MULTI-ARMED BANDITS UNDER GENERAL DEPRECIATION AND COMMITMENT

Generally, the multi-armed has been studied under the setting that at each time step over an infinite horizon a controller chooses to activate a single process or bandit out of a finite collection of independent processes (statistical experiments, populations, etc.) for a single period, receiving a...

Full description

Saved in:
Bibliographic Details
Published inProbability in the engineering and informational sciences Vol. 29; no. 1; pp. 51 - 76
Main Authors Cowan, Wesley, Katehakis, Michael N.
Format Journal Article
LanguageEnglish
Published New York, USA Cambridge University Press 01.01.2015
Subjects
Online AccessGet full text

Cover

Loading…
Abstract Generally, the multi-armed has been studied under the setting that at each time step over an infinite horizon a controller chooses to activate a single process or bandit out of a finite collection of independent processes (statistical experiments, populations, etc.) for a single period, receiving a reward that is a function of the activated process, and in doing so advancing the chosen process. Classically, rewards are discounted by a constant factor β∈(0, 1) per round. In this paper, we present a solution to the problem, with potentially non-Markovian, uncountable state space reward processes, under a framework in which, first, the discount factors may be non-uniform and vary over time, and second, the periods of activation of each bandit may be not be fixed or uniform, subject instead to a possibly stochastic duration of activation before a change to a different bandit is allowed. The solution is based on generalized restart-in-state indices, and it utilizes a view of the problem not as “decisions over state space” but rather “decisions over time”.
AbstractList Generally, the multi-armed has been studied under the setting that at each time step over an infinite horizon a controller chooses to activate a single process or bandit out of a finite collection of independent processes (statistical experiments, populations, etc.) for a single period, receiving a reward that is a function of the activated process, and in doing so advancing the chosen process. Classically, rewards are discounted by a constant factor [beta]∈(0, 1) per round. In this paper, we present a solution to the problem, with potentially non-Markovian, uncountable state space reward processes, under a framework in which, first, the discount factors may be non-uniform and vary over time, and second, the periods of activation of each bandit may be not be fixed or uniform, subject instead to a possibly stochastic duration of activation before a change to a different bandit is allowed. The solution is based on generalized restart-in-state indices, and it utilizes a view of the problem not as "decisions over state space" but rather "decisions over time".
Generally, the multi-armed has been studied under the setting that at each time step over an infinite horizon a controller chooses to activate a single process or bandit out of a finite collection of independent processes (statistical experiments, populations, etc.) for a single period, receiving a reward that is a function of the activated process, and in doing so advancing the chosen process. Classically, rewards are discounted by a constant factor β∈(0, 1) per round. In this paper, we present a solution to the problem, with potentially non-Markovian, uncountable state space reward processes, under a framework in which, first, the discount factors may be non-uniform and vary over time, and second, the periods of activation of each bandit may be not be fixed or uniform, subject instead to a possibly stochastic duration of activation before a change to a different bandit is allowed. The solution is based on generalized restart-in-state indices, and it utilizes a view of the problem not as “decisions over state space” but rather “decisions over time”.
Generally, the multi-armed has been studied under the setting that at each time step over an infinite horizon a controller chooses to activate a single process or bandit out of a finite collection of independent processes (statistical experiments, populations, etc.) for a single period, receiving a reward that is a function of the activated process, and in doing so advancing the chosen process. Classically, rewards are discounted by a constant factor beta (0, 1) per round. In this paper, we present a solution to the problem, with potentially non-Markovian, uncountable state space reward processes, under a framework in which, first, the discount factors may be non-uniform and vary over time, and second, the periods of activation of each bandit may be not be fixed or uniform, subject instead to a possibly stochastic duration of activation before a change to a different bandit is allowed. The solution is based on generalized restart-in-state indices, and it utilizes a view of the problem not as "decisions over state space" but rather "decisions over time".
Generally, the multi-armed has been studied under the setting that at each time step over an infinite horizon a controller chooses to activate a single process or bandit out of a finite collection of independent processes (statistical experiments, populations, etc.) for a single period, receiving a reward that is a function of the activated process, and in doing so advancing the chosen process. Classically, rewards are discounted by a constant factor β∈(0, 1) per round. In this paper, we present a solution to the problem, with potentially non-Markovian, uncountable state space reward processes, under a framework in which, first, the discount factors may be non-uniform and vary over time, and second, the periods of activation of each bandit may be not be fixed or uniform, subject instead to a possibly stochastic duration of activation before a change to a different bandit is allowed. The solution is based on generalized restart-in-state indices, and it utilizes a view of the problem not as “decisions over state space” but rather “decisions over time”.
Author Katehakis, Michael N.
Cowan, Wesley
Author_xml – sequence: 1
  givenname: Wesley
  surname: Cowan
  fullname: Cowan, Wesley
  email: cwcowan@mah.rutgers.edu
  organization: Department of Mathematics, Rutgers University, 110 Frelinghuysen Road, Piscataway, NJ 08854, USA E-mail: cwcowan@mah.rutgers.edu
– sequence: 2
  givenname: Michael N.
  surname: Katehakis
  fullname: Katehakis, Michael N.
  email: mnk@rutgers.edu
  organization: Department of Management Science and Information Systems, Rutgers Business School, Newark and New Brunswick, 100 Rockafeller Road, Piscataway, NJ 08854, USA E-mail: mnk@rutgers.edu
BookMark eNp9kEFPgzAUxxujidv0A3gj8eIFbWkp7cEDQp0kwAxjZwKsGBYGs2UHv71dtoOZ0cPLO7zf772X_xRc9kMvAbhD8BFB5D0toUM5p4QhAiF0kHcBJohQbjPuokswOYztw_waTLXeGMZjhE3Ac7KK88j2s0SE1oufhlG-tFZpKDJrLlKR-bEVivdMBJGfR4vUMoQVLJIkyhOR5jfgqik7LW9PfQbyV5EHb3a8mEeBH9s1oXi0qTTXmNsguJalxI1TVRWtPBcjLiuCCKsJw9yUy9fQk5xQiF0JJWXMoSXGM_BwXLtTw-de6rHYtrqWXVf2ctjrAlEKIcHcdQ16f4Zuhr3qzXOGIthxmMOZodCRqtWgtZJNsVPttlRfBYLFIc_iV57G8c6cuh3LsR36UZVt96-JT2a5rVS7_pA_nvrT-gahloGL
CitedBy_id crossref_primary_10_1007_s10479_015_1965_7
crossref_primary_10_1109_TCNS_2017_2774046
crossref_primary_10_1007_s10479_024_06336_3
crossref_primary_10_1137_19M1282386
crossref_primary_10_1002_nav_22145
crossref_primary_10_1016_j_peva_2021_102208
crossref_primary_10_1007_s10479_020_03536_5
crossref_primary_10_1017_S026996481600036X
crossref_primary_10_1287_moor_2019_0998
crossref_primary_10_1017_S0269964818000529
Cites_doi 10.1007/978-1-4757-1776-1
10.1109/ROBOT.2008.4543563
10.1109/TAC.1985.1103989
10.1287/moor.1050.0165
10.1017/S0001867800017456
10.1287/opre.1070.0444
10.1017/S0269964810000021
10.1109/MCOM.2012.6257528
10.1111/j.2517-6161.1979.tb01068.x
10.1561/9781601986276
10.1287/moor.12.2.262
10.1002/nav.3800070429
10.1073/pnas.92.19.8584
10.1007/978-0-387-49819-5_6
10.1090/S0002-9947-1952-0050209-9
10.1017/S0021900200039176
10.1017/S0269964811000015
10.1287/moor.22.1.222
10.1214/aoap/1028903380
10.1016/j.spl.2008.01.049
10.1006/aama.1996.0007
10.1007/BF02191765
10.1073/pnas.90.4.1232
10.1016/0196-8858(85)90002-8
10.1109/ALLERTON.2010.5706896
10.1080/01966324.1991.10737307
10.5711/morj.14.2.41
10.1214/lnms/1215540286
10.1214/10-AAP705
10.1002/9780470980033
10.1214/aoap/1034968239
10.1109/TSP.2010.2041600
10.1080/17442508.2010.514051
10.1080/17442509008833627
10.1109/ACSSC.2012.6489015
10.1007/s10479-013-1430-4
10.1214/aoap/1177005588
10.1214/aoap/1177005207
10.1109/9.222316
ContentType Journal Article
Copyright Copyright © Cambridge University Press 2014
Copyright_xml – notice: Copyright © Cambridge University Press 2014
DBID AAYXX
CITATION
3V.
7SC
7TB
7XB
88I
8AL
8FD
8FE
8FG
8FK
ABJCF
ABUWG
AFKRA
ARAPS
AZQEC
BENPR
BGLVJ
CCPQU
DWQXO
FR3
GNUQQ
HCIFZ
JQ2
K7-
KR7
L6V
L7M
L~C
L~D
M0N
M2P
M7S
P5Z
P62
PHGZM
PHGZT
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
PTHSS
Q9U
DOI 10.1017/S0269964814000217
DatabaseName CrossRef
ProQuest Central (Corporate)
Computer and Information Systems Abstracts
Mechanical & Transportation Engineering Abstracts
ProQuest Central (purchase pre-March 2016)
Science Database (Alumni Edition)
Computing Database (Alumni Edition)
Technology Research Database
ProQuest SciTech Collection
ProQuest Technology Collection
ProQuest Central (Alumni) (purchase pre-March 2016)
Materials Science & Engineering Collection
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest Central
Technology Collection
ProQuest One
ProQuest Central Korea
Engineering Research Database
ProQuest Central Student
SciTech Premium Collection
ProQuest Computer Science Collection
Computer Science Database
Civil Engineering Abstracts
ProQuest Engineering Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
Computing Database
Science Database
Engineering Database
Advanced Technologies & Aerospace Database
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Premium
ProQuest One Academic (New)
ProQuest One Academic Middle East (New)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic
ProQuest One Academic UKI Edition
ProQuest Central China
Engineering Collection
ProQuest Central Basic
DatabaseTitle CrossRef
Computer Science Database
ProQuest Central Student
Technology Collection
Technology Research Database
Computer and Information Systems Abstracts – Academic
ProQuest One Academic Middle East (New)
Mechanical & Transportation Engineering Abstracts
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
ProQuest Central (Alumni Edition)
SciTech Premium Collection
ProQuest One Community College
ProQuest Central China
ProQuest Central
ProQuest One Applied & Life Sciences
ProQuest Engineering Collection
ProQuest Central Korea
ProQuest Central (New)
Advanced Technologies Database with Aerospace
Engineering Collection
Advanced Technologies & Aerospace Collection
Civil Engineering Abstracts
ProQuest Computing
Engineering Database
ProQuest Science Journals (Alumni Edition)
ProQuest Central Basic
ProQuest Science Journals
ProQuest Computing (Alumni Edition)
ProQuest One Academic Eastern Edition
ProQuest Technology Collection
ProQuest SciTech Collection
Computer and Information Systems Abstracts Professional
Advanced Technologies & Aerospace Database
ProQuest One Academic UKI Edition
Materials Science & Engineering Collection
Engineering Research Database
ProQuest One Academic
ProQuest Central (Alumni)
ProQuest One Academic (New)
DatabaseTitleList Computer Science Database

Civil Engineering Abstracts
CrossRef
Database_xml – sequence: 1
  dbid: 8FG
  name: ProQuest Technology Collection
  url: https://search.proquest.com/technologycollection1
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
Engineering
DocumentTitleAlternate W. Cowan and M. N. Katehakis
MULTI-ARMED BANDITS UNDER GENERAL DEPRECIATION AND COMMITMENT
EISSN 1469-8951
EndPage 76
ExternalDocumentID 3550930891
10_1017_S0269964814000217
Genre Feature
GroupedDBID -1D
-1F
-2P
-2V
-E.
-~6
-~N
-~X
.FH
09C
09D
09E
0E1
0R~
123
29O
3V.
4.4
5VS
6~7
6~8
74X
74Y
74Z
7~V
88I
8FE
8FG
8I0
8R4
8R5
9M5
AAAZR
AABES
AABWE
AACJH
AAGFV
AAKTX
AALKF
AAMNQ
AANRG
AAPYI
AARAB
AASVR
AATMM
AAUIS
AAUKB
ABBXD
ABBZL
ABITZ
ABJCF
ABJNI
ABKKG
ABMWE
ABQTM
ABQWD
ABROB
ABTCQ
ABTND
ABUWG
ABVFV
ABVKB
ABVZP
ABXAU
ABZCX
ABZUI
ACABY
ACAJB
ACBMC
ACDLN
ACETC
ACGFS
ACGOD
ACIMK
ACIWK
ACMRT
ACRPL
ACUIJ
ACYZP
ACZBM
ACZBN
ACZUX
ACZWT
ADCGK
ADDNB
ADFEC
ADKIL
ADNMO
ADOVH
ADOVT
ADTCA
ADVJH
AEBAK
AEBPU
AEHGV
AEMFK
AEMTW
AENCP
AENEX
AENGE
AEYYC
AFFNX
AFFUJ
AFKQG
AFKRA
AFKRZ
AFLOS
AFLVW
AFUTZ
AFZFC
AGABE
AGBYD
AGHGI
AGJUD
AGLWM
AHQXX
AHRGI
AIGNW
AIHIV
AIOIP
AISIE
AJ7
AJCYY
AJPFC
AJQAS
AKZCZ
ALMA_UNASSIGNED_HOLDINGS
ALVPG
ALWZO
ANFVQ
AOWSX
AQJOH
ARABE
ARAPS
ARZZG
ATUCA
AUXHV
AVDNQ
AYIQA
AZQEC
BBLKV
BCGOX
BENPR
BESQT
BGHMG
BGLVJ
BJBOZ
BLZWO
BMAJL
BPHCQ
BQFHP
C0O
CAG
CBIIA
CCPQU
CCQAD
CCUQV
CDIZJ
CFAFE
CFBFF
CGMFO
CGQII
CHEAL
CJCSC
COF
CS3
DC4
DOHLZ
DU5
DWQXO
EBS
ED0
EGQIC
EJD
GNUQQ
HCIFZ
HG-
HOVLH
HSS
HST
HZ~
I.5
I.6
I.7
I.9
IH6
IOEEP
IOO
IS6
I~P
J36
J38
J3A
J3B
JHPGK
JOSPZ
JPPIE
JQKCU
JRMXA
K6V
K7-
KAFGG
KCGVB
KFECR
L6V
L98
LHUNA
LW7
M-V
M0N
M2P
M7S
M7~
M8.
NIKVX
NMFBF
NQS
NZEOI
O9-
OYBOY
P2P
P62
PQQKQ
PROAC
PTHSS
PYCCK
Q2X
RAMDC
RCA
RIG
ROL
RR0
S6-
S6U
SAAAG
T9M
TN5
UCJ
UT1
WFFJZ
WQ3
WXS
WXU
WYP
ZDLDU
ZJOSE
ZMEZD
ZYDXJ
~A4
~V1
AAKNA
AAYXX
ABGDZ
ABHFL
ABXHF
ACEJA
ACOZI
AGQPQ
AGTDA
AKMAY
ANOYL
CITATION
IPYYG
PHGZM
PHGZT
7SC
7TB
7XB
8AL
8FD
8FK
FR3
JQ2
KR7
L7M
L~C
L~D
PKEHL
PQEST
PQGLB
PQUKI
PRINS
Q9U
ID FETCH-LOGICAL-c463t-6e07885f10deae3f2bbb6b75319eb4148c483948359d07e946035e0e68826a33
IEDL.DBID BENPR
ISSN 0269-9648
IngestDate Fri Jul 11 16:49:17 EDT 2025
Sat Aug 23 13:51:01 EDT 2025
Tue Jul 01 03:05:02 EDT 2025
Thu Apr 24 22:54:56 EDT 2025
Tue Jan 21 06:27:42 EST 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
License https://www.cambridge.org/core/terms
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c463t-6e07885f10deae3f2bbb6b75319eb4148c483948359d07e946035e0e68826a33
Notes SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
OpenAccessLink https://www.cambridge.org/core/services/aop-cambridge-core/content/view/CE9A226238311D80DD60E6A241C7F836/S0269964814000217a.pdf/div-class-title-multi-armed-bandits-under-general-depreciation-and-commitment-div.pdf
PQID 1643228298
PQPubID 37288
PageCount 26
ParticipantIDs proquest_miscellaneous_1660043955
proquest_journals_1643228298
crossref_primary_10_1017_S0269964814000217
crossref_citationtrail_10_1017_S0269964814000217
cambridge_journals_10_1017_S0269964814000217
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2015-01-01
PublicationDateYYYYMMDD 2015-01-01
PublicationDate_xml – month: 01
  year: 2015
  text: 2015-01-01
  day: 01
PublicationDecade 2010
PublicationPlace New York, USA
PublicationPlace_xml – name: New York, USA
– name: Cambridge
PublicationTitle Probability in the engineering and informational sciences
PublicationTitleAlternate Prob. Eng. Inf. Sci
PublicationYear 2015
Publisher Cambridge University Press
Publisher_xml – name: Cambridge University Press
References S0269964814000217_ref24
S0269964814000217_ref25
S0269964814000217_ref23
S0269964814000217_ref29
S0269964814000217_ref27
S0269964814000217_ref19
Burnetas (S0269964814000217_ref7) 2002; 17
Sonin (S0269964814000217_ref44) 2011; 83
Steinberg (S0269964814000217_ref45) 2014
Kaspi (S0269964814000217_ref28) 1998; 8
S0269964814000217_ref31
S0269964814000217_ref32
S0269964814000217_ref35
S0269964814000217_ref36
S0269964814000217_ref33
S0269964814000217_ref34
S0269964814000217_ref39
S0269964814000217_ref37
S0269964814000217_ref38
S0269964814000217_ref42
S0269964814000217_ref43
S0269964814000217_ref40
S0269964814000217_ref41
S0269964814000217_ref46
S0269964814000217_ref47
Gittins (S0269964814000217_ref22) 1989
Bertsekas (S0269964814000217_ref4) 2011; II
S0269964814000217_ref49
Katehakis (S0269964814000217_ref30) 1996; 6
Denardo (S0269964814000217_ref12) 2013
Honda (S0269964814000217_ref26) 2010
S0269964814000217_ref8
S0269964814000217_ref9
S0269964814000217_ref2
S0269964814000217_ref3
S0269964814000217_ref50
Gittins (S0269964814000217_ref20) 1974
S0269964814000217_ref1
S0269964814000217_ref6
S0269964814000217_ref10
S0269964814000217_ref51
S0269964814000217_ref5
S0269964814000217_ref52
S0269964814000217_ref13
Tewari (S0269964814000217_ref48) 2007
S0269964814000217_ref14
S0269964814000217_ref11
S0269964814000217_ref17
S0269964814000217_ref15
S0269964814000217_ref16
Gittins (S0269964814000217_ref21) 1979; 41
Frostig (S0269964814000217_ref18) 2014
References_xml – ident: S0269964814000217_ref11
  doi: 10.1007/978-1-4757-1776-1
– ident: S0269964814000217_ref2
  doi: 10.1109/ROBOT.2008.4543563
– volume: II
  volume-title: Dynamic programming and optimal control
  year: 2011
  ident: S0269964814000217_ref4
– ident: S0269964814000217_ref50
  doi: 10.1109/TAC.1985.1103989
– ident: S0269964814000217_ref38
  doi: 10.1287/moor.1050.0165
– volume-title: Cyrus Derman Memorial Volume I: Optimization under Uncertainty: Costs, Risks and Revenues
  year: 2013
  ident: S0269964814000217_ref12
– ident: S0269964814000217_ref10
  doi: 10.1017/S0001867800017456
– ident: S0269964814000217_ref24
  doi: 10.1287/opre.1070.0444
– ident: S0269964814000217_ref9
  doi: 10.1017/S0269964810000021
– start-page: 67
  volume-title: COLT
  year: 2010
  ident: S0269964814000217_ref26
– ident: S0269964814000217_ref34
– ident: S0269964814000217_ref46
  doi: 10.1109/MCOM.2012.6257528
– volume: 41
  start-page: 335
  year: 1979
  ident: S0269964814000217_ref21
  article-title: Bandit processes and dynamic allocation indices (with discussion)
  publication-title: Journal of Royal Statistics Society, Series B
  doi: 10.1111/j.2517-6161.1979.tb01068.x
– ident: S0269964814000217_ref5
  doi: 10.1561/9781601986276
– volume: 17
  start-page: 157
  year: 2002
  ident: S0269964814000217_ref7
  article-title: Asymptotic Bayes analysis for the finite horizon one armed bandit problem
  publication-title: Probability in the Engineering and Informational Science
– ident: S0269964814000217_ref33
  doi: 10.1287/moor.12.2.262
– ident: S0269964814000217_ref13
  doi: 10.1002/nav.3800070429
– ident: S0269964814000217_ref32
  doi: 10.1073/pnas.92.19.8584
– volume-title: Cyrus Derman Memorial Volume II: Optimization under Uncertainty: Costs, Risks and Revenues
  year: 2014
  ident: S0269964814000217_ref45
– ident: S0269964814000217_ref37
  doi: 10.1007/978-0-387-49819-5_6
– start-page: 1505
  volume-title: Advances in Neural Information Processing Systems
  year: 2007
  ident: S0269964814000217_ref48
– ident: S0269964814000217_ref42
  doi: 10.1090/S0002-9947-1952-0050209-9
– ident: S0269964814000217_ref52
  doi: 10.1017/S0021900200039176
– ident: S0269964814000217_ref1
  doi: 10.1017/S0269964811000015
– ident: S0269964814000217_ref6
  doi: 10.1287/moor.22.1.222
– volume: 8
  start-page: 1270
  year: 1998
  ident: S0269964814000217_ref28
  article-title: Multi-armed bandits in discrete and continuous time
  publication-title: The Annals of Applied Probability
  doi: 10.1214/aoap/1028903380
– ident: S0269964814000217_ref43
  doi: 10.1016/j.spl.2008.01.049
– volume-title: Multi-armed bandit allocation indices
  year: 1989
  ident: S0269964814000217_ref22
– ident: S0269964814000217_ref41
– ident: S0269964814000217_ref8
  doi: 10.1006/aama.1996.0007
– ident: S0269964814000217_ref27
  doi: 10.1007/BF02191765
– ident: S0269964814000217_ref14
  doi: 10.1073/pnas.90.4.1232
– ident: S0269964814000217_ref35
  doi: 10.1016/0196-8858(85)90002-8
– ident: S0269964814000217_ref16
  doi: 10.1109/ALLERTON.2010.5706896
– start-page: 241
  volume-title: Progress in statistics
  year: 1974
  ident: S0269964814000217_ref20
– volume-title: Cyrus Derman Memorial Volume II: Optimization under Uncertainty: Costs, Risks and Revenues
  year: 2014
  ident: S0269964814000217_ref18
– ident: S0269964814000217_ref25
  doi: 10.1080/01966324.1991.10737307
– ident: S0269964814000217_ref40
– ident: S0269964814000217_ref17
  doi: 10.5711/morj.14.2.41
– ident: S0269964814000217_ref29
  doi: 10.1214/lnms/1215540286
– ident: S0269964814000217_ref23
  doi: 10.1214/10-AAP705
– ident: S0269964814000217_ref19
  doi: 10.1002/9780470980033
– volume: 6
  start-page: 1024
  year: 1996
  ident: S0269964814000217_ref30
  article-title: Finite state multi-armed bandit problems: sensitive-discount, average-reward and average-overtaking optimality
  publication-title: The Annals of Applied Probability
  doi: 10.1214/aoap/1034968239
– ident: S0269964814000217_ref36
  doi: 10.1109/TSP.2010.2041600
– volume: 83
  start-page: 405
  year: 2011
  ident: S0269964814000217_ref44
  article-title: Optimal stopping of Markov chains and three abstract optimization problems
  publication-title: Stochastics
  doi: 10.1080/17442508.2010.514051
– ident: S0269964814000217_ref47
– ident: S0269964814000217_ref3
  doi: 10.1080/17442509008833627
– ident: S0269964814000217_ref39
  doi: 10.1109/ACSSC.2012.6489015
– ident: S0269964814000217_ref31
  doi: 10.1007/s10479-013-1430-4
– ident: S0269964814000217_ref51
  doi: 10.1214/aoap/1177005588
– ident: S0269964814000217_ref49
  doi: 10.1214/aoap/1177005207
– ident: S0269964814000217_ref15
  doi: 10.1109/9.222316
SSID ssj0007848
Score 2.095314
Snippet Generally, the multi-armed has been studied under the setting that at each time step over an infinite horizon a controller chooses to activate a single process...
SourceID proquest
crossref
cambridge
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 51
SubjectTerms Activation
Collection
Constants
Decisions
Depreciation
Discounts
Mathematical analysis
Mathematical models
Probability
Receiving
Stochasticity
Title MULTI-ARMED BANDITS UNDER GENERAL DEPRECIATION AND COMMITMENT
URI https://www.cambridge.org/core/product/identifier/S0269964814000217/type/journal_article
https://www.proquest.com/docview/1643228298
https://www.proquest.com/docview/1660043955
Volume 29
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LTwIxEJ6IXPTg24iv1MSTsXEfbbccjEEeghE0CAk3sn3syYAK_n-nS9lgTDjspY_NdjqdfvPYGYBrvPPDJNQxtSY1lGVJTKXRhmZaR9aqNIh0HuXbE-0hex7xkTe4zXxY5VIm5oLaTLWzkd8hrEfek1FVPnx-UVc1ynlXfQmNEpRRBEtUvsqPzd5bv5DFiczrZ6Gi4fJQMrn0a-ZJo7HRtaGKkSPz1ewKf2-pv0I6v3lae7DjISOpLfZ4Hzbs5AB2PXwk_nDODmB7JbfgIdx3hy-DDq31u80Geaz1Gp3BO8l_KSA-XI00mkj_eie3UhEcQeqvXRRlLr3_EQxazUG9TX2tBKqZiOdUWFyr5FkYGJvaOIuUUkIl7oRZxVDn0QyhED68aoLEVpkIYm4DKxBhizSOj2FzMp3YEyDGxIkKw0xFXDFmhIrCVPIAtzK1HLsqcFuQaewZfjZeBIsl439UrUCwpORY-7TjrvrFx7opN8WUz0XOjXWDz5fbs_I1BbNU4KroxoPjvCHpxE5_3Bjh3KBVzk_Xv-IMthAl8YXd5Rw2598_9gKRyFxdQkm2ni490_0CIgHRdA
linkProvider ProQuest
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Jj9MwFH6qhgNwYIYCorNhJLggLLLYTnIYoU4XGrogQUaaWxQvOaF2mHaE5kfNf-TZWdQRUm895OLYUfT8-e1-D-ADynw_8lVIjS40ZWUU0lgrTUulAmNk4QXKZfkuxOSKfb_m1x14aO7C2LTKhic6Rq1XyvrIv6Baj9iLgyT-evOH2q5RNrratNCoYDE193_RZFtfpEPc349BMB5lgwmtuwpQxUS4ocKgVIx56XvaFCYsAymlkJHFopEMrQPFUGnAhyfai0zChBdy4xmBuqgorP8TOf4TFoaJPVDx-FvL-KPYNetCq8YWvWRxE0R1Fapx0I6hPePMgO1SDo9F4mOJ4MTc-Ahe1Pop6VeAegkds-zCYa2rkpoTrLvwfKuQ4Su4mF_NspT2f85HQ3LZXwzT7Bdx9xdInRtHhiPc7EHqXGIEZ5DBjznyTdtL4DVk-yDhGzhYrpbmLRCtw0j6fikDLhnTQgZ-EXMPcVMYjq968LklU16frnVeZaZF-X9U7YHXUDJXdY1z22rj964ln9olN1WBj12TT5vt2fqbFpk9eN--xlNqQy_F0qzu7BxhY64J58e7P_EOnk6y-SyfpYvpCTxD9YxXDp9TONjc3pkzVIE28twBj0C-Z6D_A5mRCcU
linkToPdf http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3NT9swFH9CRZrYYQO2iY4vT2IXhEU-bCc9oKk0rQjQgliRuEXxR05T29GiiT-N_27PiRMVIfXGIRfHjqLnn9-33wM4QpnvR74KqdG5pqyIQhprpWmhVGCMzL1AlVm-I3Fxzy4f-MMavNR3YWxaZc0TS0atp8r6yE9RrUfsxUEnPi1cWsRtMvg1-0ttBykbaa3baVQQuTLP_9B8m5-lCe71zyAY9Me9C-o6DFDFRLigwqCEjHnhe9rkJiwCKaWQkcWlkQwtBcVQgcCHd7QXmQ4TXsiNZwTqpSK3vlDk_usRGkVeC9bP-6Pbu0YMRHHZugttHFsCk8V1SLWsV42Ddgytm9IoWC7s8FpAvpYPpdAbbMInp62SbgWvLVgzk2347DRX4vjCfBs-LpU1_AJnw_vrcUq7d8N-Qs67oyQd_yblbQbiMuVI0set76Wlg4zgDNK7GSIXtZ0FvsL4PYj4DVqT6cTsANE6jKTvFzLgkjEtZODnMfcQRbnh-KoNJw2ZMnfW5lmVpxZlb6jaBq-mZKZcxXPbeOPPqiXHzZJZVe5j1eS9enuW_qbBaRt-NK_xzNpATD4x0yc7R9gIbIfz76s_cQgfEOTZdTq62oUN1NV45f3Zg9bi8cnsoz60kAcOeQSyd8b6fzWmD1c
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=MULTI-ARMED+BANDITS+UNDER+GENERAL+DEPRECIATION+AND+COMMITMENT&rft.jtitle=Probability+in+the+engineering+and+informational+sciences&rft.au=Cowan%2C+Wesley&rft.au=Katehakis%2C+Michael+N.&rft.date=2015-01-01&rft.issn=0269-9648&rft.eissn=1469-8951&rft.volume=29&rft.issue=1&rft.spage=51&rft.epage=76&rft_id=info:doi/10.1017%2FS0269964814000217&rft.externalDBID=n%2Fa&rft.externalDocID=10_1017_S0269964814000217
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0269-9648&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0269-9648&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0269-9648&client=summon