{"id":"https://openalex.org/W4416195089","doi":"https://doi.org/10.1145/3768292.3770340","title":"Regret-Optimized Portfolio Enhancement through Deep Reinforcement Learning and Future Looking Rewards","display_name":"Regret-Optimized Portfolio Enhancement through Deep Reinforcement Learning and Future Looking Rewards","publication_year":2025,"publication_date":"2025-11-14","ids":{"openalex":"https://openalex.org/W4416195089","doi":"https://doi.org/10.1145/3768292.3770340"},"language":"en","primary_location":{"id":"doi:10.1145/3768292.3770340","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3768292.3770340","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM International Conference on AI in Finance","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://infoscience.epfl.ch/handle/20.500.14299/255886","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092685338","display_name":"Daniil Karzanov","orcid":"https://orcid.org/0000-0003-1767-9649"},"institutions":[{"id":"https://openalex.org/I97565354","display_name":"University of Lausanne","ror":"https://ror.org/019whta54","country_code":"CH","type":"education","lineage":["https://openalex.org/I97565354"]},{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Daniil Karzanov","raw_affiliation_strings":["AXA Group Operations, Lausanne, Switzerland and EPFL, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"AXA Group Operations, Lausanne, Switzerland and EPFL, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864","https://openalex.org/I97565354"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116176095","display_name":"Rub\u00e9n Garz\u00f3n","orcid":"https://orcid.org/0000-0002-5695-2495"},"institutions":[{"id":"https://openalex.org/I4210164457","display_name":"Anaxomics (Spain)","ror":"https://ror.org/05jnac203","country_code":"ES","type":"company","lineage":["https://openalex.org/I4210164457"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Rub\u00e9n Garz\u00f3n","raw_affiliation_strings":["AXA Group Operations, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"AXA Group Operations, Barcelona, Spain","institution_ids":["https://openalex.org/I4210164457"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099623228","display_name":"Mikhail Terekhov","orcid":"https://orcid.org/0009-0005-7403-3731"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mikhail Terekhov","raw_affiliation_strings":["CLAIRE, EPFL, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"CLAIRE, EPFL, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041145688","display_name":"\u00c7a\u01e7lar G\u00fcl\u00e7ehre","orcid":"https://orcid.org/0009-0003-4124-1687"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Caglar Gulcehre","raw_affiliation_strings":["CLAIRE, EPFL, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"CLAIRE, EPFL, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089358533","display_name":"Thomas Raffinot","orcid":"https://orcid.org/0000-0003-2338-3596"},"institutions":[{"id":"https://openalex.org/I4210100579","display_name":"AXA (France)","ror":"https://ror.org/013z4qk72","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210100579"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thomas Raffinot","raw_affiliation_strings":["AXA Investment Managers, Paris, France"],"affiliations":[{"raw_affiliation_string":"AXA Investment Managers, Paris, France","institution_ids":["https://openalex.org/I4210100579"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065404842","display_name":"Marcin Detyniecki","orcid":"https://orcid.org/0000-0001-5669-4871"},"institutions":[{"id":"https://openalex.org/I4210100579","display_name":"AXA (France)","ror":"https://ror.org/013z4qk72","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210100579"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Marcin Detyniecki","raw_affiliation_strings":["AXA Group Operations, Paris, France"],"affiliations":[{"raw_affiliation_string":"AXA Group Operations, Paris, France","institution_ids":["https://openalex.org/I4210100579"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5092685338"],"corresponding_institution_ids":["https://openalex.org/I5124864","https://openalex.org/I97565354"],"apc_list":null,"apc_paid":null,"fwci":2.3361,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91723991,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"890","last_page":"897"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.39800000190734863,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.39800000190734863,"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/T11413","display_name":"Risk and Portfolio Optimization","score":0.1875,"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/T11326","display_name":"Stock Market Forecasting Methods","score":0.15449999272823334,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7430999875068665},{"id":"https://openalex.org/keywords/sharpe-ratio","display_name":"Sharpe ratio","score":0.6836000084877014},{"id":"https://openalex.org/keywords/portfolio","display_name":"Portfolio","score":0.6597999930381775},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5038999915122986},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4964999854564667},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.49470001459121704},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.48030000925064087},{"id":"https://openalex.org/keywords/transaction-cost","display_name":"Transaction cost","score":0.4259999990463257}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7430999875068665},{"id":"https://openalex.org/C139938925","wikidata":"https://www.wikidata.org/wiki/Q1501898","display_name":"Sharpe ratio","level":3,"score":0.6836000084877014},{"id":"https://openalex.org/C2780821815","wikidata":"https://www.wikidata.org/wiki/Q5340806","display_name":"Portfolio","level":2,"score":0.6597999930381775},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6424000263214111},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5038999915122986},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4964999854564667},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.49470001459121704},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.48030000925064087},{"id":"https://openalex.org/C98965940","wikidata":"https://www.wikidata.org/wiki/Q877496","display_name":"Transaction cost","level":2,"score":0.4259999990463257},{"id":"https://openalex.org/C51485801","wikidata":"https://www.wikidata.org/wiki/Q16966861","display_name":"Efficient frontier","level":3,"score":0.4172999858856201},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38420000672340393},{"id":"https://openalex.org/C202655437","wikidata":"https://www.wikidata.org/wiki/Q7231728","display_name":"Portfolio optimization","level":3,"score":0.3693000078201294},{"id":"https://openalex.org/C74510933","wikidata":"https://www.wikidata.org/wiki/Q1936145","display_name":"Project portfolio management","level":3,"score":0.3635999858379364},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.32829999923706055},{"id":"https://openalex.org/C73938075","wikidata":"https://www.wikidata.org/wiki/Q2858767","display_name":"Application portfolio management","level":4,"score":0.3244999945163727},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3059000074863434},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.27649998664855957},{"id":"https://openalex.org/C103144560","wikidata":"https://www.wikidata.org/wiki/Q2670999","display_name":"Investment strategy","level":3,"score":0.2761000096797943},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3768292.3770340","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3768292.3770340","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM International Conference on AI in Finance","raw_type":"proceedings-article"},{"id":"pmh:oai:infoscience.epfl.ch:20.500.14299/255886","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/255886","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:20.500.14299/255886","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/255886","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2108855171","https://openalex.org/W2145339207","https://openalex.org/W2158366624","https://openalex.org/W2257979135","https://openalex.org/W2296073425","https://openalex.org/W2625101268","https://openalex.org/W2809515733","https://openalex.org/W2943230607","https://openalex.org/W2946661738","https://openalex.org/W2998274290","https://openalex.org/W3086839219","https://openalex.org/W3087349278","https://openalex.org/W3121513733","https://openalex.org/W3123675609","https://openalex.org/W3134096209","https://openalex.org/W3136027957","https://openalex.org/W3161671626","https://openalex.org/W3186499994","https://openalex.org/W3209380964","https://openalex.org/W4211177483","https://openalex.org/W4220700195","https://openalex.org/W4226205224","https://openalex.org/W4232474910","https://openalex.org/W4281705590","https://openalex.org/W4282838956","https://openalex.org/W4362722548","https://openalex.org/W4366548317","https://openalex.org/W4387372714","https://openalex.org/W4394580000"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"a":[3,77,83,93],"novel":[4],"agent-based":[5],"approach":[6,26],"for":[7],"enhancing":[8],"existing":[9,126],"portfolio":[10,23,127],"strategies":[11],"using":[12],"Proximal":[13],"Policy":[14],"Optimization":[15],"(PPO).":[16],"Rather":[17],"than":[18],"focusing":[19],"solely":[20],"on":[21,108],"traditional":[22,49],"construction,":[24],"our":[25],"aims":[27],"to":[28,46,98,138],"improve":[29],"an":[30],"already":[31],"high-performing":[32],"strategy":[33,128],"through":[34,92,129],"dynamic":[35],"rebalancing":[36,131],"driven":[37],"by":[38,56],"PPO":[39],"and":[40,71,87,114],"Oracle":[41],"agents.":[42],"Our":[43,117],"target":[44],"is":[45],"enhance":[47],"the":[48,58,65,100,122,125],"60/40":[50],"benchmark":[51],"(60%":[52],"stocks,":[53],"40%":[54],"bonds)":[55],"employing":[57],"Regret-based":[59],"Sharpe":[60],"reward":[61,85],"function.":[62],"To":[63],"address":[64],"impact":[66],"of":[67,102,124],"transaction":[68,78],"fee":[69],"frictions":[70],"prevent":[72],"signal":[73],"loss,":[74],"we":[75],"develop":[76],"cost":[79],"scheduler.":[80],"We":[81,106],"introduce":[82],"future-looking":[84],"function":[86],"employ":[88],"synthetic":[89],"data":[90],"training":[91],"circular":[94],"block":[95],"bootstrap":[96],"method":[97,118],"facilitate":[99],"learning":[101],"generalizable":[103],"allocation":[104],"strategies.":[105],"focus":[107],"two":[109],"key":[110],"evaluation":[111],"measures:":[112],"return":[113],"maximum":[115],"drawdown.":[116],"not":[119],"only":[120],"enhances":[121],"performance":[123],"strategic":[130],"but":[132],"also":[133],"demonstrates":[134],"strong":[135],"results":[136],"compared":[137],"other":[139],"RL":[140],"baselines.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-11-14T00:00:00"}