{"id":"https://openalex.org/W4403094434","doi":"https://doi.org/10.1109/lra.2024.3472348","title":"Robust Proximal Adversarial Reinforcement Learning Under Model Mismatch","display_name":"Robust Proximal Adversarial Reinforcement Learning Under Model Mismatch","publication_year":2024,"publication_date":"2024-10-03","ids":{"openalex":"https://openalex.org/W4403094434","doi":"https://doi.org/10.1109/lra.2024.3472348"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2024.3472348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3472348","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/A5036810000","display_name":"Peng Zhai","orcid":"https://orcid.org/0000-0002-1374-7969"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Peng Zhai","raw_affiliation_strings":["Academy for Engineering and Technology, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1374-7969","affiliations":[{"raw_affiliation_string":"Academy for Engineering and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101555647","display_name":"Xiaoyi Wei","orcid":"https://orcid.org/0000-0001-7899-9297"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyi Wei","raw_affiliation_strings":["Academy for Engineering and Technology, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academy for Engineering and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027312666","display_name":"Taixian Hou","orcid":"https://orcid.org/0000-0002-2741-0494"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Taixian Hou","raw_affiliation_strings":["Academy for Engineering and Technology, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2741-0494","affiliations":[{"raw_affiliation_string":"Academy for Engineering and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074114254","display_name":"Xiaopeng Ji","orcid":"https://orcid.org/0000-0003-3920-8362"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaopeng Ji","raw_affiliation_strings":["State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3920-8362","affiliations":[{"raw_affiliation_string":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067808391","display_name":"Zhiyan Dong","orcid":"https://orcid.org/0000-0002-9459-1889"},"institutions":[{"id":"https://openalex.org/I4210089285","display_name":"Ji Hua Laboratory","ror":"https://ror.org/006aydy55","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210089285"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyan Dong","raw_affiliation_strings":["Ji Hua Laboratory, Foshan, China"],"raw_orcid":"https://orcid.org/0000-0002-9459-1889","affiliations":[{"raw_affiliation_string":"Ji Hua Laboratory, Foshan, China","institution_ids":["https://openalex.org/I4210089285"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109301408","display_name":"Jiafu Yi","orcid":null},"institutions":[{"id":"https://openalex.org/I20942203","display_name":"Hainan University","ror":"https://ror.org/03q648j11","country_code":"CN","type":"education","lineage":["https://openalex.org/I20942203"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiafu Yi","raw_affiliation_strings":["School of Information and Communication Engineering, Hainan University, Hainan, China"],"raw_orcid":"https://orcid.org/0009-0005-4560-4267","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Hainan University, Hainan, China","institution_ids":["https://openalex.org/I20942203"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100414906","display_name":"Lihua Zhang","orcid":"https://orcid.org/0000-0003-0467-4347"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lihua Zhang","raw_affiliation_strings":["Engineering Research Center of AI and Robotics, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0467-4347","affiliations":[{"raw_affiliation_string":"Engineering Research Center of AI and Robotics, Shanghai, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5036810000"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.3311,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66420242,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"9","issue":"11","first_page":"10248","last_page":"10255"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9761999845504761,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9761999845504761,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9021000266075134,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.912236213684082},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7352540493011475},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6175270676612854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5385146737098694},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5056941509246826},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36241260170936584},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.21667328476905823},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.10885250568389893}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.912236213684082},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7352540493011475},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6175270676612854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5385146737098694},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5056941509246826},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36241260170936584},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.21667328476905823},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.10885250568389893}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2024.3472348","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3472348","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":[{"score":0.5,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G335827678","display_name":null,"funder_award_id":"BX20220071","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G4822250653","display_name":null,"funder_award_id":"2022M720769","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2105078254","https://openalex.org/W2736601468","https://openalex.org/W2930863966","https://openalex.org/W2942465044","https://openalex.org/W2962890638","https://openalex.org/W2977389550","https://openalex.org/W2998401161","https://openalex.org/W3007035358","https://openalex.org/W3007869767","https://openalex.org/W3008634534","https://openalex.org/W3045875028","https://openalex.org/W3091635810","https://openalex.org/W3152878473","https://openalex.org/W3203069471","https://openalex.org/W3212580602","https://openalex.org/W4214717370","https://openalex.org/W4221110788","https://openalex.org/W4242795701","https://openalex.org/W4285603252","https://openalex.org/W4293846201","https://openalex.org/W4301180680","https://openalex.org/W4309326691","https://openalex.org/W4310541177","https://openalex.org/W4382119300","https://openalex.org/W6733049761","https://openalex.org/W6735677848","https://openalex.org/W6737897983","https://openalex.org/W6741002519","https://openalex.org/W6747027214","https://openalex.org/W6759312646","https://openalex.org/W6801964084"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"can":[3],"generate":[4],"high-performance":[5],"control":[6],"policies":[7],"for":[8,136],"complex":[9],"tasks":[10],"in":[11,85,119],"simulation":[12,31],"through":[13],"an":[14],"end-to-end":[15],"approach.":[16],"However,":[17],"the":[18,41,47,63,67,79,83,86,90,100,109,130,134,137,141],"RL":[19,58],"policy":[20,135],"is":[21],"not":[22],"robust":[23,57,115],"to":[24,38,40,46,74],"uncertainties":[25],"caused":[26],"by":[27],"modeling":[28,138],"mismatch":[29],"between":[30],"and":[32,55,112,122],"real":[33,42,123],"environments,":[34],"making":[35,78],"it":[36],"difficult":[37],"transfer":[39],"world.":[43],"In":[44],"response":[45],"above":[48],"challenge,":[49],"this":[50],"letter":[51],"introduces":[52],"a":[53,70,75,96],"lightweight":[54],"efficient":[56],"algorithm.":[59],"The":[60],"algorithm":[61,128],"transforms":[62],"optimization":[64],"objective":[65],"of":[66,133],"adversary":[68,80],"from":[69],"long-term":[71],"cumulative":[72],"reward":[73],"short-term":[76],"reward,":[77],"focus":[81],"on":[82],"performance":[84],"near":[87],"future.":[88],"Additionally,":[89],"adversarial":[91],"actions":[92],"are":[93],"projected":[94,104],"onto":[95],"finite":[97],"subset":[98],"within":[99],"perturbation":[101],"space":[102],"using":[103],"gradient":[105],"descent,":[106],"effectively":[107],"constraining":[108],"adversary's":[110],"strength":[111],"obtaining":[113],"more":[114],"policies.":[116],"Extensive":[117],"experiments":[118],"both":[120],"simulated":[121],"environments":[124],"show":[125],"that":[126],"our":[127],"improves":[129],"generalization":[131],"ability":[132],"mismatch,":[139],"outperforming":[140],"next":[142],"best":[143],"prior":[144],"methods":[145],"across":[146],"almost":[147],"all":[148],"environments.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}