{"id":"https://openalex.org/W4410866785","doi":"https://doi.org/10.1007/s40747-025-01884-y","title":"A novel multi-agent dynamic portfolio optimization learning system based on hierarchical deep reinforcement learning","display_name":"A novel multi-agent dynamic portfolio optimization learning system based on hierarchical deep reinforcement learning","publication_year":2025,"publication_date":"2025-05-29","ids":{"openalex":"https://openalex.org/W4410866785","doi":"https://doi.org/10.1007/s40747-025-01884-y"},"language":"en","primary_location":{"id":"doi:10.1007/s40747-025-01884-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-01884-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-01884-y.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-01884-y.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014042408","display_name":"Ruoyu Sun","orcid":"https://orcid.org/0009-0002-6052-0051"},"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":true,"raw_author_name":"Ruoyu Sun","raw_affiliation_strings":["School of AI and Advanced Computing, XJTLU Entrepreneur College (Taicang), Xi\u2019an Jiaotong-Liverpool University, Suzhou, 215123, Jiangsu, China","School of AI and Advanced Computing, XJTLU Entrepreneur College (Taicang), Xi'an Jiaotong-Liverpool University, Suzhou, 215123, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"School of AI and Advanced Computing, XJTLU Entrepreneur College (Taicang), Xi\u2019an Jiaotong-Liverpool University, Suzhou, 215123, Jiangsu, China","institution_ids":["https://openalex.org/I69356397"]},{"raw_affiliation_string":"School of AI and Advanced Computing, XJTLU Entrepreneur College (Taicang), Xi'an Jiaotong-Liverpool University, Suzhou, 215123, Jiangsu, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100819453","display_name":"Yue Xi","orcid":null},"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":"Yue Xi","raw_affiliation_strings":["Department of Educational Studies, School of Academy of Future Education, Xi\u2019an Jiaotong-Liverpool University, Suzhou, 215123, Jiangsu, China","Department of Educational Studies, School of Academy of Future Education, Xi'an Jiaotong-Liverpool University, Suzhou, 215123, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"Department of Educational Studies, School of Academy of Future Education, Xi\u2019an Jiaotong-Liverpool University, Suzhou, 215123, Jiangsu, China","institution_ids":["https://openalex.org/I69356397"]},{"raw_affiliation_string":"Department of Educational Studies, School of Academy of Future Education, Xi'an Jiaotong-Liverpool University, Suzhou, 215123, Jiangsu, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034081162","display_name":"Angelos Stefanidis","orcid":"https://orcid.org/0000-0002-4703-8765"},"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":"Angelos Stefanidis","raw_affiliation_strings":["School of AI and Advanced Computing, XJTLU Entrepreneur College (Taicang), Xi\u2019an Jiaotong-Liverpool University, Suzhou, 215123, Jiangsu, China","School of AI and Advanced Computing, XJTLU Entrepreneur College (Taicang), Xi'an Jiaotong-Liverpool University, Suzhou, 215123, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"School of AI and Advanced Computing, XJTLU Entrepreneur College (Taicang), Xi\u2019an Jiaotong-Liverpool University, Suzhou, 215123, Jiangsu, China","institution_ids":["https://openalex.org/I69356397"]},{"raw_affiliation_string":"School of AI and Advanced Computing, XJTLU Entrepreneur College (Taicang), Xi'an Jiaotong-Liverpool University, Suzhou, 215123, Jiangsu, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011243810","display_name":"Zhengyong Jiang","orcid":"https://orcid.org/0000-0001-8873-4073"},"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":"Zhengyong Jiang","raw_affiliation_strings":["School of AI and Advanced Computing, XJTLU Entrepreneur College (Taicang), Xi\u2019an Jiaotong-Liverpool University, Suzhou, 215123, Jiangsu, China","School of AI and Advanced Computing, XJTLU Entrepreneur College (Taicang), Xi'an Jiaotong-Liverpool University, Suzhou, 215123, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"School of AI and Advanced Computing, XJTLU Entrepreneur College (Taicang), Xi\u2019an Jiaotong-Liverpool University, Suzhou, 215123, Jiangsu, China","institution_ids":["https://openalex.org/I69356397"]},{"raw_affiliation_string":"School of AI and Advanced Computing, XJTLU Entrepreneur College (Taicang), Xi'an Jiaotong-Liverpool University, Suzhou, 215123, Jiangsu, China","institution_ids":["https://openalex.org/I69356397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085156744","display_name":"Jionglong Su","orcid":"https://orcid.org/0000-0001-5360-6493"},"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":"Jionglong Su","raw_affiliation_strings":["School of AI and Advanced Computing, XJTLU Entrepreneur College (Taicang), Xi\u2019an Jiaotong-Liverpool University, Suzhou, 215123, Jiangsu, China","School of AI and Advanced Computing, XJTLU Entrepreneur College (Taicang), Xi'an Jiaotong-Liverpool University, Suzhou, 215123, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"School of AI and Advanced Computing, XJTLU Entrepreneur College (Taicang), Xi\u2019an Jiaotong-Liverpool University, Suzhou, 215123, Jiangsu, China","institution_ids":["https://openalex.org/I69356397"]},{"raw_affiliation_string":"School of AI and Advanced Computing, XJTLU Entrepreneur College (Taicang), Xi'an Jiaotong-Liverpool University, Suzhou, 215123, Jiangsu, China","institution_ids":["https://openalex.org/I69356397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5014042408"],"corresponding_institution_ids":["https://openalex.org/I69356397"],"apc_list":{"value":1320,"currency":"GBP","value_usd":1619},"apc_paid":{"value":1320,"currency":"GBP","value_usd":1619},"fwci":26.1237,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.99427825,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"11","issue":"7","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9805999994277954,"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":0.9805999994277954,"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/T11052","display_name":"Energy Load and Power Forecasting","score":0.9523000121116638,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T11326","display_name":"Stock Market Forecasting Methods","score":0.9020000100135803,"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":0.858111560344696},{"id":"https://openalex.org/keywords/computational-intelligence","display_name":"Computational intelligence","score":0.6502124071121216},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5965419411659241},{"id":"https://openalex.org/keywords/portfolio","display_name":"Portfolio","score":0.5700735449790955},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5495667457580566},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5262638330459595},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3746953010559082},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19597336649894714},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.08876186609268188},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.08770263195037842}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.858111560344696},{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.6502124071121216},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5965419411659241},{"id":"https://openalex.org/C2780821815","wikidata":"https://www.wikidata.org/wiki/Q5340806","display_name":"Portfolio","level":2,"score":0.5700735449790955},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5495667457580566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5262638330459595},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3746953010559082},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19597336649894714},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.08876186609268188},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.08770263195037842},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s40747-025-01884-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-01884-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-01884-y.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:ec6be2ea4b9d468aa9fb76a5290d2c14","is_oa":true,"landing_page_url":"https://doaj.org/article/ec6be2ea4b9d468aa9fb76a5290d2c14","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complex & Intelligent Systems, Vol 11, Iss 7, Pp 1-41 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s40747-025-01884-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-01884-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-01884-y.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Complex & Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410866785.pdf","grobid_xml":"https://content.openalex.org/works/W4410866785.grobid-xml"},"referenced_works_count":87,"referenced_works":["https://openalex.org/W1484084033","https://openalex.org/W1582504559","https://openalex.org/W1780163389","https://openalex.org/W1964964840","https://openalex.org/W1976658031","https://openalex.org/W2014583745","https://openalex.org/W2015856032","https://openalex.org/W2029480990","https://openalex.org/W2034489173","https://openalex.org/W2034806191","https://openalex.org/W2064240901","https://openalex.org/W2068643490","https://openalex.org/W2106052345","https://openalex.org/W2112261373","https://openalex.org/W2120499560","https://openalex.org/W2140917889","https://openalex.org/W2158076035","https://openalex.org/W2163382420","https://openalex.org/W2173248099","https://openalex.org/W2626389465","https://openalex.org/W2736601468","https://openalex.org/W2793864397","https://openalex.org/W2903325752","https://openalex.org/W2912823139","https://openalex.org/W2963065757","https://openalex.org/W2965672544","https://openalex.org/W2983579676","https://openalex.org/W2985815252","https://openalex.org/W2998034590","https://openalex.org/W3024896014","https://openalex.org/W3031339344","https://openalex.org/W3041202696","https://openalex.org/W3083887855","https://openalex.org/W3084759552","https://openalex.org/W3087349278","https://openalex.org/W3114374801","https://openalex.org/W3121919567","https://openalex.org/W3121933628","https://openalex.org/W3122305330","https://openalex.org/W3125503432","https://openalex.org/W3129190273","https://openalex.org/W3155398915","https://openalex.org/W3159521583","https://openalex.org/W3175835345","https://openalex.org/W3177318507","https://openalex.org/W3212614390","https://openalex.org/W4212996499","https://openalex.org/W4221140674","https://openalex.org/W4225140907","https://openalex.org/W4232474910","https://openalex.org/W4234620788","https://openalex.org/W4237883889","https://openalex.org/W4241584625","https://openalex.org/W4249441547","https://openalex.org/W4281906850","https://openalex.org/W4283804236","https://openalex.org/W4289333266","https://openalex.org/W4293377385","https://openalex.org/W4297751865","https://openalex.org/W4309760235","https://openalex.org/W4310416691","https://openalex.org/W4311432121","https://openalex.org/W4312055796","https://openalex.org/W4313908847","https://openalex.org/W4316035578","https://openalex.org/W4362722548","https://openalex.org/W4367058992","https://openalex.org/W4377102997","https://openalex.org/W4382203079","https://openalex.org/W4383737760","https://openalex.org/W4385989154","https://openalex.org/W4387431647","https://openalex.org/W4387514094","https://openalex.org/W4389219081","https://openalex.org/W4390685501","https://openalex.org/W4391360925","https://openalex.org/W4392499083","https://openalex.org/W4393204168","https://openalex.org/W4394566165","https://openalex.org/W4396856184","https://openalex.org/W4399602477","https://openalex.org/W4399610293","https://openalex.org/W4401487120","https://openalex.org/W4404505670","https://openalex.org/W4406185642","https://openalex.org/W4406633991","https://openalex.org/W6776764508"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1,164],"learning":[2,116,157,165,181,204,231,276,294,305,354,368,392],"(DRL)":[3],"has":[4],"been":[5],"extensively":[6],"used":[7,54],"to":[8,75,139,358],"address":[9,149],"portfolio":[10,35,136,184,237],"optimization":[11,137],"problems.":[12],"DRL":[13,39,55,63,82,112,129,302],"agents":[14,113,130,176],"acquire":[15],"knowledge":[16,29],"and":[17,46,69,104,223,260,323,337,362,375,410],"make":[18],"decisions":[19],"through":[20],"unsupervised":[21],"interactions":[22],"with":[23,195,212,220],"their":[24],"environment":[25,281,422],"without":[26],"requiring":[27],"explicit":[28],"of":[30,34,43,107,228,238,257,274,306,332,335,373,390,405],"the":[31,41,51,62,66,78,81,96,105,122,128,134,141,145,161,175,196,203,210,217,229,242,251,254,258,268,279,289,301,312,320,330,333,339,343,352,371,383,388,416,420,429],"joint":[32],"dynamics":[33],"assets.":[36],"Among":[37],"these":[38,150],"algorithms,":[40],"combination":[42],"actor-critic":[44,67],"algorithms":[45,369],"deep":[47,70,163],"function":[48,71],"approximators":[49,72],"is":[50,86,233,282,356],"most":[52],"widely":[53],"algorithm.":[56],"Here,":[57],"we":[58,152,286,316],"find":[59,317],"that":[60,90,192,288,318,415],"training":[61,123,146,252,269,280,313,325,340,421],"agent":[64,191,198,322],"using":[65,235],"algorithm":[68,326],"may":[73],"lead":[74],"scenarios":[76],"where":[77],"improvement":[79],"in":[80,101,121,144,169,216,246,267,278,296,311,342,370,382,403,419,428],"agent's":[83],"risk-adjusted":[84,142,214,272],"profitability":[85,143,273,374],"insignificant.":[87],"We":[88],"argue":[89],"such":[91],"situations":[92],"primarily":[93],"arise":[94],"from":[95,114,241,300],"following":[97],"two":[98],"problems:":[99],"sparsity":[100],"positive":[102,221,344],"reward":[103,345],"curse":[106,334],"dimensionality.":[108],"These":[109],"limitations":[110],"prevent":[111],"comprehensively":[115],"asset":[117,307],"price":[118,308],"change":[119,309],"patterns":[120,310],"environment.":[124,314,347],"As":[125],"a":[126,154,180,236],"result,":[127],"cannot":[131],"effectively":[132],"explore":[133],"dynamic":[135],"policy":[138,201,211],"improve":[140,338],"process.":[147,270],"To":[148],"problems,":[151],"propose":[153],"novel":[155],"multi-agent":[156],"system":[158,182,205,232,277,295,355],"based":[159,365],"on":[160,208,366],"hierarchical":[162],"(HDRL)":[166],"algorithmic":[167],"framework":[168],"this":[170,173],"research.":[171],"Under":[172],"framework,":[174],"work":[177],"together":[178,194],"as":[179],"for":[183,199],"optimization.":[185],"Specifically,":[186],"by":[187,292,399],"designing":[188],"an":[189],"auxiliary":[190,321],"works":[193],"executive":[197],"optimal":[200],"exploration,":[202],"can":[206,327,423],"focus":[207],"exploring":[209],"higher":[213],"return":[215,222],"action":[218],"space":[219],"low":[224],"variance.":[225],"The":[226,271,379],"performance":[227,372],"proposed":[230,353],"evaluated":[234],"29":[239],"stocks":[240],"Dow":[243],"Jones":[244],"index":[245],"four":[247,384],"different":[248],"experiments.":[249,431],"In":[250,348],"process,":[253],"objective":[255],"functions":[256],"actor":[259],"critic":[261],"both":[262],"ultimately":[263],"achieve":[264],"stable":[265],"convergence":[266],"our":[275,293,391],"significantly":[283],"improved.":[284],"Hence,":[285],"prove":[287],"policies":[290,417],"executed":[291],"out-sample":[297],"experiments":[298,386],"originate":[299],"agents'":[303],"comprehensive":[304],"Furthermore,":[315],"adopting":[319],"HDRL":[324],"efficiently":[328],"overcome":[329],"issue":[331],"dimensionality":[336],"efficiency":[341],"sparse":[346],"each":[349],"back-test":[350],"experiment,":[351],"compared":[357],"sixteen":[359],"traditional":[360],"strategies":[361,364,398],"ten":[363],"machine":[367],"risk":[376],"control":[377],"ability.":[378],"empirical":[380],"results":[381],"evaluation":[385],"demonstrate":[387],"efficacy":[389],"system,":[393],"which":[394],"outperforms":[395],"all":[396],"other":[397],"at":[400],"least":[401],"8.2%":[402],"terms":[404],"Sharpe":[406],"ratio,":[407,409],"Sorino":[408],"Calmar":[411],"ratio.":[412],"This":[413],"indicates":[414],"learned":[418],"exhibit":[424],"excellent":[425],"generalization":[426],"ability":[427],"back-testing":[430]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}