Premium control with reinforcement learning

We consider a premium control problem in discrete time, formulated in terms of a Markov decision process. In a simplified setting, the optimal premium rule can be derived with dynamic programming methods. However, these classical methods are not feasible in a more realistic setting due to the dimens...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:ASTIN Bulletin : The Journal of the IAA Ročník 53; číslo 2; s. 233 - 257
Hlavní autoři: Palmborg, Lina, Lindskog, Filip
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York, USA Cambridge University Press 01.05.2023
Témata:
Actuarial science
Approximation
Control algorithms
Deep learning
Dividends
Dynamical systems
Hedging
Insurance premiums
Markov analysis
Markov decision process
matematisk statistik
Mathematical Statistics
Mutual insurance companies
Premium control
Present value
Probability
reinforcement learning
Stochastic control theory
Stochastic models
Teaching methods
Markov decision process
Premium control
C60
G22
reinforcement learning
ISSN:0515-0361, 1783-1350, 1783-1350
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract We consider a premium control problem in discrete time, formulated in terms of a Markov decision process. In a simplified setting, the optimal premium rule can be derived with dynamic programming methods. However, these classical methods are not feasible in a more realistic setting due to the dimension of the state space and lack of explicit expressions for transition probabilities. We explore reinforcement learning techniques, using function approximation, to solve the premium control problem for realistic stochastic models. We illustrate the appropriateness of the approximate optimal premium rule compared with the true optimal premium rule in a simplified setting and further demonstrate that the approximate optimal premium rule outperforms benchmark rules in more realistic settings where classical approaches fail.
AbstractList We consider a premium control problem in discrete time, formulated in terms of a Markov decision process. In a simplified setting, the optimal premium rule can be derived with dynamic programming methods. However, these classical methods are not feasible in a more realistic setting due to the dimension of the state space and lack of explicit expressions for transition probabilities. We explore reinforcement learning techniques, using function approximation, to solve the premium control problem for realistic stochastic models. We illustrate the appropriateness of the approximate optimal premium rule compared with the true optimal premium rule in a simplified setting and further demonstrate that the approximate optimal premium rule outperforms benchmark rules in more realistic settings where classical approaches fail.
Author Lindskog, Filip
Palmborg, Lina
Author_xml – sequence: 1
  givenname: Lina
  orcidid: 0000-0001-6338-3692
  surname: Palmborg
  fullname: Palmborg, Lina
  email: lina.palmborg@math.su.se
  organization: Department of Mathematics Stockholm University Stockholm 106 91, Sweden
– sequence: 2
  givenname: Filip
  surname: Lindskog
  fullname: Lindskog, Filip
  organization: Department of Mathematics Stockholm University Stockholm 106 91, Sweden
BackLink https://urn.kb.se/resolve?urn=urn:nbn:se:su:diva-217014$$DView record from Swedish Publication Index (Stockholms universitet)
BookMark eNpt0EtLAzEUhuEgCrbVlX-g4LJOzUlmmpllqVco6ELdhlzO1JROUpMZiv_eKS26cXU2Dx-Hd0hOffBIyBXQKVAQtyrpKaOMT4GfkAGIkmfAC3pKBrSAIqN8BudkmNKaUg4lYwMyeY3YuK4Zm-DbGDbjnWs_xxGdr0M02KBvxxtU0Tu_uiBntdokvDzeEXl_uH9bPGXLl8fnxXyZGV6WbVbWimlEY5TNNVaWcywExVmFxgJYY43OjVYlr7CohLCCqYpaW-eKVZhbzUfk5rCbdrjttNxG16j4LYNy8s59zGWIK5k6yUBQyHt-feDbGL46TK1chy76_kPJSmA5FXkJvZoclIkhpYj17yxQuY8n-3hyH08C73V21KrR0dkV_o3-538A7Ulzug
Cites_doi 10.1007/BF00992701
10.1609/aaai.v25i1.7903
10.1080/03461238.1994.10413927
10.1109/ICASSP.2012.6288330
10.1023/A:1007678930559
10.1080/03461238.1983.10408686
10.2143/AST.23.2.2005092
10.1080/14697688.2019.1571683
10.1007/BF00992696
10.1145/1390156.1390240
10.1109/9.580874
10.1016/j.engappai.2019.01.010
10.1287/mnsc.2013.1788
ContentType Journal Article
Copyright The Author(s), 2023. Published by Cambridge University Press on behalf of The International Actuarial Association
The Author(s), 2023. Published by Cambridge University Press on behalf of The International Actuarial Association. This work is licensed under the Creative Commons Attribution License This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted re-use, distribution and reproduction, provided the original article is properly cited. (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml – notice: The Author(s), 2023. Published by Cambridge University Press on behalf of The International Actuarial Association
– notice: The Author(s), 2023. Published by Cambridge University Press on behalf of The International Actuarial Association. This work is licensed under the Creative Commons Attribution License This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted re-use, distribution and reproduction, provided the original article is properly cited. (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID IKXGN
AAYXX
CITATION
3V.
7X1
7XB
8A9
8FK
ABUWG
AFKRA
ANIOZ
BENPR
BEZIV
CCPQU
DWQXO
FRAZJ
FRNLG
K60
K6~
PHGZM
PHGZT
PKEHL
PQBIZ
PQBZA
PQEST
PQQKQ
PQUKI
Q9U
ABAVF
ADTPV
AOWAS
D8T
DG7
ZZAVC
DOI 10.1017/asb.2023.13
DatabaseName Cambridge University Press Gold Open Access Journals
CrossRef
ProQuest Central (Corporate)
Accounting & Tax Database
ProQuest Central (purchase pre-March 2016)
Accounting & Tax Database (Alumni Edition)
ProQuest Central (Alumni) (purchase pre-March 2016)
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
Accounting, Tax & Banking Collection
ProQuest Central
Business Premium Collection
ProQuest One
ProQuest Central
Accounting, Tax & Banking Collection (Alumni)
Business Premium Collection (Alumni)
ProQuest Business Collection (Alumni Edition)
ProQuest Business Collection
ProQuest Central Premium
ProQuest One Academic
ProQuest One Academic Middle East (New)
ProQuest One Business
ProQuest One Business (Alumni)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central Basic
SWEPUB Stockholms universitet full text
SwePub
SwePub Articles
SWEPUB Freely available online
SWEPUB Stockholms universitet
SwePub Articles full text
DatabaseTitle CrossRef
Business Premium Collection
ProQuest Business Collection (Alumni Edition)
ProQuest One Business
ProQuest Central Basic
ProQuest One Academic Middle East (New)
ProQuest One Academic Eastern Edition
ProQuest Central (Alumni Edition)
ProQuest One Community College
ProQuest Business Collection
Accounting & Tax
ProQuest Central
Accounting, Tax & Banking Collection
ProQuest One Academic UKI Edition
ProQuest Central Korea
ProQuest One Business (Alumni)
Accounting, Tax & Banking Collection (Alumni)
Accounting & Tax (Alumni Edition)
ProQuest One Academic
ProQuest Central (New)
ProQuest Central (Alumni)
Business Premium Collection (Alumni)
ProQuest One Academic (New)
DatabaseTitleList CrossRef
Business Premium Collection
Database_xml – sequence: 1
  dbid: IKXGN
  name: Cambridge University Press Wholly Gold Open Access Journals
  url: http://journals.cambridge.org/action/login
  sourceTypes: Publisher
– sequence: 2
  dbid: BENPR
  name: ProQuest Central - New (Subscription)
  url: https://www.proquest.com/central
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Business
EISSN 1783-1350
EndPage 257
ExternalDocumentID oai_DiVA_org_su_217014
10_1017_asb_2023_13
GroupedDBID 09C
09D
09E
0E1
0R~
23N
4.4
5GY
5VS
8I0
AAAZR
AABES
AABWE
AACJH
AADNG
AAFWJ
AAGFV
AAKTX
AALKF
AANRG
AAOIO
AAPYI
AARAB
AASVR
AAUKB
ABBXD
ABBZL
ABGDZ
ABJNI
ABJWI
ABKKG
ABMWE
ABMYL
ABQTM
ABROB
ABTND
ABUWG
ABXAU
ABYPY
ABZCX
ACABY
ACBMC
ACCHT
ACETC
ACFCP
ACGFS
ACHQT
ACIMK
ACQFJ
ACREK
ACUIJ
ACUYZ
ACYZP
ACZBM
ACZBN
ACZUX
ACZWT
ADBZK
ADDNB
ADFEC
ADGEJ
ADKIL
ADOCW
ADOVH
ADTCA
ADVJH
AEBAK
AEBPU
AEFOJ
AEHGV
AENCP
AENEX
AENGE
AEYYC
AFFUJ
AFKQG
AFKRA
AFKRZ
AFLOS
AFLVW
AGABE
AGHGI
AGJUD
AGLWM
AGOOT
AHQXX
AHRGI
AIGNW
AIHIV
AIOIP
AISIE
AJCYY
AJPFC
AJQAS
AKZCZ
ALMA_UNASSIGNED_HOLDINGS
ALWZO
ANFVQ
ANIOZ
AOWSX
AQJOH
ARZZG
ATUCA
AUXHV
AVDNQ
AWRMI
AWSUU
AYIQA
BBLKV
BBQHK
BCGOX
BENPR
BESQT
BEZIV
BGHMG
BJBOZ
BLZWO
BMAJL
C0O
CBIIA
CCPQU
CCQAD
CCUQV
CFAFE
CFBFF
CFLAC
CGMFO
CGQII
CHEAL
CJCSC
DOHLZ
DWQXO
EBS
ED0
EGQIC
EJD
FRNLG
GDOGT
HG-
HOVLH
HZ~
I.5
I.6
I.7
IH6
IKXGN
IOEEP
IOO
IS6
I~P
JHPGK
JOSPZ
JPPIE
JQKCU
JRMXA
KAFGG
KCGVB
KFECR
LHUNA
LW7
M-V
M7~
MS~
NIKVX
NZEOI
O9-
OK1
PQBIZ
RAMDC
RCA
ROL
RR0
RWP
S6-
S6U
SAAAG
SJN
T9M
TR2
UT1
WFFJZ
ZJOSE
ZMEZD
ZYDXJ
~A4
AAXMD
AAYXX
ABVKB
ABVZP
ABXHF
ACDLN
AFFHD
AFZFC
AGTDA
AKMAY
AMVHM
CITATION
PHGZM
PHGZT
PQBZA
3V.
7X1
7XB
8A9
8FK
K60
K6~
PKEHL
PQEST
PQQKQ
PQUKI
Q9U
ABAVF
ADTPV
AOWAS
D8T
DG7
ZZAVC
ID FETCH-LOGICAL-c388t-8fa2beeccad4be9d33e570e69ecd11dcdcb4cba839e5977d72a90ddf4a29e4db3
IEDL.DBID BENPR
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000969164700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0515-0361
1783-1350
IngestDate Tue Nov 04 16:28:07 EST 2025
Mon Jun 30 13:42:43 EDT 2025
Sat Nov 29 01:43:22 EST 2025
Wed Mar 13 05:50:33 EDT 2024
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 2
Keywords Markov decision process
Premium control
C60
G22
reinforcement learning
Language English
License This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted re-use, distribution and reproduction, provided the original article is properly cited.
https://creativecommons.org/licenses/by/4.0
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c388t-8fa2beeccad4be9d33e570e69ecd11dcdcb4cba839e5977d72a90ddf4a29e4db3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0001-6338-3692
OpenAccessLink https://www.cambridge.org/core/product/identifier/S0515036123000132/type/journal_article
PQID 2812407481
PQPubID 5514772
PageCount 25
ParticipantIDs swepub_primary_oai_DiVA_org_su_217014
proquest_journals_2812407481
crossref_primary_10_1017_asb_2023_13
cambridge_journals_10_1017_asb_2023_13
PublicationCentury 2000
PublicationDate 20230501
PublicationDateYYYYMMDD 2023-05-01
PublicationDate_xml – month: 05
  year: 2023
  text: 20230501
  day: 01
PublicationDecade 2020
PublicationPlace New York, USA
PublicationPlace_xml – name: New York, USA
– name: Cambridge
PublicationTitle ASTIN Bulletin : The Journal of the IAA
PublicationTitleAlternate ASTIN Bull
PublicationYear 2023
Publisher Cambridge University Press
Publisher_xml – name: Cambridge University Press
References 1994; 1994
2019; 19
1992; 8
2019; 80
1993; 23
2000; 38
2021; 99
1983; 1983
1997; 42
2014; 60
1957
2012; 42
De Finetti (S0515036123000132_ref6) 1957
Martin-Löf (S0515036123000132_ref16) 1983; 1983
Bertsekas (S0515036123000132_ref1) 1996
S0515036123000132_ref20
Puterman (S0515036123000132_ref21) 2005
S0515036123000132_ref22
Miranda (S0515036123000132_ref19) 2012; 42
S0515036123000132_ref2
Carbonneau (S0515036123000132_ref3) 2021; 99
Martin-Löf (S0515036123000132_ref17) 1994; 1994
S0515036123000132_ref4
S0515036123000132_ref7
S0515036123000132_ref24
S0515036123000132_ref8
S0515036123000132_ref9
S0515036123000132_ref26
S0515036123000132_ref28
S0515036123000132_ref29
Mack (S0515036123000132_ref14) 1993; 23
Schmidli (S0515036123000132_ref23) 2008
S0515036123000132_ref30
S0515036123000132_ref31
S0515036123000132_ref10
S0515036123000132_ref11
Sutton (S0515036123000132_ref27) 2018
S0515036123000132_ref12
S0515036123000132_ref13
S0515036123000132_ref15
Dayan (S0515036123000132_ref5) 1992; 8
S0515036123000132_ref18
Sutton (S0515036123000132_ref25) 1992
References_xml – volume: 80
  start-page: 8
  year: 2019
  end-page: 19
  article-title: Reinforcement learning for pricing strategy optimization in the insurance industry
  publication-title: Engineering Applications of Artificial Intelligence
– volume: 1983
  start-page: 1
  issue: 1
  year: 1983
  end-page: 27
  article-title: Premium control in an insurance system, an approach using linear control theory
  publication-title: Scandinavian Actuarial Journal
– volume: 99
  start-page: 327
  year: 2021
  end-page: 340
  article-title: Deep hedging of long-term financial derivatives
  publication-title: Insurance: Mathematics and Economics
– volume: 8
  start-page: 341
  issue: 3–4
  year: 1992
  end-page: 362
  article-title: The convergence of TD(
  publication-title: Machine Learning
– volume: 42
  start-page: 674
  issue: 5
  year: 1997
  end-page: 690
  article-title: An analysis of temporal-difference learning with function approximation
  publication-title: IEEE Transactions on Automatic Control
– volume: 19
  start-page: 1271
  issue: 8
  year: 2019
  end-page: 1291
  article-title: Deep hedging
  publication-title: Quantitative Finance
– volume: 8
  start-page: 229
  year: 1992
  end-page: 256
  article-title: Simple statistical gradient-following algorithms for connectionist reinforcement learning
  publication-title: Machine Learning
– volume: 38
  start-page: 287
  issue: 3
  year: 2000
  end-page: 308
  article-title: Convergence results for single-step on-policy reinforcement-learning algorithms
  publication-title: Machine Learning
– volume: 1994
  start-page: 1
  issue: 1
  year: 1994
  end-page: 25
  article-title: Lectures on the use of control theory in insurance
  publication-title: Scandinavian Actuarial Journal
– volume: 42
  start-page: 59
  issue: 1
  year: 2012
  end-page: 76
  article-title: Double chain ladder
  publication-title: ASTIN Bulletin: The Journal of the IAA
– start-page: 433
  year: 1957
  end-page: 443
  article-title: Su un’ impostazione alternativa della teoria collettivadel rischio
  publication-title: Transactions of the XVth International Congress of Actuaries
– volume: 60
  start-page: 770
  issue: 3
  year: 2014
  article-title: Simultaneously learning and optimizing using controlled variance pricing
  publication-title: Management Science
– volume: 23
  start-page: 213
  issue: 2
  year: 1993
  end-page: 225
  article-title: Distribution-free calculation of the standard error of chain ladder reserve estimates
  publication-title: ASTIN Bulletin: The Journal of the IAA
– ident: S0515036123000132_ref10
– volume-title: Stochastic Control in Insurance
  year: 2008
  ident: S0515036123000132_ref23
– volume: 8
  start-page: 341
  year: 1992
  ident: S0515036123000132_ref5
  article-title: The convergence of TD(
  publication-title: Machine Learning
  doi: 10.1007/BF00992701
– ident: S0515036123000132_ref12
  doi: 10.1609/aaai.v25i1.7903
– volume: 1994
  start-page: 1
  year: 1994
  ident: S0515036123000132_ref17
  article-title: Lectures on the use of control theory in insurance
  publication-title: Scandinavian Actuarial Journal
  doi: 10.1080/03461238.1994.10413927
– ident: S0515036123000132_ref15
  doi: 10.1109/ICASSP.2012.6288330
– ident: S0515036123000132_ref24
  doi: 10.1023/A:1007678930559
– start-page: 171
  year: 1992
  ident: S0515036123000132_ref25
– volume: 99
  start-page: 327
  year: 2021
  ident: S0515036123000132_ref3
  article-title: Deep hedging of long-term financial derivatives
  publication-title: Insurance: Mathematics and Economics
– ident: S0515036123000132_ref22
– ident: S0515036123000132_ref26
– volume-title: Neuro-dynamic Programming
  year: 1996
  ident: S0515036123000132_ref1
– volume: 1983
  start-page: 1
  year: 1983
  ident: S0515036123000132_ref16
  article-title: Premium control in an insurance system, an approach using linear control theory
  publication-title: Scandinavian Actuarial Journal
  doi: 10.1080/03461238.1983.10408686
– ident: S0515036123000132_ref28
– ident: S0515036123000132_ref9
– volume: 23
  start-page: 213
  year: 1993
  ident: S0515036123000132_ref14
  article-title: Distribution-free calculation of the standard error of chain ladder reserve estimates
  publication-title: ASTIN Bulletin: The Journal of the IAA
  doi: 10.2143/AST.23.2.2005092
– volume-title: Markov Decision Processes: Discrete Stochastic Dynamic Programming
  year: 2005
  ident: S0515036123000132_ref21
– ident: S0515036123000132_ref20
– ident: S0515036123000132_ref11
– ident: S0515036123000132_ref2
  doi: 10.1080/14697688.2019.1571683
– volume: 42
  start-page: 59
  year: 2012
  ident: S0515036123000132_ref19
  article-title: Double chain ladder
  publication-title: ASTIN Bulletin: The Journal of the IAA
– start-page: 433
  year: 1957
  ident: S0515036123000132_ref6
  article-title: Su un’ impostazione alternativa della teoria collettivadel rischio
  publication-title: Transactions of the XVth International Congress of Actuaries
– volume-title: Reinforcement Learning: An Introduction
  year: 2018
  ident: S0515036123000132_ref27
– ident: S0515036123000132_ref30
– ident: S0515036123000132_ref31
  doi: 10.1007/BF00992696
– ident: S0515036123000132_ref4
– ident: S0515036123000132_ref18
  doi: 10.1145/1390156.1390240
– ident: S0515036123000132_ref29
  doi: 10.1109/9.580874
– ident: S0515036123000132_ref13
  doi: 10.1016/j.engappai.2019.01.010
– ident: S0515036123000132_ref7
  doi: 10.1287/mnsc.2013.1788
– ident: S0515036123000132_ref8
SSID ssj0031822
Score 2.2740796
Snippet We consider a premium control problem in discrete time, formulated in terms of a Markov decision process. In a simplified setting, the optimal premium rule can...
SourceID swepub
proquest
crossref
cambridge
SourceType Open Access Repository
Aggregation Database
Index Database
Publisher
StartPage 233
SubjectTerms Actuarial science
Approximation
Control algorithms
Deep learning
Dividends
Dynamical systems
Hedging
Insurance premiums
Markov analysis
Markov decision process
matematisk statistik
Mathematical Statistics
Mutual insurance companies
Premium control
Present value
Probability
reinforcement learning
Stochastic control theory
Stochastic models
Teaching methods
SummonAdditionalLinks – databaseName: Cambridge University Press Gold Open Access Journals
  dbid: IKXGN
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV07T8MwELZKixALb0ShoAyFzbR5J2MFFBCoQgKqbJZfQRlaqqTl93OXOG2RGFjYkii6xP4S3-fz-TtCun4QcvB6gkoexdQLRUCjSMQ0hVOYtHAhy4Db-DkcjaIkiV8aJKn3wmBa5VLjoFzJL-ujzSr5016mqhwanfdesToJjL8w9JZExulh0LJnIGCm4zdICxiMA79s6_EpuR_VozR8ytUKAxihaMXs3UM5aV6Ia6wqfo01D1aKCz891xodXZcYLd3ScPf_GrRHdgxVtQbVlX3S0NMDslVnyh8STN-YZIuJZdLdLYzpWrkutVhlGXa0TFGKjyPyPrx7u3mgpvYClW4UzWmUckdoxFd5QsfKdbUf9nUQa6lsW0klhScFB3qlUcFOhQ6P-0qlHndi7SnhHpPm9HOqT4gVcOWDp8QFUJgLapjfSan6Mky58Liv7Ta5WnYQM60tWJV9FjIAgyEYzHbbpFsDwGaVFsfvt3VqcFbmHCQyQJcieNxlBdjSBips32bjAQN0WLFgDmrUe6d_fa0zso1HVRZkhzTn-UKfk035Nc-K_MJ8d98Jier1
  priority: 102
  providerName: Cambridge University Press
Title Premium control with reinforcement learning
URI https://www.cambridge.org/core/product/identifier/S0515036123000132/type/journal_article
https://www.proquest.com/docview/2812407481
https://urn.kb.se/resolve?urn=urn:nbn:se:su:diva-217014
Volume 53
WOSCitedRecordID wos000969164700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVPQU
  databaseName: Accounting, Tax & Banking Collection
  customDbUrl:
  eissn: 1783-1350
  dateEnd: 20241209
  omitProxy: false
  ssIdentifier: ssj0031822
  issn: 1783-1350
  databaseCode: ANIOZ
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/accountingtaxbanking
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central - New (Subscription)
  customDbUrl:
  eissn: 1783-1350
  dateEnd: 20241209
  omitProxy: false
  ssIdentifier: ssj0031822
  issn: 1783-1350
  databaseCode: BENPR
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LT8JAEJ4oGOPFtxFF0gN6W6QPaHsyqKBEU4lRQrxs9gXhwEMK_n532i1gYrx4apo002Z2Ot_szOw3AOVa3Wca9TgRLAiJ5_M6CQIekr6-1ZsWxkWScOs--1EU9HphxyTcYtNWmfnExFHLicAc-bWDSKTxLrBvpp8Ep0ZhddWM0NiEPDKVaTvP3zajzmvmi7XBpnUEjdpE-2rbnNBD0mgW8wrODq_gZIMVr8JPfFoLOteJRBPwae3997P3YdeEnVYjtZMD2FDjQ9jOut6PAFsxRsPFyDKt6xbmZ62ZSnhVRZJCtMyAicExvLeab3ePxMxRIMINgjkJ-szhCtdKelyF0nVVza-qeqiEtG0ppOCe4EyHSgrZ6KTvsLAqZd9jTqg8yd0TyI0nY3UKVp3JmkY9LGbqfZ3SezUhZFX4fcY9VlN2Aa6WmqTmb4hp2knmU61yiiqntluAcqZmOk15NX5_rJipdSVupdMCXKbLspSBbNn3w26DTmYDGi-og3zz3tnfYs5hB9-X9jEWITefLdQFbImv-TCelSDfiNovHyVjW_rafuo9RN_2NNmf
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1LT8JAEJ4gGPXi24ii9iDeVukD2h6MISKRiOgBifGy7gvCgYcUNP4pf6M7fQAmxhsHj02a6abfzM5jZ78BOC2WXKa9HieCeT5xXF4insd90taPOmlhXIQFt1bdbTS852f_MQVfyV0YbKtM9sRwo5YDgTXyCws9kfZ3nnk1fCM4NQpPV5MRGpFa3KnPD52yBZe1isY3b1nVm-b1LYmnChBhe96YeG1mcYUrlw5XvrRtVXQLquQrIU1TCim4IzjTgYNCbjbpWswvSNl2mOUrR3Jby12CjGPrzCgNmXKj9vCS7P3aQKJzCx0lEO0bzPhGIJJUs4Cf46zyc5ykMONx-OkP54LceeLS0NlVN_7bb9qE9TisNsqRHWxBSvW3YSXp6t8BbDXpdSc9I27NN7D-bIxUyBsrwhKpEQ_Q6OzC00KWugfp_qCv9sEoMVnUXh0Pa3XeqnQuKoQsCLfNuMOKyszC2RQ5Glt7QKNOOZdqiClCTE07C6cJrHQY8Yb8_lougXEmboZhFvKRGkxlIBt4pdsq08GoQ4MJtZBP3zn4W8wJrN427-u0XmvcHcIafjvq2cxBejyaqCNYFu_jbjA6jvXZgNdF68Y3s1I5cQ
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3JTgJBEK0gGOLF3YjrHMBbC7PAzByMISKRaJCDEuOl7W0IBxYZ0Phrfp1ds4AmxhsHj5NMapaq7ldbvwIoVmsu06jHiWCeTxyX14jncZ8E-lIHLYyLKOHWvXPbbe_pye9k4DM9C4NtlemeGG3UciQwR162EIk03nlmOUjaIjqN5uX4leAEKay0puM0YhO5VR_vOnwLL1oNreuSZTWvH65uSDJhgAjb86bEC5jFFX6FdLjypW2rqltRNV8JaZpSSMEdwZl2IhTytEnXYn5FysBhlq8cyW0tdwVyyAjjZCFXb7fun1Mc0IslrmFoj4FonDCT04FIWM1Cfo5zy89xqsKC0-EnNn5zeL-TmEbA19z4z79sE9YTd9uox-tjCzJquA35tNt_B7AFZdCfDYykZd_AvLQxURGfrIhSp0YyWKO3C49LedU9yA5HQ7UPRo3JqkZ7LOLqeFbpGFUIWRFuwLjDqsoswNlcizTZBUIad9C5VKuborqpaRegmKqYjmM-kd9vO0pVuhC30GcBSrFJzGUgS3ij363T0aRHwxm1kGffOfhbzCnktUHQu1b79hDW8NFxK-cRZKeTmTqGVfE27YeTk8S0DXhZtml8AYX7QjY
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=Premium+control+with+reinforcement+learning&rft.jtitle=ASTIN+Bulletin+%3A+The+Journal+of+the+IAA&rft.au=Palmborg%2C+Lina&rft.au=Lindskog%2C+Filip&rft.date=2023-05-01&rft.pub=Cambridge+University+Press&rft.issn=0515-0361&rft.eissn=1783-1350&rft.volume=53&rft.issue=2&rft.spage=233&rft.epage=257&rft_id=info:doi/10.1017%2Fasb.2023.13&rft.externalDBID=HAS_PDF_LINK
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0515-0361&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0515-0361&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0515-0361&client=summon