Solving semi-Markov decision problems using average reward reinforcement learning

Tapas K. Das; Abhijit Gosavi; Sridhar Mahadevan; Nicholas Marchalleck

doi:10.1287/mnsc.45.4.560

Solving semi-Markov decision problems using average reward reinforcement learning

Tapas K. Das
, Abhijit Gosavi
, Sridhar Mahadevan
, Nicholas Marchalleck

University of South Florida
Michigan State University
Cybear, Inc.

Research output: Contribution to journal › Article › peer-review

Original language	English
Pages (from-to)	560-574
Number of pages	15
Journal	Management Science
Volume	45
Issue number	4
DOIs	https://doi.org/10.1287/mnsc.45.4.560
State	Published - Apr 1999
Externally published	Yes

ASJC Scopus Subject Areas

Strategy and Management
Management Science and Operations Research

Access to Document

10.1287/mnsc.45.4.560

Cite this

@article{05ef559e3cf74b26b5da00e24ffc95e7,

title = "Solving semi-Markov decision problems using average reward reinforcement learning",

author = "Das, \{Tapas K.\} and Abhijit Gosavi and Sridhar Mahadevan and Nicholas Marchalleck",

year = "1999",

month = apr,

doi = "10.1287/mnsc.45.4.560",

language = "English",

volume = "45",

pages = "560--574",

journal = "Management Science",

issn = "0025-1909",

number = "4",

}

TY - JOUR

T1 - Solving semi-Markov decision problems using average reward reinforcement learning

AU - Das, Tapas K.

AU - Gosavi, Abhijit

AU - Mahadevan, Sridhar

AU - Marchalleck, Nicholas

PY - 1999/4

Y1 - 1999/4

UR - https://www.scopus.com/pages/publications/0032643313

UR - https://www.scopus.com/pages/publications/0032643313#tab=citedBy

U2 - 10.1287/mnsc.45.4.560

DO - 10.1287/mnsc.45.4.560

M3 - Article

AN - SCOPUS:0032643313

SN - 0025-1909

VL - 45

SP - 560

EP - 574

JO - Management Science

JF - Management Science

IS - 4

ER -

Solving semi-Markov decision problems using average reward reinforcement learning

ASJC Scopus Subject Areas

Access to Document

Other files and links

Fingerprint

Cite this