{"id":"https://openalex.org/W4402673483","doi":"https://doi.org/10.1109/tnnls.2024.3455422","title":"TVDO: Tchebycheff Value-Decomposition Optimization for Multiagent Reinforcement Learning","display_name":"TVDO: Tchebycheff Value-Decomposition Optimization for Multiagent Reinforcement Learning","publication_year":2024,"publication_date":"2024-09-20","ids":{"openalex":"https://openalex.org/W4402673483","doi":"https://doi.org/10.1109/tnnls.2024.3455422","pmid":"https://pubmed.ncbi.nlm.nih.gov/39302794"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3455422","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3455422","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":null,"display_name":"Xiaoliang Hu","orcid":"https://orcid.org/0009-0004-0810-2324"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoliang Hu","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056265693","display_name":"Pengcheng Guo","orcid":"https://orcid.org/0000-0002-1249-2300"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Guo","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yadong Li","orcid":"https://orcid.org/0000-0003-0412-5858"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yadong Li","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412642","display_name":"Guangyu Li","orcid":"https://orcid.org/0000-0003-4817-0618"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyu Li","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhen Cui","orcid":"https://orcid.org/0000-0002-0543-4196"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Cui","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100726984","display_name":"Jian Yang","orcid":"https://orcid.org/0000-0003-4800-832X"},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Yang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36399199"],"apc_list":null,"apc_paid":null,"fwci":1.366,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.84316989,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"36","issue":"7","first_page":"12521","last_page":"12534"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.847599983215332,"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":0.847599983215332,"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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.7684999704360962,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T10524","display_name":"Traffic control and management","score":0.7563999891281128,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7810245752334595},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5077096223831177},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45464688539505005},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.43349123001098633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3776094913482666},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.19046568870544434},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.14214211702346802},{"id":"https://openalex.org/keywords/organic-chemistry","display_name":"Organic chemistry","score":0.049055248498916626}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7810245752334595},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5077096223831177},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45464688539505005},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.43349123001098633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3776094913482666},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.19046568870544434},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14214211702346802},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.049055248498916626}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3455422","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3455422","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:39302794","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39302794","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":[],"awards":[{"id":"https://openalex.org/G1200572148","display_name":null,"funder_award_id":"ZR2022LZH003","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G2287201929","display_name":null,"funder_award_id":"62476133","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7456927639","display_name":null,"funder_award_id":"62006119","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7791872048","display_name":null,"funder_award_id":"30919011232","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W2018375997","https://openalex.org/W2145339207","https://openalex.org/W2155345556","https://openalex.org/W2292533394","https://openalex.org/W2617547828","https://openalex.org/W2747213132","https://openalex.org/W2963658727","https://openalex.org/W2981038142","https://openalex.org/W2997502221","https://openalex.org/W3014891618","https://openalex.org/W3030840723","https://openalex.org/W3153787838","https://openalex.org/W3201284849","https://openalex.org/W4200635426","https://openalex.org/W4205501012","https://openalex.org/W4210870706","https://openalex.org/W4224036449","https://openalex.org/W4280586962","https://openalex.org/W4308365139","https://openalex.org/W4309367642","https://openalex.org/W4315489542","https://openalex.org/W6675811377","https://openalex.org/W6689424278","https://openalex.org/W6738796088","https://openalex.org/W6749032143","https://openalex.org/W6749304979","https://openalex.org/W6752380930","https://openalex.org/W6755069753","https://openalex.org/W6758846586","https://openalex.org/W6762491519","https://openalex.org/W6767327128","https://openalex.org/W6772005887","https://openalex.org/W6773620346","https://openalex.org/W6780768476","https://openalex.org/W6781750019","https://openalex.org/W6784152626","https://openalex.org/W6784178060","https://openalex.org/W6784341771","https://openalex.org/W6791043475","https://openalex.org/W6795908048","https://openalex.org/W6796258226","https://openalex.org/W6796991022"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109","https://openalex.org/W4362501864","https://openalex.org/W2001405890"],"abstract_inverted_index":{"In":[0,37,55],"cooperative":[1],"multiagent":[2,155],"reinforcement":[3],"learning":[4],"(MARL),":[5],"centralized":[6],"training":[7],"with":[8,102,142],"decentralized":[9],"execution":[10],"(CTDE)":[11],"has":[12],"recently":[13],"attracted":[14],"more":[15],"attention":[16],"due":[17],"to":[18,49,64],"the":[19,23,28,51,66,72,83,98,106,115,118,127,138,153],"physical":[20],"demand.":[21],"However,":[22],"most":[24],"dilemma":[25],"therein":[26],"is":[27,62,80],"inconsistency":[29],"between":[30,117],"jointly-trained":[31],"policies":[32],"and":[33,108,120,129,159],"individually":[34],"executed":[35],"actions.":[36],"this":[38],"article,":[39],"we":[40,132,149],"propose":[41],"a":[42,57,143,166],"factorized":[43,99],"Tchebycheff":[44,59,84,103],"value-decomposition":[45],"optimization":[46,88],"(TVDO)":[47],"method":[48,85],"overcome":[50],"trouble":[52],"of":[53,75,86,110,145],"inconsistency.":[54],"particular,":[56],"nonlinear":[58],"aggregation":[60,104],"function":[61],"formulated":[63],"realize":[65],"global":[67,119],"optimum":[68],"by":[69,82],"tightly":[70],"constraining":[71],"upper":[73],"bound":[74],"individual":[76,121],"action-value":[77,123],"bias,":[78],"which":[79,113],"inspired":[81],"multiobjective":[87],"(MOO).":[89],"We":[90],"theoretically":[91],"prove":[92],"that,":[93],"under":[94],"no":[95],"extra":[96],"limitations,":[97],"value":[100,140],"decomposition":[101,141],"satisfies":[105],"sufficiency":[107],"necessity":[109],"individual-global-max":[111],"(IGM),":[112],"guarantees":[114],"consistency":[116],"optimal":[122],"function.":[124],"Empirically,":[125],"in":[126,152],"climb":[128],"penalty":[130],"game,":[131],"verify":[133],"that":[134,163],"TVDO":[135,151,164],"precisely":[136],"expresses":[137],"global-to-individual":[139],"guarantee":[144],"policy":[146],"consistency.":[147],"Meanwhile,":[148],"evaluate":[150],"StarCraft":[154],"challenge":[156],"(SMAC)":[157],"benchmark,":[158],"extensive":[160],"experiments":[161],"demonstrate":[162],"achieves":[165],"significant":[167],"performance":[168],"superiority":[169],"over":[170],"some":[171],"SOTA":[172],"MARL":[173],"baselines.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}