{"id":"https://openalex.org/W4387171246","doi":"https://doi.org/10.3233/faia230551","title":"BiERL: A Meta Evolutionary Reinforcement Learning Framework via Bilevel Optimization","display_name":"BiERL: A Meta Evolutionary Reinforcement Learning Framework via Bilevel Optimization","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387171246","doi":"https://doi.org/10.3233/faia230551"},"language":"en","primary_location":{"id":"doi:10.3233/faia230551","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230551","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230551","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://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230551","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100649301","display_name":"Junyi Wang","orcid":"https://orcid.org/0000-0003-0464-4543"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyi Wang","raw_affiliation_strings":["Department of Control Science and Intelligent Engineering, Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Control Science and Intelligent Engineering, Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021451616","display_name":"Yuanyang Zhu","orcid":"https://orcid.org/0000-0001-7484-1804"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyang Zhu","raw_affiliation_strings":["Department of Control Science and Intelligent Engineering, Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Control Science and Intelligent Engineering, Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376415","display_name":"Zhi Wang","orcid":"https://orcid.org/0000-0003-0304-3965"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Wang","raw_affiliation_strings":["Department of Control Science and Intelligent Engineering, Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Control Science and Intelligent Engineering, Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084937471","display_name":"Yan Zheng","orcid":"https://orcid.org/0000-0003-2741-058X"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Zheng","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University","Department of Control Science and Intelligent Engineering, Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Department of Control Science and Intelligent Engineering, Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047509839","display_name":"Jianye Hao","orcid":"https://orcid.org/0000-0002-0422-8235"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianye Hao","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100697167","display_name":"Chunlin Chen","orcid":"https://orcid.org/0000-0003-3929-4707"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunlin Chen","raw_affiliation_strings":["Department of Control Science and Intelligent Engineering, Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Control Science and Intelligent Engineering, Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4988,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.68003628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9952999949455261,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9952999949455261,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9919000267982483,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9904999732971191,"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":0.8510963916778564},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.8053429126739502},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7474273443222046},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5936534404754639},{"id":"https://openalex.org/keywords/bilevel-optimization","display_name":"Bilevel optimization","score":0.5620635747909546},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.529471755027771},{"id":"https://openalex.org/keywords/aka","display_name":"AKA","score":0.5251326560974121},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.5197960138320923},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.49006712436676025},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4785110056400299},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4302710294723511},{"id":"https://openalex.org/keywords/evolutionary-algorithm","display_name":"Evolutionary algorithm","score":0.4183880090713501},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.33827733993530273},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.3069188594818115},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12048202753067017},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10788896679878235}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8510963916778564},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.8053429126739502},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7474273443222046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5936534404754639},{"id":"https://openalex.org/C3309286","wikidata":"https://www.wikidata.org/wiki/Q4907693","display_name":"Bilevel optimization","level":3,"score":0.5620635747909546},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.529471755027771},{"id":"https://openalex.org/C121158502","wikidata":"https://www.wikidata.org/wiki/Q4652161","display_name":"AKA","level":2,"score":0.5251326560974121},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.5197960138320923},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.49006712436676025},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4785110056400299},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4302710294723511},{"id":"https://openalex.org/C159149176","wikidata":"https://www.wikidata.org/wiki/Q14489129","display_name":"Evolutionary algorithm","level":2,"score":0.4183880090713501},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33827733993530273},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3069188594818115},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12048202753067017},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10788896679878235},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia230551","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230551","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230551","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/faia230551","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230551","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230551","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":[{"id":"https://openalex.org/G4904587412","display_name":null,"funder_award_id":"62006111","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7996831764","display_name":null,"funder_award_id":"62073160","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8734799983","display_name":null,"funder_award_id":"62106172","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387171246.pdf"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2158782408","https://openalex.org/W2591916597","https://openalex.org/W2596367596","https://openalex.org/W2604763608","https://openalex.org/W2614367549","https://openalex.org/W2623491082","https://openalex.org/W2779977383","https://openalex.org/W2787387965","https://openalex.org/W2898585845","https://openalex.org/W2907670343","https://openalex.org/W2943810245","https://openalex.org/W2950728319","https://openalex.org/W2951799422","https://openalex.org/W2952465248","https://openalex.org/W2953437684","https://openalex.org/W2955061181","https://openalex.org/W2957856373","https://openalex.org/W2978843034","https://openalex.org/W2982316857","https://openalex.org/W2995179471","https://openalex.org/W3004082694","https://openalex.org/W3004704245","https://openalex.org/W3021933818","https://openalex.org/W3034960860","https://openalex.org/W3035180992","https://openalex.org/W3046093665","https://openalex.org/W3048000637","https://openalex.org/W3089723243","https://openalex.org/W3091795298","https://openalex.org/W3097892290","https://openalex.org/W3117812535","https://openalex.org/W3130140588","https://openalex.org/W3154227779","https://openalex.org/W3174931113","https://openalex.org/W3204238027","https://openalex.org/W3205764667","https://openalex.org/W4220744913","https://openalex.org/W4248908364","https://openalex.org/W4286909706","https://openalex.org/W4287116371","https://openalex.org/W4287624180","https://openalex.org/W4288359891","https://openalex.org/W4288418822","https://openalex.org/W4302010773","https://openalex.org/W4307934390","https://openalex.org/W4394662461","https://openalex.org/W4394666657"],"related_works":["https://openalex.org/W4297800546","https://openalex.org/W4301772239","https://openalex.org/W3199608561","https://openalex.org/W1762936176","https://openalex.org/W2898569737","https://openalex.org/W4386702721","https://openalex.org/W4297803541","https://openalex.org/W4385945014","https://openalex.org/W2963852457","https://openalex.org/W4387171246"],"abstract_inverted_index":{"Evolutionary":[0],"reinforcement":[1,11],"learning":[2,12,110,136],"(ERL)":[3],"algorithms":[4],"recently":[5],"raise":[6],"attention":[7],"in":[8,53,116],"tackling":[9],"complex":[10],"(RL)":[13],"problems":[14],"due":[15],"to":[16,23,49,55,108,121],"high":[17],"parallelism,":[18],"while":[19],"they":[20],"are":[21],"prone":[22],"insufficient":[24],"exploration":[25],"or":[26,72],"model":[27,59,77],"collapse":[28],"without":[29],"carefully":[30],"tuning":[31],"hyperparameters":[32,52],"(aka":[33],"meta-parameters).":[34],"In":[35],"the":[36,57,66,87,104,135],"paper,":[37],"we":[38],"propose":[39],"a":[40,61,98,125,139],"general":[41,126],"meta":[42],"ERL":[43,58,142],"framework":[44],"via":[45],"bilevel":[46],"optimization":[47,74],"(BiERL)":[48],"jointly":[50],"update":[51],"parallel":[54],"training":[56],"within":[60],"single":[62],"agent,":[63],"which":[64],"relieves":[65],"need":[67],"for":[68,138],"prior":[69],"domain":[70],"knowledge":[71],"costly":[73],"procedure":[75],"before":[76],"deployment.":[78],"We":[79,112],"design":[80],"an":[81,92],"elegant":[82],"meta-level":[83,105],"architecture":[84],"that":[85,123],"embeds":[86],"inner-level\u2019s":[88],"evolving":[89],"experience":[90],"into":[91],"informative":[93],"population":[94],"representation":[95],"and":[96,100,118,132],"introduce":[97],"simple":[99],"feasible":[101],"evaluation":[102],"of":[103,141],"fitness":[106],"function":[107],"facilitate":[109],"efficiency.":[111],"perform":[113],"extensive":[114],"experiments":[115],"MuJoCo":[117],"Box2D":[119],"tasks":[120],"verify":[122],"as":[124],"framework,":[127],"BiERL":[128],"outperforms":[129],"various":[130],"baselines":[131],"consistently":[133],"improves":[134],"performance":[137],"diversity":[140],"algorithms.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}