{"id":"https://openalex.org/W4415303762","doi":"https://doi.org/10.1007/s10957-025-02858-3","title":"A Hybrid Deep Reinforcement Learning Method for Insurance Portfolio Management","display_name":"A Hybrid Deep Reinforcement Learning Method for Insurance Portfolio Management","publication_year":2025,"publication_date":"2025-10-17","ids":{"openalex":"https://openalex.org/W4415303762","doi":"https://doi.org/10.1007/s10957-025-02858-3"},"language":"en","primary_location":{"id":"doi:10.1007/s10957-025-02858-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10957-025-02858-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10957-025-02858-3.pdf","source":{"id":"https://openalex.org/S52430896","display_name":"Journal of Optimization Theory and Applications","issn_l":"0022-3239","issn":["0022-3239","1573-2878"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Optimization Theory and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10957-025-02858-3.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073773211","display_name":"Xiang Cheng","orcid":"https://orcid.org/0000-0002-0426-8384"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang Cheng","raw_affiliation_strings":["London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"London, UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071607165","display_name":"Zhuo Jin","orcid":"https://orcid.org/0000-0002-9488-2993"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Zhuo Jin","raw_affiliation_strings":["Department of Actuarial Studies and Business Analytics, Macquarie University, Sydney, NSW 2109, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9488-2993","affiliations":[{"raw_affiliation_string":"Department of Actuarial Studies and Business Analytics, Macquarie University, Sydney, NSW 2109, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082000840","display_name":"Hailiang Yang","orcid":"https://orcid.org/0000-0002-8869-7783"},"institutions":[{"id":"https://openalex.org/I69356397","display_name":"Xi\u2019an Jiaotong-Liverpool University","ror":"https://ror.org/03zmrmn05","country_code":"CN","type":"education","lineage":["https://openalex.org/I69356397"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hailiang Yang","raw_affiliation_strings":["Department of Financial and Actuarial Mathematics, School of Mathematics & Physics, Xi\u2019an Jiaotong-Liverpool University, 215123, Suzhou, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Financial and Actuarial Mathematics, School of Mathematics & Physics, Xi\u2019an Jiaotong-Liverpool University, 215123, Suzhou, P.R. China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008853967","display_name":"George Yin","orcid":"https://orcid.org/0000-0002-2951-0704"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Yin","raw_affiliation_strings":["Department of Mathematics, University of Connecticut, 06269-1009, Storrs, CT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, University of Connecticut, 06269-1009, Storrs, CT, USA","institution_ids":["https://openalex.org/I140172145"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5071607165"],"corresponding_institution_ids":["https://openalex.org/I99043593"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48180177,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"208","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12011","display_name":"Insurance, Mortality, Demography, Risk Management","score":0.9621999859809875,"subfield":{"id":"https://openalex.org/subfields/3317","display_name":"Demography"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12011","display_name":"Insurance, Mortality, Demography, Risk Management","score":0.9621999859809875,"subfield":{"id":"https://openalex.org/subfields/3317","display_name":"Demography"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12394","display_name":"Insurance and Financial Risk Management","score":0.9538999795913696,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9341999888420105,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8149999976158142},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6406999826431274},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5580999851226807},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5340999960899353},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.5098999738693237},{"id":"https://openalex.org/keywords/portfolio","display_name":"Portfolio","score":0.4417000114917755},{"id":"https://openalex.org/keywords/theory-of-computation","display_name":"Theory of computation","score":0.43230000138282776},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.41819998621940613},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4147000014781952}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8149999976158142},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6413000226020813},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6406999826431274},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5580999851226807},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5340999960899353},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.5098999738693237},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49140000343322754},{"id":"https://openalex.org/C2780821815","wikidata":"https://www.wikidata.org/wiki/Q5340806","display_name":"Portfolio","level":2,"score":0.4417000114917755},{"id":"https://openalex.org/C24858836","wikidata":"https://www.wikidata.org/wiki/Q844718","display_name":"Theory of computation","level":2,"score":0.43230000138282776},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.41819998621940613},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4147000014781952},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.396699994802475},{"id":"https://openalex.org/C137631369","wikidata":"https://www.wikidata.org/wiki/Q7617831","display_name":"Stochastic programming","level":2,"score":0.3919000029563904},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3772999942302704},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37630000710487366},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3407999873161316},{"id":"https://openalex.org/C127491075","wikidata":"https://www.wikidata.org/wiki/Q7617825","display_name":"Stochastic modelling","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.329800009727478},{"id":"https://openalex.org/C158535547","wikidata":"https://www.wikidata.org/wiki/Q5165437","display_name":"Continuous-time stochastic process","level":3,"score":0.32910001277923584},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3127000033855438},{"id":"https://openalex.org/C62469222","wikidata":"https://www.wikidata.org/wiki/Q17092103","display_name":"Hybrid algorithm (constraint satisfaction)","level":5,"score":0.3068000078201294},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.30649998784065247},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C202655437","wikidata":"https://www.wikidata.org/wiki/Q7231728","display_name":"Portfolio optimization","level":3,"score":0.29330000281333923},{"id":"https://openalex.org/C74510933","wikidata":"https://www.wikidata.org/wiki/Q1936145","display_name":"Project portfolio management","level":3,"score":0.2856999933719635},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C86582703","wikidata":"https://www.wikidata.org/wiki/Q7617824","display_name":"Stochastic neural network","level":4,"score":0.25929999351501465}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10957-025-02858-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10957-025-02858-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10957-025-02858-3.pdf","source":{"id":"https://openalex.org/S52430896","display_name":"Journal of Optimization Theory and Applications","issn_l":"0022-3239","issn":["0022-3239","1573-2878"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Optimization Theory and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10957-025-02858-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10957-025-02858-3","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10957-025-02858-3.pdf","source":{"id":"https://openalex.org/S52430896","display_name":"Journal of Optimization Theory and Applications","issn_l":"0022-3239","issn":["0022-3239","1573-2878"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Optimization Theory and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4196572834","display_name":null,"funder_award_id":"12471452","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7050721155","display_name":null,"funder_award_id":"DMS-2404508","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7085477924","display_name":null,"funder_award_id":"2204240","funder_id":"https://openalex.org/F4320332172","funder_display_name":"Directorate for Mathematical and Physical Sciences"},{"id":"https://openalex.org/G7821388300","display_name":"MPS/DMS-EPSRC: Stabilization Using Feedback Controls, Numerical Methods for Stochastic Systems, and Systems with Mean-Field Interactions","funder_award_id":"2404508","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320591","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320332172","display_name":"Directorate for Mathematical and Physical Sciences","ror":"https://ror.org/029b7h395"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415303762.pdf","grobid_xml":"https://content.openalex.org/works/W4415303762.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1499021337","https://openalex.org/W1972792800","https://openalex.org/W2004220372","https://openalex.org/W2052773335","https://openalex.org/W2085096176","https://openalex.org/W2092911205","https://openalex.org/W2128636346","https://openalex.org/W2134698488","https://openalex.org/W2145339207","https://openalex.org/W2169015875","https://openalex.org/W2563902504","https://openalex.org/W2567212694","https://openalex.org/W2625995436","https://openalex.org/W2782891976","https://openalex.org/W2796693555","https://openalex.org/W2889026921","https://openalex.org/W2903857590","https://openalex.org/W3016378723","https://openalex.org/W3021614052","https://openalex.org/W3037286161","https://openalex.org/W3080840864","https://openalex.org/W3081478208","https://openalex.org/W3099661895","https://openalex.org/W3110347183","https://openalex.org/W3183560208","https://openalex.org/W3208215078","https://openalex.org/W4200081317","https://openalex.org/W4214597064","https://openalex.org/W4214717370","https://openalex.org/W4231581167","https://openalex.org/W4292366002","https://openalex.org/W4311549306","https://openalex.org/W4386221420"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"This":[1],"paper":[2],"develops":[3],"a":[4,35,71],"hybrid":[5,99],"deep":[6,79],"reinforcement":[7,40,80],"learning":[8,81,112],"approach":[9],"to":[10,123,134,152],"manage":[11],"an":[12,44,51],"insurance":[13,45],"portfolio":[14,46],"for":[15],"diffusion":[16],"models.":[17],"To":[18,62],"address":[19],"the":[20,25,64,84,88,111,118,136,144,154,157],"model":[21],"uncertainty,":[22],"we":[23,69],"adopt":[24],"recently":[26],"developed":[27],"modelling":[28],"of":[29,87,116,138,143,156],"exploration":[30],"and":[31,55,75,105],"exploitation":[32],"strategies":[33],"in":[34,49,110],"continuous-time":[36],"decision-making":[37],"process":[38],"with":[39],"learning.":[41],"We":[42],"consider":[43],"management":[47],"problem":[48],"which":[50],"entropy-regularized":[52],"reward":[53],"function":[54],"corresponding":[56],"relaxed":[57,66],"stochastic":[58,67,76,90,106,130],"controls":[59,91],"are":[60,108,150],"formulated.":[61],"obtain":[63],"optimal":[65,89],"controls,":[68],"develop":[70],"Markov":[72,102,119],"chain":[73,103,120],"approximation":[74,104,107,121,131],"approximation-based":[77],"iterative":[78],"algorithm":[82,145],"where":[83],"probability":[85],"distribution":[86],"is":[92,127,132,146],"approximated":[93],"by":[94],"neural":[95,139],"networks.":[96,140],"In":[97],"our":[98],"algorithm,":[100],"both":[101],"adopted":[109,133],"processes.":[113],"The":[114],"idea":[115],"using":[117],"method":[122],"find":[124],"initial":[125],"guesses":[126],"proposed.":[128],"A":[129],"estimate":[135],"parameters":[137],"Convergence":[141],"analysis":[142],"presented.":[147],"Numerical":[148],"examples":[149],"provided":[151],"illustrate":[153],"performance":[155],"algorithm.":[158]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-18T00:00:00"}