On uniformly nearly-optimal Markov strategies

J. Wal, van der

doi:10.1007/978-3-642-68997-0_80

On uniformly nearly-optimal Markov strategies

J. Wal, van der

Stochastic Operations Research

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

In this paper the following result is proved. In any total reward countable state Markov decision process a Markov strategy IT exists which is uniformly nearly-optimal in the following sense: v(i,π,) ≥ v*(i) − ε − εu*(i) for any initial state i. Here v* denotes the value function of the process and u* denotes the value of the process if all negative rewards are neglected.

Original language	English
Title of host publication	Operations Research Proceedings 1982 (Papers of the 11th Annual Meeting of DGOR, Frankfurt am Main, Germany, September 22-24, 1982)
Editors	W. Bühler, B. Fleischmann, K.P. Schuster, L. Streitferdt, H. Zander
Place of Publication	Berlin
Publisher	Springer
Pages	461-467
ISBN (Electronic)	978-3-642-68997-0
ISBN (Print)	3-540-12239-7, 978-3-540-12239-5
DOIs	https://doi.org/10.1007/978-3-642-68997-0_80
Publication status	Published - 1983

Publication series

Name	Operations Research Proceedings (ORP)
Volume	1982

Access to Document

10.1007/978-3-642-68997-0_80

Cite this

Wal, van der, J. (1983). On uniformly nearly-optimal Markov strategies. In W. Bühler, B. Fleischmann, K. P. Schuster, L. Streitferdt, & H. Zander (Eds.), Operations Research Proceedings 1982 (Papers of the 11th Annual Meeting of DGOR, Frankfurt am Main, Germany, September 22-24, 1982) (pp. 461-467). (Operations Research Proceedings (ORP); Vol. 1982). Springer. https://doi.org/10.1007/978-3-642-68997-0_80

@inproceedings{9d2251d678ce423f9985c8371859465d,

title = "On uniformly nearly-optimal Markov strategies",

abstract = "In this paper the following result is proved. In any total reward countable state Markov decision process a Markov strategy IT exists which is uniformly nearly-optimal in the following sense: v(i,π,) ≥ v*(i) − ε − εu*(i) for any initial state i. Here v* denotes the value function of the process and u* denotes the value of the process if all negative rewards are neglected.",

author = "{Wal, van der}, J.",

year = "1983",

doi = "10.1007/978-3-642-68997-0_80",

language = "English",

isbn = "3-540-12239-7",

series = "Operations Research Proceedings (ORP)",

publisher = "Springer",

pages = "461--467",

editor = "W. B{\"u}hler and B. Fleischmann and K.P. Schuster and L. Streitferdt and H. Zander",

booktitle = "Operations Research Proceedings 1982 (Papers of the 11th Annual Meeting of DGOR, Frankfurt am Main, Germany, September 22-24, 1982)",

address = "Germany",

}

Wal, van der, J 1983, On uniformly nearly-optimal Markov strategies. in W Bühler, B Fleischmann, KP Schuster, L Streitferdt & H Zander (eds), Operations Research Proceedings 1982 (Papers of the 11th Annual Meeting of DGOR, Frankfurt am Main, Germany, September 22-24, 1982). Operations Research Proceedings (ORP), vol. 1982, Springer, Berlin, pp. 461-467. https://doi.org/10.1007/978-3-642-68997-0_80

On uniformly nearly-optimal Markov strategies. / Wal, van der, J.

Operations Research Proceedings 1982 (Papers of the 11th Annual Meeting of DGOR, Frankfurt am Main, Germany, September 22-24, 1982). ed. / W. Bühler; B. Fleischmann; K.P. Schuster; L. Streitferdt; H. Zander. Berlin : Springer, 1983. p. 461-467 (Operations Research Proceedings (ORP); Vol. 1982).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - On uniformly nearly-optimal Markov strategies

AU - Wal, van der, J.

PY - 1983

Y1 - 1983

N2 - In this paper the following result is proved. In any total reward countable state Markov decision process a Markov strategy IT exists which is uniformly nearly-optimal in the following sense: v(i,π,) ≥ v*(i) − ε − εu*(i) for any initial state i. Here v* denotes the value function of the process and u* denotes the value of the process if all negative rewards are neglected.

AB - In this paper the following result is proved. In any total reward countable state Markov decision process a Markov strategy IT exists which is uniformly nearly-optimal in the following sense: v(i,π,) ≥ v*(i) − ε − εu*(i) for any initial state i. Here v* denotes the value function of the process and u* denotes the value of the process if all negative rewards are neglected.

U2 - 10.1007/978-3-642-68997-0_80

DO - 10.1007/978-3-642-68997-0_80

M3 - Conference contribution

SN - 3-540-12239-7

SN - 978-3-540-12239-5

T3 - Operations Research Proceedings (ORP)

SP - 461

EP - 467

BT - Operations Research Proceedings 1982 (Papers of the 11th Annual Meeting of DGOR, Frankfurt am Main, Germany, September 22-24, 1982)

A2 - Bühler, W.

A2 - Fleischmann, B.

A2 - Schuster, K.P.

A2 - Streitferdt, L.

A2 - Zander, H.

PB - Springer

CY - Berlin

ER -

Wal, van der J. On uniformly nearly-optimal Markov strategies. In Bühler W, Fleischmann B, Schuster KP, Streitferdt L, Zander H, editors, Operations Research Proceedings 1982 (Papers of the 11th Annual Meeting of DGOR, Frankfurt am Main, Germany, September 22-24, 1982). Berlin: Springer. 1983. p. 461-467. (Operations Research Proceedings (ORP)). doi: 10.1007/978-3-642-68997-0_80

On uniformly nearly-optimal Markov strategies

Abstract

Publication series

Access to Document

Fingerprint

Cite this