{"id":"https://openalex.org/W7118343003","doi":"https://doi.org/10.1080/00207179.2025.2610334","title":"Optimal investment and reinsurance in an entropy-regularised multidimensional reinforcement learning model","display_name":"Optimal investment and reinsurance in an entropy-regularised multidimensional reinforcement learning model","publication_year":2026,"publication_date":"2026-01-07","ids":{"openalex":"https://openalex.org/W7118343003","doi":"https://doi.org/10.1080/00207179.2025.2610334"},"language":"en","primary_location":{"id":"doi:10.1080/00207179.2025.2610334","is_oa":false,"landing_page_url":"https://doi.org/10.1080/00207179.2025.2610334","pdf_url":null,"source":{"id":"https://openalex.org/S88061139","display_name":"International Journal of Control","issn_l":"0020-7179","issn":["0020-7179","1366-5820"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Control","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101733441","display_name":"Yifan Wu","orcid":"https://orcid.org/0009-0009-9735-9987"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Wu","raw_affiliation_strings":["East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030194216","display_name":"Jiaqin Wei","orcid":"https://orcid.org/0000-0002-2534-6046"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiaqin Wei","raw_affiliation_strings":["East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024718990","display_name":"Lin Xu","orcid":"https://orcid.org/0000-0001-6952-824X"},"institutions":[{"id":"https://openalex.org/I4472751","display_name":"Anhui Normal University","ror":"https://ror.org/05fsfvw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I4472751"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Xu","raw_affiliation_strings":["Anhui Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui Normal University","institution_ids":["https://openalex.org/I4472751"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5030194216"],"corresponding_institution_ids":["https://openalex.org/I66867065"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04084047,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"99","issue":"6","first_page":"1750","last_page":"1768"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.289900004863739,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.289900004863739,"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"}},{"id":"https://openalex.org/T11413","display_name":"Risk and Portfolio Optimization","score":0.09719999879598618,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11270","display_name":"Complex Systems and Time Series Analysis","score":0.059300001710653305,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinsurance","display_name":"Reinsurance","score":0.7329999804496765},{"id":"https://openalex.org/keywords/investment","display_name":"Investment (military)","score":0.5809000134468079},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5070000290870667},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3370000123977661},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.3203999996185303}],"concepts":[{"id":"https://openalex.org/C166970017","wikidata":"https://www.wikidata.org/wiki/Q476118","display_name":"Reinsurance","level":2,"score":0.7329999804496765},{"id":"https://openalex.org/C27548731","wikidata":"https://www.wikidata.org/wiki/Q88272","display_name":"Investment (military)","level":3,"score":0.5809000134468079},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5070000290870667},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4713999927043915},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.45840001106262207},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.37070000171661377},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.33000001311302185},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C103144560","wikidata":"https://www.wikidata.org/wiki/Q2670999","display_name":"Investment strategy","level":3,"score":0.3163999915122986},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C162118730","wikidata":"https://www.wikidata.org/wiki/Q1128453","display_name":"Actuarial science","level":1,"score":0.2874999940395355},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2831999957561493},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.2791999876499176},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/00207179.2025.2610334","is_oa":false,"landing_page_url":"https://doi.org/10.1080/00207179.2025.2610334","pdf_url":null,"source":{"id":"https://openalex.org/S88061139","display_name":"International Journal of Control","issn_l":"0020-7179","issn":["0020-7179","1366-5820"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4183264374732971,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G6629413664","display_name":null,"funder_award_id":"25YJAZH200","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"},{"id":"https://openalex.org/G8426779462","display_name":null,"funder_award_id":"2408085MA019","funder_id":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"id":"https://openalex.org/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W756180390","https://openalex.org/W1585575029","https://openalex.org/W1958272982","https://openalex.org/W1965012323","https://openalex.org/W1967453651","https://openalex.org/W1978721202","https://openalex.org/W2011797827","https://openalex.org/W2068441370","https://openalex.org/W2074414121","https://openalex.org/W2081377551","https://openalex.org/W2091149102","https://openalex.org/W2094884995","https://openalex.org/W2118573305","https://openalex.org/W2121156749","https://openalex.org/W2130711276","https://openalex.org/W2171169470","https://openalex.org/W2765302304","https://openalex.org/W3007135855","https://openalex.org/W3106017595","https://openalex.org/W3110347183","https://openalex.org/W3173247913","https://openalex.org/W3199075411","https://openalex.org/W4214597064","https://openalex.org/W4234311681","https://openalex.org/W4235413109","https://openalex.org/W4244547439","https://openalex.org/W4309029392","https://openalex.org/W4386696665","https://openalex.org/W4386750089"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"studies":[2],"optimal":[3,50,100,113],"investment":[4],"and":[5,24,36,47,56,89],"reinsurance":[6],"strategies":[7],"for":[8],"insurers":[9],"facing":[10],"parameter":[11],"uncertainty,":[12],"addressing":[13],"three":[14],"objectives:":[15],"maximising":[16,25],"expected":[17,26],"terminal":[18,27],"utility,":[19],"minimising":[20],"ultimate":[21],"bankruptcy":[22,58],"probability":[23],"utility":[28,38,54],"under":[29],"constraints.":[30],"When":[31],"no":[32],"constraints":[33],"are":[34,63],"imposed":[35],"the":[37,43,48,57,74,80,83,90,94,99,104,107,112,117,120],"is":[39,124],"exponential,":[40],"we":[41,66],"derive":[42],"approximate":[44],"analytical":[45],"solution":[46,92],"associated":[49],"strategy.":[51],"For":[52],"general":[53],"functions":[55],"minimisation":[59],"problem,":[60],"explicit":[61],"solutions":[62],"unavailable,":[64],"so":[65],"propose":[67],"a":[68],"policy":[69],"improvement":[70],"algorithm":[71,78],"that":[72],"approximates":[73],"value":[75,87,108],"function.":[76],"The":[77],"exploits":[79],"identity":[81],"between":[82],"entropy-regularised":[84],"reinforcement":[85],"learning":[86],"function":[88,109],"viscosity":[91],"of":[93,106,119],"exploratory":[95],"Hamilton-Jacobi-Bellman":[96],"equation,":[97],"expressing":[98],"feedback":[101],"strategy":[102],"through":[103,126],"derivative":[105],"to":[110],"obtain":[111],"distributional":[114],"control.":[115],"Finally,":[116],"effectiveness":[118],"proposed":[121],"numerical":[122,127],"methods":[123],"validated":[125],"examples.":[128]},"counts_by_year":[],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2026-01-08T00:00:00"}