{"id":"https://openalex.org/W4410027608","doi":"https://doi.org/10.1109/lra.2025.3566585","title":"Meta-Reinforcement Learning With Evolving Gradient Regularization","display_name":"Meta-Reinforcement Learning With Evolving Gradient Regularization","publication_year":2025,"publication_date":"2025-05-02","ids":{"openalex":"https://openalex.org/W4410027608","doi":"https://doi.org/10.1109/lra.2025.3566585"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2025.3566585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3566585","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100685932","display_name":"Jiaxing Chen","orcid":"https://orcid.org/0000-0001-7309-0535"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiaxing Chen","raw_affiliation_strings":["College of Intelligent Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligent Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ao Ma","orcid":"https://orcid.org/0009-0005-0849-0256"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ao Ma","raw_affiliation_strings":["College of Intelligent Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligent Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081802331","display_name":"Shaofei Chen","orcid":"https://orcid.org/0000-0001-6823-555X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaofei Chen","raw_affiliation_strings":["College of Intelligent Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligent Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090802334","display_name":"Weilin Yuan","orcid":"https://orcid.org/0000-0001-9894-5253"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weilin Yuan","raw_affiliation_strings":["College of Information and Communication, National University of Defense Technology, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"College of Information and Communication, National University of Defense Technology, Wuhan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090565823","display_name":"Zhenzhen Hu","orcid":"https://orcid.org/0000-0003-2807-8208"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenzhen Hu","raw_affiliation_strings":["College of Intelligent Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligent Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100432725","display_name":"Peng Li","orcid":"https://orcid.org/0000-0002-7138-430X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Li","raw_affiliation_strings":["College of Intelligent Science and Technology, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligent Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100685932"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":2.3568,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.88879577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"10","issue":"6","first_page":"6280","last_page":"6287"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.7587000131607056,"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/T12676","display_name":"Machine Learning and ELM","score":0.7587000131607056,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.7010999917984009,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.6363000273704529,"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":0.7216143012046814},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.623040497303009},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5154224634170532},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48543626070022583},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4499165713787079},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17915159463882446},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.05325108766555786}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7216143012046814},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.623040497303009},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5154224634170532},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48543626070022583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4499165713787079},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17915159463882446},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.05325108766555786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2025.3566585","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2025.3566585","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1683118484","display_name":null,"funder_award_id":"62376280","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1977655452","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2766447205","https://openalex.org/W3127561923","https://openalex.org/W4312125978","https://openalex.org/W4386712244","https://openalex.org/W4398194910","https://openalex.org/W6638018090","https://openalex.org/W6714477741","https://openalex.org/W6731982132","https://openalex.org/W6735618850","https://openalex.org/W6736057607","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6747625265","https://openalex.org/W6750254146","https://openalex.org/W6755365793","https://openalex.org/W6755476724","https://openalex.org/W6760378562","https://openalex.org/W6760698134","https://openalex.org/W6764592398","https://openalex.org/W6765145614","https://openalex.org/W6767067800","https://openalex.org/W6767599400","https://openalex.org/W6768532476","https://openalex.org/W6768560635","https://openalex.org/W6769596995","https://openalex.org/W6797636097","https://openalex.org/W6797674030","https://openalex.org/W6810200297","https://openalex.org/W6810568894","https://openalex.org/W6838836181","https://openalex.org/W6849169497","https://openalex.org/W6849765087","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,20],"(DRL)":[3],"typically":[4],"requires":[5],"reinitializing":[6],"training":[7],"for":[8],"new":[9],"tasks,":[10],"limiting":[11],"its":[12],"generalization":[13,126],"due":[14,43],"to":[15,44],"isolated":[16],"knowledge":[17],"transfer.":[18],"Meta-reinforcement":[19],"(Meta-RL)":[21],"addresses":[22],"this":[23,51],"by":[24,98],"enabling":[25],"rapid":[26],"adaptation":[27,74,112],"through":[28],"prior":[29],"task":[30,47,90],"experiences,":[31],"yet":[32],"existing":[33],"gradient-based":[34],"methods":[35],"like":[36],"MAML":[37,58,67],"suffer":[38],"from":[39],"poor":[40],"out-of-distribution":[41,104],"performance":[42,113],"overfitting":[45],"narrow":[46],"distributions.":[48,91],"To":[49],"overcome":[50],"limitation,":[52],"we":[53],"propose":[54],"Evolving":[55],"Gradient":[56],"Regularization":[57],"(ER-MAML).":[59],"By":[60],"integrating":[61],"evolving":[62],"gradient":[63],"regularization":[64,78],"into":[65],"the":[66,115],"framework,":[68],"ER-MAML":[69,94],"optimizes":[70],"meta-gradients":[71],"while":[72],"constraining":[73],"directions":[75],"via":[76],"a":[77],"policy.":[79],"This":[80],"dual":[81],"mechanism":[82],"prevents":[83],"overparameterization":[84],"and":[85],"enhances":[86],"robustness":[87],"across":[88],"diverse":[89],"Experiments":[92],"demonstrate":[93],"outperforms":[95],"state-of-the-art":[96],"baselines":[97],"<inline-formula":[99],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[100],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[101],"notation=\"LaTeX\">$14.6\\%$</tex-math></inline-formula>":[102],"in":[103,114,123],"success":[105],"rates.":[106],"It":[107],"also":[108],"achieves":[109],"strong":[110],"online":[111],"MetaWorld":[116],"benchmark.":[117],"These":[118],"results":[119],"validate":[120],"ER-MAML's":[121],"effectiveness":[122],"improving":[124],"meta-RL":[125],"under":[127],"distribution":[128],"shifts.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}