{"id":"https://openalex.org/W4415428419","doi":"https://doi.org/10.3233/faia251161","title":"Population-Based Multi-Objective Reinforcement Learning with Information Sharing and Differentiation","display_name":"Population-Based Multi-Objective Reinforcement Learning with Information Sharing and Differentiation","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428419","doi":"https://doi.org/10.3233/faia251161"},"language":null,"primary_location":{"id":"doi:10.3233/faia251161","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251161","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia251161","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017761703","display_name":"Xiaoqiang Wu","orcid":"https://orcid.org/0000-0001-7115-3264"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqiang Wu","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101903539","display_name":"Qingling Zhu","orcid":"https://orcid.org/0000-0002-0925-9903"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingling Zhu","raw_affiliation_strings":["National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046906366","display_name":"Junkai Ji","orcid":"https://orcid.org/0000-0002-1985-938X"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junkai Ji","raw_affiliation_strings":["National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066935890","display_name":"Qiuzhen Lin","orcid":"https://orcid.org/0000-0003-2415-0401"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiuzhen Lin","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050385116","display_name":"Wei\u2013Neng Chen","orcid":"https://orcid.org/0000-0003-0843-5802"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Neng Chen","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100393871","display_name":"Jianqiang Li","orcid":"https://orcid.org/0000-0002-2208-962X"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqiang Li","raw_affiliation_strings":["National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.63946711,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.8946999907493591,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.8946999907493591,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.7656999826431274},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.6215999722480774},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.5652999877929688},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.47600001096725464},{"id":"https://openalex.org/keywords/information-sharing","display_name":"Information sharing","score":0.4226999878883362},{"id":"https://openalex.org/keywords/advice","display_name":"Advice (programming)","score":0.3765999972820282},{"id":"https://openalex.org/keywords/complete-information","display_name":"Complete information","score":0.34929999709129333}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7656999826431274},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7508999705314636},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.6215999722480774},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.5652999877929688},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.47600001096725464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4648999869823456},{"id":"https://openalex.org/C2776854237","wikidata":"https://www.wikidata.org/wiki/Q6031064","display_name":"Information sharing","level":2,"score":0.4226999878883362},{"id":"https://openalex.org/C2779955035","wikidata":"https://www.wikidata.org/wiki/Q4686785","display_name":"Advice (programming)","level":2,"score":0.3765999972820282},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37369999289512634},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.34929999709129333},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C2776604539","wikidata":"https://www.wikidata.org/wiki/Q6423395","display_name":"Knowledge sharing","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C2781043087","wikidata":"https://www.wikidata.org/wiki/Q939761","display_name":"Preference theory","level":3,"score":0.2603999972343445},{"id":"https://openalex.org/C136979486","wikidata":"https://www.wikidata.org/wiki/Q773483","display_name":"Existential quantification","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia251161","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251161","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia251161","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251161","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"To":[0,58],"efficiently":[1],"tackle":[2],"problems":[3],"with":[4,74],"multiple":[5,72,152],"conflicting":[6],"objectives,":[7],"several":[8,167],"Multi-Objective":[9],"Reinforcement":[10],"Learning":[11],"(MORL)":[12],"algorithms":[13],"utilize":[14],"a":[15,41,79],"universal":[16,42,75],"policy":[17,43,76,104],"network":[18],"that":[19,70],"takes":[20],"preference":[21,117],"weights":[22,94],"as":[23,44],"input":[24],"to":[25,38,48,52,95,110],"represent":[26],"optimal":[27],"policies":[28],"for":[29,55,150],"all":[30],"different":[31],"preferences.":[32,57],"However,":[33],"it":[34,45],"is":[35,46,85],"quite":[36],"challenging":[37],"train":[39],"such":[40],"easy":[47],"forget":[49],"or":[50],"fail":[51],"learn":[53],"skills":[54],"some":[56],"alleviate":[59],"this":[60],"issue,":[61],"we":[62],"propose":[63],"an":[64],"efficient":[65],"Population-Based":[66],"MORL":[67,169],"(PB-MORL)":[68],"method":[69],"trains":[71],"agents":[73],"networks":[77],"using":[78],"shared":[80],"replay":[81],"buffer.":[82,101],"Each":[83],"agent":[84,107],"biased":[86],"towards":[87],"optimizing":[88],"specific":[89,113],"objectives":[90],"by":[91],"applying":[92],"differentiated":[93],"the":[96,100,103,112,116,121,125,129,132,136,145,162],"rewards":[97],"sampled":[98],"from":[99],"Therefore,":[102],"of":[105,115,147,164],"each":[106],"only":[108],"needs":[109],"handle":[111],"part":[114],"space":[118],"rather":[119],"than":[120],"entire":[122],"space,":[123],"simplifying":[124],"training":[126,151],"task.":[127],"Meanwhile,":[128],"experiences":[130],"in":[131],"common":[133],"buffer":[134],"facilitate":[135],"information":[137],"sharing":[138],"among":[139],"individuals,":[140],"which":[141],"can":[142],"significantly":[143],"reduce":[144],"number":[146],"interaction":[148],"steps":[149],"agents.":[153],"Experiments":[154],"on":[155],"both":[156],"continuous":[157],"and":[158],"discrete":[159],"tasks":[160],"demonstrate":[161],"superiority":[163],"PB-MORL":[165],"over":[166],"state-of-the-art":[168],"methods.":[170]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-24T00:00:00"}