{"id":"https://openalex.org/W7154153368","doi":"https://doi.org/10.1109/tpami.2026.3683517","title":"Enhancing Value Decomposition With Target Transformation in Cooperative Multi-Agent Reinforcement Learning","display_name":"Enhancing Value Decomposition With Target Transformation in Cooperative Multi-Agent Reinforcement Learning","publication_year":2026,"publication_date":"2026-04-13","ids":{"openalex":"https://openalex.org/W7154153368","doi":"https://doi.org/10.1109/tpami.2026.3683517","pmid":"https://pubmed.ncbi.nlm.nih.gov/41973590"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3683517","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3683517","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","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/A5133519147","display_name":"Zeyang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyang Liu","raw_affiliation_strings":["Xi\u2019an Jiaotong University"],"raw_orcid":"https://orcid.org/0000-0002-3110-8618","affiliations":[{"raw_affiliation_string":"Xi\u2019an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133528130","display_name":"Lipeng Wan","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lipeng Wan","raw_affiliation_strings":["Xi\u2019an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi\u2019an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113924966","display_name":"Shiguang Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiguang Sun","raw_affiliation_strings":["Xi\u2019an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi\u2019an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042809978","display_name":"Xue Sui","orcid":"https://orcid.org/0000-0002-4746-764X"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xue Sui","raw_affiliation_strings":["Xi\u2019an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi\u2019an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330050","display_name":"Xi Chen","orcid":"https://orcid.org/0000-0003-4221-4288"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyu Chen","raw_affiliation_strings":["Xi\u2019an Jiaotong University"],"raw_orcid":"https://orcid.org/0000-0002-5226-963X","affiliations":[{"raw_affiliation_string":"Xi\u2019an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133519488","display_name":"Xuguang Lan","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuguang Lan","raw_affiliation_strings":["Xi\u2019an Jiaotong University"],"raw_orcid":"https://orcid.org/0000-0002-3422-944X","affiliations":[{"raw_affiliation_string":"Xi\u2019an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101623346","display_name":"Na Zheng","orcid":"https://orcid.org/0000-0001-5213-2345"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nanning Zheng","raw_affiliation_strings":["Xi\u2019an Jiaotong University"],"raw_orcid":"https://orcid.org/0000-0003-1608-8257","affiliations":[{"raw_affiliation_string":"Xi\u2019an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35313855,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"9","first_page":"10299","last_page":"10315"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5092999935150146,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5092999935150146,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.07109999656677246,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.015300000086426735,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.5684000253677368},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4779999852180481},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.46639999747276306},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.40450000762939453},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3319000005722046},{"id":"https://openalex.org/keywords/singular-value-decomposition","display_name":"Singular value decomposition","score":0.2809000015258789}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6401000022888184},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5828999876976013},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5684000253677368},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4779999852180481},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.46639999747276306},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.40450000762939453},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3725999891757965},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36550000309944153},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3319000005722046},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3296000063419342},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25690001249313354},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.2526000142097473}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2026.3683517","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3683517","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41973590","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41973590","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 pattern analysis and machine intelligence","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1066177181","display_name":null,"funder_award_id":"2025SYSSYSZD-083","funder_id":"https://openalex.org/F4320324173","funder_display_name":"Natural Science Foundation of Shaanxi Province"},{"id":"https://openalex.org/G8180423952","display_name":null,"funder_award_id":"62125305","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"},{"id":"https://openalex.org/F4320324173","display_name":"Natural Science Foundation of Shaanxi Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2108892923","https://openalex.org/W2166533447","https://openalex.org/W2292533394","https://openalex.org/W2617547828","https://openalex.org/W2747213132","https://openalex.org/W2807741983","https://openalex.org/W2912471136","https://openalex.org/W2913662073","https://openalex.org/W3005761304","https://openalex.org/W3021959079","https://openalex.org/W3116982717","https://openalex.org/W3173211893","https://openalex.org/W3173782550","https://openalex.org/W3212907084","https://openalex.org/W4214712602","https://openalex.org/W4283789768","https://openalex.org/W4323851615","https://openalex.org/W4366957200","https://openalex.org/W4382202546","https://openalex.org/W4382202881","https://openalex.org/W7133193803","https://openalex.org/W7133222302","https://openalex.org/W7133226216","https://openalex.org/W7133238541","https://openalex.org/W7133246398"],"related_works":[],"abstract_inverted_index":{"The":[0],"increasing":[1],"need":[2],"for":[3],"cooperation":[4],"among":[5],"intelligent":[6],"machines":[7],"has":[8],"heightened":[9],"the":[10,38,90],"importance":[11],"of":[12,22,41],"cooperative":[13,23,122],"multi-agent":[14],"reinforcement":[15],"learning":[16,48,82],"(MARL).":[17],"However,":[18,44],"a":[19,85,115],"dominant":[20],"class":[21,40],"MARL":[24,123],"approaches":[25],"relies":[26],"on":[27,95,120],"monotonic":[28],"value":[29],"decomposition,":[30],"which":[31,53,77],"enables":[32],"scalable":[33],"decentralized":[34],"execution":[35],"but":[36,66],"restricts":[37],"representable":[39],"joint":[42,92],"action-values.":[43],"existing":[45],"remedies":[46],"bias":[47],"targets":[49,83],"toward":[50],"high-value":[51],"samples,":[52],"can":[54],"be":[55],"fragile":[56],"under":[57],"stochastic":[58,81],"returns":[59],"because":[60],"optimistic":[61],"emphasis":[62],"may":[63],"amplify":[64],"lucky":[65],"suboptimal":[67],"trajectories.":[68],"To":[69],"solve":[70],"this":[71,96],"challenge,":[72],"we":[73,98],"propose":[74],"Target":[75,101],"Transformation,":[76],"maps":[78],"non-monotonic":[79],"and":[80,106,131,141],"into":[84],"monotonic-representable":[86],"surrogate":[87],"while":[88],"preserving":[89],"optimal":[91],"action.":[93],"Building":[94],"idea,":[97],"develop":[99],"Uncertainty-aware":[100],"Transformation":[102],"(UT2)":[103],"with":[104,114,136],"value-based":[105],"policy-based":[107],"instantiations":[108],"that":[109,126],"combine":[110],"an":[111],"uncertainty":[112],"estimator":[113],"best-individual":[116],"coordination":[117],"envelope.":[118],"Experiments":[119],"diverse":[121],"benchmarks":[124],"show":[125],"UT2":[127],"improves":[128],"both":[129],"performance":[130],"stability":[132],"over":[133],"strong":[134],"baselines,":[135],"larger":[137],"gains":[138],"as":[139],"non-monotonicity":[140],"stochasticity":[142],"increase.":[143]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-04-14T00:00:00"}