{"id":"https://openalex.org/W4411446786","doi":"https://doi.org/10.1109/tit.2025.3581454","title":"Theoretical Study of Conflict-Avoidant Multi-Objective Reinforcement Learning","display_name":"Theoretical Study of Conflict-Avoidant Multi-Objective Reinforcement Learning","publication_year":2025,"publication_date":"2025-06-19","ids":{"openalex":"https://openalex.org/W4411446786","doi":"https://doi.org/10.1109/tit.2025.3581454"},"language":"en","primary_location":{"id":"doi:10.1109/tit.2025.3581454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tit.2025.3581454","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"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 Information Theory","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/A5100705264","display_name":"Yudan Wang","orcid":"https://orcid.org/0000-0001-8757-8937"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yudan Wang","raw_affiliation_strings":["School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA","School of Electrical, Computer and Energy Engineering at Arizona State University, Tempe, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"School of Electrical, Computer and Energy Engineering at Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009073025","display_name":"Peiyao Xiao","orcid":"https://orcid.org/0000-0001-6879-7966"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peiyao Xiao","raw_affiliation_strings":["Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA","Department of Computer Science and Engineering at the University at Buffalo, Buffalo, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]},{"raw_affiliation_string":"Department of Computer Science and Engineering at the University at Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hao Ban","orcid":"https://orcid.org/0009-0004-4680-2233"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hao Ban","raw_affiliation_strings":["Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA","Department of Computer Science and Engineering at the University at Buffalo, Buffalo, NY, USA"],"raw_orcid":"https://orcid.org/0009-0004-4680-2233","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]},{"raw_affiliation_string":"Department of Computer Science and Engineering at the University at Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071973105","display_name":"Kaiyi Ji","orcid":"https://orcid.org/0000-0002-9533-0058"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaiyi Ji","raw_affiliation_strings":["Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA","Department of Computer Science and Engineering at the University at Buffalo, Buffalo, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-9533-0058","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]},{"raw_affiliation_string":"Department of Computer Science and Engineering at the University at Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012545205","display_name":"Shaofeng Zou","orcid":"https://orcid.org/0000-0002-2821-6941"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaofeng Zou","raw_affiliation_strings":["School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA","School of Electrical, Computer and Energy Engineering at Arizona State University, Tempe, AZ, USA"],"raw_orcid":"https://orcid.org/0000-0002-2821-6941","affiliations":[{"raw_affiliation_string":"School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"School of Electrical, Computer and Energy Engineering at Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100705264"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":1.0626,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77676647,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"71","issue":"9","first_page":"7254","last_page":"7269"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14420","display_name":"Advanced Research in Systems and Signal Processing","score":0.36890000104904175,"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"}},"topics":[{"id":"https://openalex.org/T14420","display_name":"Advanced Research in Systems and Signal Processing","score":0.36890000104904175,"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"}},{"id":"https://openalex.org/T12659","display_name":"Innovation Diffusion and Forecasting","score":0.34450000524520874,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.3151000142097473,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6407715082168579},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.47437387704849243},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.42424240708351135},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4151558578014374},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40785151720046997},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3264435827732086},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.3174719214439392},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28683656454086304}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6407715082168579},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47437387704849243},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.42424240708351135},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4151558578014374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40785151720046997},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3264435827732086},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.3174719214439392},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28683656454086304}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tit.2025.3581454","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tit.2025.3581454","pdf_url":null,"source":{"id":"https://openalex.org/S4502562","display_name":"IEEE Transactions on Information Theory","issn_l":"0018-9448","issn":["0018-9448","1557-9654"],"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 Information Theory","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G22116599","display_name":null,"funder_award_id":"CCF-2438429","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3350776499","display_name":null,"funder_award_id":"ECCS-2438392","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1987725948","https://openalex.org/W2009303086","https://openalex.org/W2012204020","https://openalex.org/W2012612381","https://openalex.org/W2060727197","https://openalex.org/W2344786740","https://openalex.org/W2575705757","https://openalex.org/W2583993537","https://openalex.org/W2963616027","https://openalex.org/W2981237928","https://openalex.org/W2990747716","https://openalex.org/W3160923286","https://openalex.org/W3167995857","https://openalex.org/W4367311517","https://openalex.org/W4367311942","https://openalex.org/W4376269829","https://openalex.org/W6630841318","https://openalex.org/W6674628981","https://openalex.org/W6683204974","https://openalex.org/W6747473740","https://openalex.org/W6755069753","https://openalex.org/W6766952794","https://openalex.org/W6767434776","https://openalex.org/W6769596995","https://openalex.org/W6771753067","https://openalex.org/W6771876938","https://openalex.org/W6775647304","https://openalex.org/W6777944346","https://openalex.org/W6780089238","https://openalex.org/W6786571078","https://openalex.org/W6796233699","https://openalex.org/W6803156713","https://openalex.org/W6811282592","https://openalex.org/W6844082324","https://openalex.org/W6853073828","https://openalex.org/W6853242963","https://openalex.org/W6868720813","https://openalex.org/W6979294194","https://openalex.org/W7009022386","https://openalex.org/W7029270301"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4391375266","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","https://openalex.org/W2145821588"],"abstract_inverted_index":{"Multi-objective":[0],"reinforcement":[1],"learning":[2],"(MORL)":[3],"has":[4],"shown":[5],"great":[6],"promise":[7],"in":[8,62,95],"many":[9],"real-world":[10],"applications.":[11],"Existing":[12],"MORL":[13,214],"algorithms":[14,211],"often":[15,40],"aim":[16],"to":[17,101,168,191],"learn":[18],"a":[19,28,63,74,103,119,126,140,156,197],"policy":[20,148],"that":[21,51,107,136,185],"optimizes":[22],"individual":[23],"objective":[24,96],"functions":[25],"simultaneously":[26],"with":[27,54,196,216],"given":[29],"prior":[30],"preference":[31],"(or":[32],"weights)":[33],"on":[34,66,203],"different":[35],"objectives.":[36,68],"However,":[37],"these":[38],"methods":[39,215],"suffer":[41],"from":[42],"the":[43,52,58,109,166,169,177,188,206],"issue":[44],"of":[45,85,209],"<italic":[46],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[47,144,151,160,174,193],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">gradient":[48],"conflict</i>":[49],"such":[50],"objectives":[53],"larger":[55],"gradients":[56],"dominate":[57],"update":[59,105],"direction,":[60],"resulting":[61],"performance":[64,208],"degeneration":[65],"other":[67],"In":[69],"this":[70],"paper,":[71],"we":[72],"develop":[73],"novel":[75],"dynamic":[76],"weighting":[77],"multi-objective":[78],"actor-critic":[79],"algorithm":[80],"(MOAC)":[81],"under":[82],"two":[83],"options":[84],"sub-procedures":[86],"named":[87],"as":[88,165],"conflict-avoidant":[89],"(CA)":[90],"and":[91,115],"faster":[92,121],"convergence":[93,122,129],"(FC)":[94],"weight":[97],"updates.":[98],"MOAC-CA":[99,137],"aims":[100],"find":[102,139],"CA":[104,162,170,199],"direction":[106],"maximizes":[108],"minimum":[110],"value":[111],"improvement":[112],"among":[113],"objectives,":[114],"MOAC-FC":[116,186],"targets":[117],"at":[118],"much":[120],"rate.":[123],"We":[124,134],"provide":[125],"comprehensive":[127],"finite-time":[128],"analysis":[130,182],"for":[131],"both":[132],"algorithms.":[133],"show":[135],"can":[138],"\u03f5":[141],"+":[142],"\u03f5<sub":[143,173],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">app</sub>-accurate":[145],"Pareto":[146],"stationary":[147],"using":[149],"O(\u03f5<sup":[150,192],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">\u22125</sup>)":[152],"samples,":[153],"while":[154],"ensuring":[155],"small":[157],"\u03f5+":[158],"\u221a\u03f5<sub":[159],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">app</sub>-level":[161],"distance":[163,167],"(defined":[164],"direction),":[171],"where":[172],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">app</sub>":[175],"is":[176],"function":[178],"approximation":[179],"error.":[180],"The":[181],"also":[183],"shows":[184],"improves":[187],"sample":[189],"complexity":[190],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">\u22123</sup>),":[194],"but":[195],"constant-level":[198],"distance.":[200],"Our":[201],"experiments":[202],"MT10":[204],"demonstrate":[205],"improved":[207],"our":[210],"over":[212],"existing":[213],"fixed":[217],"preference.":[218]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}