{"id":"https://openalex.org/W4398250202","doi":"https://doi.org/10.1109/tnnls.2024.3397393","title":"Robust Multiobjective Reinforcement Learning Considering Environmental Uncertainties","display_name":"Robust Multiobjective Reinforcement Learning Considering Environmental Uncertainties","publication_year":2024,"publication_date":"2024-05-23","ids":{"openalex":"https://openalex.org/W4398250202","doi":"https://doi.org/10.1109/tnnls.2024.3397393","pmid":"https://pubmed.ncbi.nlm.nih.gov/38781066"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3397393","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3397393","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5061259393","display_name":"Xiangkun He","orcid":"https://orcid.org/0000-0001-9818-0879"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Xiangkun He","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Nanyang Technological University, Jurong West, Singapore","School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-9818-0879","affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"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, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-0422-8235","affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101755392","display_name":"Xu Chen","orcid":"https://orcid.org/0000-0003-0144-1775"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Chen","raw_affiliation_strings":["Jailing School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0144-1775","affiliations":[{"raw_affiliation_string":"Jailing School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100384727","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0002-4021-4228"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["Department of Computer Science, University College London, London, U.K"],"raw_orcid":"https://orcid.org/0000-0002-4021-4228","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University College London, London, U.K","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024351828","display_name":"Xuewu Ji","orcid":"https://orcid.org/0000-0002-5242-8119"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuewu Ji","raw_affiliation_strings":["State Key Laboratory of Automotive Safety and Energy, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5242-8119","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Safety and Energy, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072073374","display_name":"Chen Lv","orcid":"https://orcid.org/0000-0001-6897-4512"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chen Lv","raw_affiliation_strings":["School of Mechanical and Aerospace Engineering, Nanyang Technological University, Jurong West, Singapore","School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6897-4512","affiliations":[{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Jurong West, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5061259393"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":2.5175,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.90402896,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"36","issue":"4","first_page":"6368","last_page":"6382"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.8849999904632568,"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":0.8849999904632568,"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/T11641","display_name":"Insect and Pesticide Research","score":0.7746000289916992,"subfield":{"id":"https://openalex.org/subfields/1109","display_name":"Insect Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7165824770927429},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6919583678245544},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6335747838020325},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6312049627304077},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6104124188423157},{"id":"https://openalex.org/keywords/pareto-principle","display_name":"Pareto principle","score":0.59259432554245},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5769135355949402},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.4857407212257385},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"Multi-objective optimization","score":0.4815845489501953},{"id":"https://openalex.org/keywords/pareto-optimal","display_name":"Pareto optimal","score":0.47250497341156006},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3974628150463104},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35457777976989746},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3068512976169586},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24756652116775513},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.088189035654068}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7165824770927429},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6919583678245544},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6335747838020325},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6312049627304077},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6104124188423157},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.59259432554245},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5769135355949402},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.4857407212257385},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.4815845489501953},{"id":"https://openalex.org/C2986314615","wikidata":"https://www.wikidata.org/wiki/Q36829","display_name":"Pareto optimal","level":3,"score":0.47250497341156006},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3974628150463104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35457777976989746},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3068512976169586},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24756652116775513},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.088189035654068},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3397393","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3397393","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:38781066","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38781066","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[{"id":"https://openalex.org/G8643382381","display_name":null,"funder_award_id":"51975311","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":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W1577581905","https://openalex.org/W2012612381","https://openalex.org/W2028560736","https://openalex.org/W2045276965","https://openalex.org/W2060846151","https://openalex.org/W2106334424","https://openalex.org/W2149726897","https://openalex.org/W2155153696","https://openalex.org/W2158782408","https://openalex.org/W2186820913","https://openalex.org/W2492629073","https://openalex.org/W2562637781","https://openalex.org/W2625286567","https://openalex.org/W2800773442","https://openalex.org/W2803896320","https://openalex.org/W2922175631","https://openalex.org/W2928408182","https://openalex.org/W2962850106","https://openalex.org/W2963574014","https://openalex.org/W3001932519","https://openalex.org/W3004325772","https://openalex.org/W3018074695","https://openalex.org/W3076768548","https://openalex.org/W3105444733","https://openalex.org/W3153119964","https://openalex.org/W3157100883","https://openalex.org/W3170257619","https://openalex.org/W3203245557","https://openalex.org/W3209378991","https://openalex.org/W4200008856","https://openalex.org/W4225773298","https://openalex.org/W4250589301","https://openalex.org/W4254547512","https://openalex.org/W4287266177","https://openalex.org/W4307774253","https://openalex.org/W4311923925","https://openalex.org/W4312876648","https://openalex.org/W4367727829","https://openalex.org/W4386824909","https://openalex.org/W4386922880","https://openalex.org/W4387303358","https://openalex.org/W4387415195","https://openalex.org/W4388208929","https://openalex.org/W4389044710","https://openalex.org/W4396599460","https://openalex.org/W6630172796","https://openalex.org/W6640425456","https://openalex.org/W6649830115","https://openalex.org/W6675655579","https://openalex.org/W6677477198","https://openalex.org/W6680139899","https://openalex.org/W6684921986","https://openalex.org/W6726075558","https://openalex.org/W6728073343","https://openalex.org/W6735677848","https://openalex.org/W6754478334","https://openalex.org/W6754554871","https://openalex.org/W6756275316","https://openalex.org/W6759312646","https://openalex.org/W6762548700","https://openalex.org/W6766952794","https://openalex.org/W6777159553","https://openalex.org/W6779277724","https://openalex.org/W6779795787","https://openalex.org/W6782628559","https://openalex.org/W6789484704","https://openalex.org/W6809919215","https://openalex.org/W6840990507"],"related_works":["https://openalex.org/W1963790170","https://openalex.org/W2073298047","https://openalex.org/W2033790662","https://openalex.org/W2090178682","https://openalex.org/W2586328217","https://openalex.org/W2049264236","https://openalex.org/W4241467429","https://openalex.org/W2001591765","https://openalex.org/W2073147994","https://openalex.org/W1588199609"],"abstract_inverted_index":{"Numerous":[0],"real-world":[1],"decision":[2,107],"or":[3,32],"control":[4],"problems":[5],"involve":[6],"multiple":[7],"conflicting":[8],"objectives":[9],"whose":[10],"relative":[11],"importance":[12],"(preference)":[13],"is":[14,25,87,142],"required":[15],"to":[16,61],"be":[17],"weighed":[18],"in":[19,144],"different":[20],"scenarios.":[21],"While":[22],"Pareto":[23],"optimality":[24],"desired,":[26],"environmental":[27,30,59,82,85],"uncertainties":[28],"(e.g.,":[29],"changes":[31],"observational":[33,118],"noises)":[34],"may":[35],"mislead":[36],"the":[37,73,94],"agent":[38,92],"into":[39,103],"performing":[40],"suboptimal":[41],"policies.":[42],"In":[43],"this":[44],"article,":[45],"we":[46,111],"present":[47],"a":[48,63,100,104],"novel":[49],"multiobjective":[50,54,105,146],"optimization":[51],"paradigm,":[52],"robust":[53,69],"reinforcement":[55],"learning":[56],"(RMORL)":[57],"considering":[58],"uncertainties,":[60],"train":[62],"single":[64],"model":[65],"that":[66,122],"can":[67],"approximate":[68],"Pareto-optimal":[70],"policies":[71],"across":[72,93],"entire":[74,95],"preference":[75,96],"space.":[76],"To":[77],"enhance":[78],"policy":[79,123],"robustness":[80],"against":[81,117],"changes,":[83],"an":[84,90,113],"disturbance":[86],"modeled":[88],"as":[89],"adversarial":[91,114,127],"space":[97],"via":[98],"incorporating":[99],"zero-sum":[101],"game":[102],"Markov":[106],"process":[108],"(MOMDP).":[109],"Additionally,":[110],"devise":[112],"defense":[115],"technique":[116,141],"perturbations,":[119],"which":[120,160],"ensures":[121],"variations,":[124],"perturbed":[125],"by":[126],"attacks":[128],"on":[129],"state":[130],"observations,":[131],"remain":[132],"within":[133],"bounds":[134],"under":[135],"any":[136],"specified":[137],"preferences.":[138],"The":[139],"proposed":[140],"assessed":[143],"five":[145],"environments":[147],"with":[148,157],"continuous":[149],"action":[150],"spaces,":[151],"showcasing":[152],"its":[153],"effectiveness":[154],"through":[155],"comparisons":[156],"competitive":[158],"baselines,":[159],"encompass":[161],"classical":[162],"and":[163],"state-of-the-art":[164],"schemes.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4}],"updated_date":"2026-05-23T08:51:43.019350","created_date":"2025-10-10T00:00:00"}