  • [36] Simulation-based optimization of Markov reward processes
    Marbach, P
    Tsitsiklis, JN
    PROCEEDINGS OF THE 37TH IEEE CONFERENCE ON DECISION AND CONTROL, VOLS 1-4, 1998, : 2698 - 2703
  • [37] PARTIALLY OBSERVABLE SEMI-MARKOV REWARD PROCESSES
    MASUDA, Y
    JOURNAL OF APPLIED PROBABILITY, 1993, 30 (03) : 548 - 560
  • [38] SOME REMARKS ON ASYMMETRIC PROCESSES
    MILLAR, PW
    ANNALS OF MATHEMATICAL STATISTICS, 1972, 43 (02): : 597 - &
  • [39] Partially observable Markov decision processes with reward information
    Cao, XR
    Guo, XP
    2004 43RD IEEE CONFERENCE ON DECISION AND CONTROL (CDC), VOLS 1-5, 2004, : 4393 - 4398
  • [40] Exact distributions for reward functions on semi-Markov and Markov additive processes
    Stefanov, Valeri T.
    JOURNAL OF APPLIED PROBABILITY, 2006, 43 (04) : 1053 - 1065
12345