{"id":"https://openalex.org/W4414134053","doi":"https://doi.org/10.1007/s40747-025-02091-5","title":"HRL-MOEA: a hybrid reinforcement learning-enhanced multi-objective recommendation algorithm with dynamic policy orchestration","display_name":"HRL-MOEA: a hybrid reinforcement learning-enhanced multi-objective recommendation algorithm with dynamic policy orchestration","publication_year":2025,"publication_date":"2025-09-11","ids":{"openalex":"https://openalex.org/W4414134053","doi":"https://doi.org/10.1007/s40747-025-02091-5"},"language":"en","primary_location":{"id":"doi:10.1007/s40747-025-02091-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-02091-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-02091-5.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/s40747-025-02091-5.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065678043","display_name":"Liang Chu","orcid":"https://orcid.org/0009-0004-5825-5687"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Chu","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058755242","display_name":"Ye Tian","orcid":"https://orcid.org/0000-0002-3487-5126"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ye Tian","raw_affiliation_strings":["Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5058755242"],"corresponding_institution_ids":["https://openalex.org/I143868143"],"apc_list":{"value":1320,"currency":"GBP","value_usd":1619},"apc_paid":{"value":1320,"currency":"GBP","value_usd":1619},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36567768,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"10","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9922999739646912,"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":0.9879000186920166,"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":0.7901999950408936},{"id":"https://openalex.org/keywords/orchestration","display_name":"Orchestration","score":0.6642000079154968},{"id":"https://openalex.org/keywords/evolutionary-algorithm","display_name":"Evolutionary algorithm","score":0.6355999708175659},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.5709999799728394},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.5666999816894531},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5065000057220459},{"id":"https://openalex.org/keywords/evolutionary-computation","display_name":"Evolutionary computation","score":0.501800000667572},{"id":"https://openalex.org/keywords/computational-intelligence","display_name":"Computational intelligence","score":0.4862000048160553}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7901999950408936},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7476999759674072},{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.6642000079154968},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.6355999708175659},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.5709999799728394},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.5666999816894531},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5065000057220459},{"id":"https://openalex.org/C105902424","wikidata":"https://www.wikidata.org/wiki/Q1197129","display_name":"Evolutionary computation","level":2,"score":0.501800000667572},{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.4862000048160553},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43369999527931213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4092999994754791},{"id":"https://openalex.org/C8880873","wikidata":"https://www.wikidata.org/wiki/Q187787","display_name":"Genetic algorithm","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C116537","wikidata":"https://www.wikidata.org/wiki/Q2169973","display_name":"Service provider","level":3,"score":0.3522000014781952},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C186625053","wikidata":"https://www.wikidata.org/wiki/Q1130191","display_name":"Information overload","level":2,"score":0.34150001406669617},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3009999990463257},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2831000089645386},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C121835503","wikidata":"https://www.wikidata.org/wiki/Q2596288","display_name":"Evolutionary programming","level":3,"score":0.26499998569488525},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C6135463","wikidata":"https://www.wikidata.org/wiki/Q5532920","display_name":"Genetic representation","level":3,"score":0.26010000705718994},{"id":"https://openalex.org/C21569690","wikidata":"https://www.wikidata.org/wiki/Q94702","display_name":"Collaborative filtering","level":3,"score":0.2554999887943268}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s40747-025-02091-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-02091-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-02091-5.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:faf632efcda94916a1815fb5f51fe0a2","is_oa":true,"landing_page_url":"https://doaj.org/article/faf632efcda94916a1815fb5f51fe0a2","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 10, Pp 1-16 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s40747-025-02091-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-025-02091-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-025-02091-5.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/W4414134053.pdf","grobid_xml":"https://content.openalex.org/works/W4414134053.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W103340358","https://openalex.org/W2000764607","https://openalex.org/W2080858591","https://openalex.org/W2106334424","https://openalex.org/W2116363350","https://openalex.org/W2326473470","https://openalex.org/W2336953982","https://openalex.org/W2541760237","https://openalex.org/W2594320709","https://openalex.org/W2907999153","https://openalex.org/W2945827670","https://openalex.org/W2965042574","https://openalex.org/W3045200674","https://openalex.org/W3097300053","https://openalex.org/W3100278010","https://openalex.org/W3116993882","https://openalex.org/W3123348991","https://openalex.org/W3126748901","https://openalex.org/W3130481949","https://openalex.org/W3154925836","https://openalex.org/W3190260202","https://openalex.org/W3199150109","https://openalex.org/W3203391496","https://openalex.org/W3214830073","https://openalex.org/W3216097587","https://openalex.org/W4212951676","https://openalex.org/W4232980324","https://openalex.org/W4282027681","https://openalex.org/W4290943562","https://openalex.org/W4297964528","https://openalex.org/W4324157320","https://openalex.org/W4375846150","https://openalex.org/W4379390495","https://openalex.org/W4387145966","https://openalex.org/W4388540026","https://openalex.org/W4393307203","https://openalex.org/W4394589830","https://openalex.org/W4394807962","https://openalex.org/W4394926854","https://openalex.org/W4399618167","https://openalex.org/W4406321924","https://openalex.org/W4407690596"],"related_works":["https://openalex.org/W79913212","https://openalex.org/W2094884983","https://openalex.org/W2378898096","https://openalex.org/W560952460","https://openalex.org/W2290927522","https://openalex.org/W4283579741","https://openalex.org/W3066706303","https://openalex.org/W876159576","https://openalex.org/W2943612818","https://openalex.org/W4385152897"],"abstract_inverted_index":{"Recommendation":[0],"algorithms":[1,167],"have":[2],"become":[3],"increasingly":[4],"prevalent":[5],"in":[6,32,47,143,168],"modern":[7],"society,":[8],"addressing":[9],"information":[10],"overload":[11],"by":[12],"delivering":[13],"content":[14],"aligned":[15],"with":[16],"user":[17],"preferences.":[18],"While":[19],"traditional":[20],"approaches":[21],"prioritize":[22],"recommendation":[23,48,69],"accuracy,":[24],"singular":[25],"focus":[26],"on":[27,73],"this":[28],"objective":[29],"often":[30],"results":[31,161],"popularity":[33],"bias.":[34],"This":[35,149],"imbalance":[36],"introduces":[37],"fairness":[38],"concerns":[39],"for":[40],"item":[41,55],"providers":[42],"and":[43,115],"detrimental":[44],"feedback":[45],"loops":[46],"ecosystems,":[49],"highlighting":[50],"the":[51,91,156],"critical":[52],"importance":[53],"of":[54,93],"exposure":[56],"fairness.":[57],"However,":[58],"balancing":[59],"these":[60,98],"dual":[61],"objectives":[62],"faces":[63],"fundamental":[64],"trade-off":[65],"challenges.":[66],"Existing":[67],"multi-objective":[68],"methods":[70],"typically":[71],"rely":[72],"empirically":[74],"fixed":[75],"genetic":[76],"operators":[77],"during":[78,122],"evolutionary":[79,107,124,158],"processes,":[80],"which":[81],"not":[82],"only":[83],"requires":[84],"laborious":[85],"parameter":[86],"tuning":[87],"but":[88],"also":[89],"constrains":[90],"generation":[92],"high-quality":[94],"solutions.":[95],"To":[96],"overcome":[97],"limitations,":[99],"we":[100],"propose":[101],"a":[102,119,126],"hybrid":[103],"reinforcement":[104],"learning-enhanced":[105],"adaptive":[106],"algorithm":[108],"(HRL-MOEA).":[109],"The":[110],"framework":[111],"synergistically":[112],"integrates":[113],"SARSA":[114],"Q-learning":[116],"strategies":[117],"through":[118],"phase-aware":[120],"mechanism:":[121],"early":[123],"stages,":[125],"conservative":[127],"SARSA-based":[128],"self-adaptive":[129],"mechanism":[130],"facilitates":[131],"comprehensive":[132],"solution":[133],"space":[134],"exploration,":[135],"while":[136],"strategically":[137],"transitioning":[138],"to":[139,146,154],"Q-learning\u2019s":[140],"exploitation-oriented":[141],"policy":[142],"later":[144],"phases":[145],"accelerate":[147],"convergence.":[148],"dynamic":[150],"strategy":[151],"is":[152],"conducive":[153],"enhancing":[155],"model\u2019s":[157],"performance.":[159],"Experimental":[160],"demonstrate":[162],"that":[163],"HRL-MOEA":[164],"outperforms":[165],"existing":[166],"performance":[169],"effectiveness.":[170]},"counts_by_year":[],"updated_date":"2026-03-14T08:43:22.919905","created_date":"2025-10-10T00:00:00"}