Total Expected Discounted Reward MDPS: Existence of Optimal Policies

Eugene A. Feinberg

doi:10.1002/9780470400531.eorms0906

Total Expected Discounted Reward MDPS: Existence of Optimal Policies

Eugene A. Feinberg

Applied Mathematics and Statistics

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

4 Scopus citations

Abstract

This article describes the results on the existence of optimal and nearly optimal policies for Markov Decision Processes (MDPs) with total expected discounted rewards. The problem of optimization of total expected discounted rewards for MDPs is also known under the name of discounted dynamic programming.

Original language	English
Title of host publication	Wiley Encyclopedia of Operations Research and Management Science
Publisher	wiley
Pages	1-8
Number of pages	8
ISBN (Electronic)	9780470400531
ISBN (Print)	9780470400630
DOIs	https://doi.org/10.1002/9780470400531.eorms0906
State	Published - Jan 1 2010

Keywords

discounted rewards
dynamic programming
Markov decision process
optimal policy
reward function

Access to Document

10.1002/9780470400531.eorms0906

Cite this

@inbook{7fad7d74db034cd7ab8e4eb43a2d4e15,

title = "Total Expected Discounted Reward MDPS: Existence of Optimal Policies",

abstract = "This article describes the results on the existence of optimal and nearly optimal policies for Markov Decision Processes (MDPs) with total expected discounted rewards. The problem of optimization of total expected discounted rewards for MDPs is also known under the name of discounted dynamic programming.",

keywords = "discounted rewards, dynamic programming, Markov decision process, optimal policy, reward function",

author = "Feinberg, \{Eugene A.\}",

year = "2010",

month = jan,

day = "1",

doi = "10.1002/9780470400531.eorms0906",

language = "English",

isbn = "9780470400630",

pages = "1--8",

booktitle = "Wiley Encyclopedia of Operations Research and Management Science",

publisher = "wiley",

}

TY - CHAP

T1 - Total Expected Discounted Reward MDPS

T2 - Existence of Optimal Policies

AU - Feinberg, Eugene A.

PY - 2010/1/1

Y1 - 2010/1/1

N2 - This article describes the results on the existence of optimal and nearly optimal policies for Markov Decision Processes (MDPs) with total expected discounted rewards. The problem of optimization of total expected discounted rewards for MDPs is also known under the name of discounted dynamic programming.

AB - This article describes the results on the existence of optimal and nearly optimal policies for Markov Decision Processes (MDPs) with total expected discounted rewards. The problem of optimization of total expected discounted rewards for MDPs is also known under the name of discounted dynamic programming.

KW - discounted rewards

KW - dynamic programming

KW - Markov decision process

KW - optimal policy

KW - reward function

UR - https://www.scopus.com/pages/publications/105026047869

U2 - 10.1002/9780470400531.eorms0906

DO - 10.1002/9780470400531.eorms0906

M3 - Chapter

AN - SCOPUS:105026047869

SN - 9780470400630

SP - 1

EP - 8

BT - Wiley Encyclopedia of Operations Research and Management Science

PB - wiley

ER -

Total Expected Discounted Reward MDPS: Existence of Optimal Policies

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this