{"id":"https://openalex.org/W4309326691","doi":"https://doi.org/10.1109/lra.2022.3220531","title":"Robust Adaptive Ensemble Adversary Reinforcement Learning","display_name":"Robust Adaptive Ensemble Adversary Reinforcement Learning","publication_year":2022,"publication_date":"2022-10-01","ids":{"openalex":"https://openalex.org/W4309326691","doi":"https://doi.org/10.1109/lra.2022.3220531"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2022.3220531","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3220531","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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":false,"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/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":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/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&amp;CG, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-3920-8362","affiliations":[{"raw_affiliation_string":"State Key Lab of CAD&amp;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/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"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":["Academy for Engineering and Technology, Fudan University, Shanghai, China","Ji Hua Laboratory, Foshan, China"],"raw_orcid":"https://orcid.org/0000-0002-9459-1889","affiliations":[{"raw_affiliation_string":"Academy for Engineering and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Ji Hua Laboratory, Foshan, China","institution_ids":["https://openalex.org/I4210089285"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100414906","display_name":"Lihua Zhang","orcid":"https://orcid.org/0000-0003-0467-4347"},"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"]},{"id":"https://openalex.org/I4210134929","display_name":"Jilin Province Science and Technology Department","ror":"https://ror.org/049x38272","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210134929"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lihua Zhang","raw_affiliation_strings":["Academy for Engineering and Technology, Fudan University, Shanghai, China","Institute of Meta-Medical, Fudan University, Shanghai, China","Jilin Provincial Key Laboratory of Intelligence Science and Engineering, Changchun, China"],"raw_orcid":"https://orcid.org/0000-0003-0467-4347","affiliations":[{"raw_affiliation_string":"Academy for Engineering and Technology, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Institute of Meta-Medical, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Jilin Provincial Key Laboratory of Intelligence Science and Engineering, Changchun, China","institution_ids":["https://openalex.org/I4210134929"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1599,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.81437766,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"7","issue":"4","first_page":"12562","last_page":"12568"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9970999956130981,"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":0.9970999956130981,"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":0.9939000010490417,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9853000044822693,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8311706781387329},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7589898109436035},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.647570788860321},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6168871521949768},{"id":"https://openalex.org/keywords/pid-controller","display_name":"PID controller","score":0.48384180665016174},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.48307207226753235},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48250889778137207},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.4777061939239502},{"id":"https://openalex.org/keywords/tracking-error","display_name":"Tracking error","score":0.4768877327442169},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46786263585090637},{"id":"https://openalex.org/keywords/generalization-error","display_name":"Generalization error","score":0.449789822101593},{"id":"https://openalex.org/keywords/drone","display_name":"Drone","score":0.4342954158782959},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.4242764115333557},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35208213329315186},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.24908855557441711},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.23663732409477234},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.186151385307312},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1572589874267578},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.142657071352005}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8311706781387329},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7589898109436035},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.647570788860321},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6168871521949768},{"id":"https://openalex.org/C47116090","wikidata":"https://www.wikidata.org/wiki/Q716829","display_name":"PID controller","level":3,"score":0.48384180665016174},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.48307207226753235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48250889778137207},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4777061939239502},{"id":"https://openalex.org/C183356978","wikidata":"https://www.wikidata.org/wiki/Q1779213","display_name":"Tracking error","level":3,"score":0.4768877327442169},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46786263585090637},{"id":"https://openalex.org/C117765406","wikidata":"https://www.wikidata.org/wiki/Q5362437","display_name":"Generalization error","level":3,"score":0.449789822101593},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.4342954158782959},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.4242764115333557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35208213329315186},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.24908855557441711},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.23663732409477234},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.186151385307312},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1572589874267578},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.142657071352005},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C536315585","wikidata":"https://www.wikidata.org/wiki/Q7698332","display_name":"Temperature control","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2022.3220531","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2022.3220531","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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/G335827678","display_name":null,"funder_award_id":"BX20220071","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":34,"referenced_works":["https://openalex.org/W2043806097","https://openalex.org/W2105078254","https://openalex.org/W2601574318","https://openalex.org/W2602963933","https://openalex.org/W2605102758","https://openalex.org/W2618858825","https://openalex.org/W2736601468","https://openalex.org/W2742658863","https://openalex.org/W2785389871","https://openalex.org/W2789758093","https://openalex.org/W2798391154","https://openalex.org/W2906430505","https://openalex.org/W2914994663","https://openalex.org/W2963184939","https://openalex.org/W3006670279","https://openalex.org/W3091635810","https://openalex.org/W3093922502","https://openalex.org/W3104876774","https://openalex.org/W3109978116","https://openalex.org/W3131678030","https://openalex.org/W3135759888","https://openalex.org/W3158253560","https://openalex.org/W4242795701","https://openalex.org/W4283797804","https://openalex.org/W4287725923","https://openalex.org/W6735677848","https://openalex.org/W6738590841","https://openalex.org/W6741002519","https://openalex.org/W6742577812","https://openalex.org/W6748519856","https://openalex.org/W6757955501","https://openalex.org/W6759312646","https://openalex.org/W6771936881","https://openalex.org/W6780587392"],"related_works":["https://openalex.org/W3211507692","https://openalex.org/W2964108292","https://openalex.org/W2955689724","https://openalex.org/W2941205169","https://openalex.org/W2604394466","https://openalex.org/W2981396729","https://openalex.org/W2952919291","https://openalex.org/W3035729345","https://openalex.org/W2950787360","https://openalex.org/W4309326691"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,90],"needs":[2],"to":[3,24,40,44,106,125,131,179],"learn":[4],"policies":[5,12],"through":[6,187],"trial":[7],"and":[8,48,59,65,120,141,160,196],"error.":[9],"The":[10,36,174],"unstable":[11],"in":[13,27,51,75,138,182],"the":[14,28,42,46,56,63,66,71,76,94,115,127,133,139,142,150,154,157,161,166,188,197,203],"early":[15],"stage":[16],"of":[17,97,153,191],"training":[18,96,135],"make":[19],"it":[20,50],"expensive":[21],"(and":[22],"time-consuming)":[23],"train":[25,45],"directly":[26],"real":[29,53,67,143,193],"environment,":[30],"which":[31,92],"may":[32,69],"cause":[33],"disastrous":[34],"consequences.":[35],"popular":[37],"solution":[38],"is":[39,200],"use":[41],"simulator":[43],"policy":[47,155],"deploy":[49],"a":[52,85,122,183,192],"environment.":[54],"However,":[55],"modeling":[57,158],"error":[58,159],"external":[60],"disturbance":[61,163],"between":[62],"simulation":[64],"environment":[68,144],"fail":[70],"physical":[72],"deployment,":[73],"resulting":[74],"sim2real":[77,184],"transfer":[78,185],"problem.":[79],"In":[80],"this":[81],"letter,":[82],"we":[83,113],"propose":[84],"novel":[86],"robust":[87],"adversarial":[88,134],"reinforcement":[89],"framework,":[91],"uses":[93],"ensemble":[95],"multi-adversarial":[98],"agents":[99],"that":[100,146],"can":[101],"adaptively":[102],"adjust":[103,126],"adversaries'":[104],"strength":[105],"enhance":[107],"RL":[108],"policy's":[109],"robustness.":[110],"More":[111],"specifically,":[112],"take":[114],"accumulative":[116],"reward":[117],"as":[118],"feedback":[119],"construct":[121],"PID":[123],"controller":[124],"adversary's":[128],"output":[129],"magnitude":[130],"perform":[132],"well.":[136],"Experiments":[137],"simulated":[140],"show":[145],"our":[147],"algorithm":[148,175],"improves":[149],"generalization":[151],"ability":[152],"for":[156],"uncertain":[162],"simultaneously,":[164],"outperforming":[165],"next":[167],"best":[168],"prior":[169],"methods":[170],"across":[171],"all":[172],"domains.":[173],"was":[176],"further":[177],"proven":[178],"be":[180],"effective":[181],"task":[186],"load":[189],"experiment":[190],"racing":[194],"drone,":[195],"tracking":[198],"performance":[199],"better":[201],"than":[202],"PID-based":[204],"flight":[205],"controller.":[206]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
