{"id":"https://openalex.org/W4404351610","doi":"https://doi.org/10.1145/3677052.3698670","title":"Autoregressive DRL with Learned Intrinsic Rewards for Portfolio Optimisation","display_name":"Autoregressive DRL with Learned Intrinsic Rewards for Portfolio Optimisation","publication_year":2024,"publication_date":"2024-11-14","ids":{"openalex":"https://openalex.org/W4404351610","doi":"https://doi.org/10.1145/3677052.3698670"},"language":"en","primary_location":{"id":"doi:10.1145/3677052.3698670","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3677052.3698670","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3677052.3698670","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM International Conference on AI in Finance","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3677052.3698670","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064859089","display_name":"Magdalene Hui Qi Lim","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Magdalene Hui Qi Lim","raw_affiliation_strings":["School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0009-0002-3859-3246","affiliations":[{"raw_affiliation_string":"School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026189293","display_name":"Nixie S. Lesmana","orcid":"https://orcid.org/0009-0000-3705-3382"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Nixie S Lesmana","raw_affiliation_strings":["School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore and Department of Physics, Faculty of Science, National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0000-3705-3382","affiliations":[{"raw_affiliation_string":"School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore and Department of Physics, Faculty of Science, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I172675005","https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089225379","display_name":"Chi Seng Pun","orcid":"https://orcid.org/0000-0002-7478-6961"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chi Seng Pun","raw_affiliation_strings":["School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7478-6961","affiliations":[{"raw_affiliation_string":"School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5064859089"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.3155,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59832245,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"353","last_page":"360"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9879999756813049,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9833999872207642,"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/autoregressive-model","display_name":"Autoregressive model","score":0.6859991550445557},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5940191745758057},{"id":"https://openalex.org/keywords/portfolio","display_name":"Portfolio","score":0.5696972012519836},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.3766475319862366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32099485397338867},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.18062013387680054},{"id":"https://openalex.org/keywords/financial-economics","display_name":"Financial economics","score":0.15838956832885742}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6859991550445557},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5940191745758057},{"id":"https://openalex.org/C2780821815","wikidata":"https://www.wikidata.org/wiki/Q5340806","display_name":"Portfolio","level":2,"score":0.5696972012519836},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3766475319862366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32099485397338867},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.18062013387680054},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.15838956832885742}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3677052.3698670","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3677052.3698670","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3677052.3698670","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM International Conference on AI in Finance","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3677052.3698670","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3677052.3698670","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3677052.3698670","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM International Conference on AI in Finance","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404351610.pdf"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W174135753","https://openalex.org/W1977051850","https://openalex.org/W2032730137","https://openalex.org/W2040956360","https://openalex.org/W2099233100","https://openalex.org/W2106052345","https://openalex.org/W2145339207","https://openalex.org/W2769883686","https://openalex.org/W2795413297","https://openalex.org/W2911495555","https://openalex.org/W2963523627","https://openalex.org/W4232593778","https://openalex.org/W4248510338"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2171218219","https://openalex.org/W1972271943","https://openalex.org/W2150410159","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W2156628102"],"abstract_inverted_index":{"The":[0],"recent":[1],"success":[2],"of":[3,20,35,41,91,103],"deep":[4],"reinforcement":[5],"learning":[6,10],"(DRL)":[7],"in":[8,39,58],"sequential":[9],"tasks":[11],"involving":[12],"high-dimensional":[13],"state":[14],"spaces":[15],"has":[16],"sparked":[17],"the":[18,21,32,50,92,120],"interest":[19],"finance":[22],"research":[23,29],"community.":[24],"In":[25,44],"portfolio":[26],"optimization,":[27],"mainstream":[28],"often":[30],"overlooks":[31],"important":[33],"question":[34],"optimal":[36],"reward":[37,56],"design,":[38],"favor":[40],"algorithm":[42],"design.":[43],"this":[45],"work,":[46],"we":[47],"focus":[48],"on":[49],"former":[51],"question,":[52],"exploring":[53],"different":[54,127],"external":[55],"functions":[57],"combination":[59],"with":[60],"reward-transforming":[61],"internal":[62],"systems.":[63],"We":[64,95],"put":[65],"forth":[66],"a":[67],"novel":[68],"strategy":[69,98],"that":[70,113,123],"combines":[71],"two":[72],"DRL":[73],"frameworks:":[74],"learned":[75,87,114],"intrinsic":[76,83,116],"rewards":[77,84,117],"and":[78,111],"autoregressive":[79],"architectures,":[80],"allowing":[81],"individual":[82,115],"to":[85,119],"be":[86],"for":[88],"each":[89,97],"dimension":[90],"action":[93],"space.":[94],"back-test":[96],"using":[99],"real":[100],"financial":[101],"data":[102],"30":[104],"Dow":[105],"Jones":[106],"stocks":[107],"over":[108],"multiple":[109],"years,":[110],"demonstrate":[112],"lead":[118],"best":[121],"performance":[122],"is":[124],"robust":[125],"across":[126],"training":[128],"objectives.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}