{"id":"https://openalex.org/W4404576592","doi":"https://doi.org/10.1109/tase.2024.3501580","title":"Multi-Task Multi-Agent Reinforcement Learning With Task-Entity Transformers and Value Decomposition Training","display_name":"Multi-Task Multi-Agent Reinforcement Learning With Task-Entity Transformers and Value Decomposition Training","publication_year":2024,"publication_date":"2024-11-21","ids":{"openalex":"https://openalex.org/W4404576592","doi":"https://doi.org/10.1109/tase.2024.3501580"},"language":"en","primary_location":{"id":"doi:10.1109/tase.2024.3501580","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2024.3501580","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","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/A5080193690","display_name":"Yuanheng Zhu","orcid":"https://orcid.org/0000-0001-5384-423X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanheng Zhu","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5384-423X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113321025","display_name":"Shangjing Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangjing Huang","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-7764-0050","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Binbin Zuo","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binbin Zuo","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Dongbin Zhao","orcid":"https://orcid.org/0000-0001-8218-9633"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbin Zhao","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8218-9633","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Institute of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019248683","display_name":"Changyin Sun","orcid":"https://orcid.org/0000-0001-9269-334X"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changyin Sun","raw_affiliation_strings":["School of Artificial Intelligence, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-9269-334X","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.496,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.95027861,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"22","issue":null,"first_page":"9164","last_page":"9177"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.739799976348877,"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"}},"topics":[{"id":"https://openalex.org/T10328","display_name":"Supply Chain and Inventory Management","score":0.739799976348877,"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"}},{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.7085000276565552,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.677299976348877,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7264019250869751},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6597162485122681},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6512497663497925},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5821064710617065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5287125706672668},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4159994125366211},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35025209188461304},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.26530197262763977},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.15817978978157043},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.12348932027816772},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.10603067278862}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7264019250869751},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6597162485122681},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6512497663497925},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5821064710617065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5287125706672668},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4159994125366211},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35025209188461304},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.26530197262763977},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.15817978978157043},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.12348932027816772},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.10603067278862},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tase.2024.3501580","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tase.2024.3501580","pdf_url":null,"source":{"id":"https://openalex.org/S34881539","display_name":"IEEE Transactions on Automation Science and Engineering","issn_l":"1545-5955","issn":["1545-5955","1558-3783"],"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 Automation Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7285338662","display_name":null,"funder_award_id":"20240484514","funder_id":"https://openalex.org/F4320334978","funder_display_name":"Beijing Nova Program"},{"id":"https://openalex.org/G745626259","display_name":null,"funder_award_id":"62236002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7837090658","display_name":null,"funder_award_id":"4232056","funder_id":"https://openalex.org/F4320334977","funder_display_name":"Beijing Municipal Natural Science Foundation"},{"id":"https://openalex.org/G800914696","display_name":null,"funder_award_id":"62136008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8179479325","display_name":null,"funder_award_id":"62293541","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/F4320334977","display_name":"Beijing Municipal Natural Science Foundation","ror":null},{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2292533394","https://openalex.org/W2617547828","https://openalex.org/W2891076394","https://openalex.org/W2891177506","https://openalex.org/W2898567809","https://openalex.org/W3084241738","https://openalex.org/W3110979110","https://openalex.org/W3196869853","https://openalex.org/W3207544809","https://openalex.org/W3210169707","https://openalex.org/W3217091241","https://openalex.org/W4226033453","https://openalex.org/W4316467202","https://openalex.org/W4319996426","https://openalex.org/W4327571609","https://openalex.org/W4362590704","https://openalex.org/W4375929017","https://openalex.org/W4381733136","https://openalex.org/W4382239700","https://openalex.org/W4385010306","https://openalex.org/W4385245566","https://openalex.org/W4386470330","https://openalex.org/W4386869541","https://openalex.org/W4387142730","https://openalex.org/W4390970989","https://openalex.org/W4392477583","https://openalex.org/W4398188128","https://openalex.org/W6735650757","https://openalex.org/W6736572398","https://openalex.org/W6752380930","https://openalex.org/W6758846586","https://openalex.org/W6762491519","https://openalex.org/W6766805167","https://openalex.org/W6767552790","https://openalex.org/W6769596995","https://openalex.org/W6769627184","https://openalex.org/W6771876938","https://openalex.org/W6784778700","https://openalex.org/W6788165329","https://openalex.org/W6790190981","https://openalex.org/W6804391786","https://openalex.org/W6838682728","https://openalex.org/W6847224448","https://openalex.org/W6849134125","https://openalex.org/W6850300045","https://openalex.org/W6859539900"],"related_works":["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","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Multi-task":[0],"multi-agent":[1,220,353],"reinforcement":[2],"learning":[3,80,170,204],"aims":[4],"to":[5,9,71,82,107,132,216,226,230,250,284,330,348],"control":[6],"multiple":[7,13,124,227,252],"agents":[8,24,99],"perform":[10],"well":[11],"on":[12,176,183,212,307],"tasks.":[14,125,214,228,253,297,340],"It":[15],"encounters":[16],"three":[17],"core":[18],"challenges:":[19],"the":[20,27,36,135,140,156,159,163,169,258,269,286,291,303,309,323,357],"varying":[21,41,96],"number":[22],"of":[23,98,172,219,261,362],"and":[25,35,77,100,110,121,138,162,167,188,289,320,327,334,355],"entities,":[26,101],"disparities":[28],"in":[29,202,352,359],"cooperative":[30],"behaviors":[31],"among":[32,295],"different":[33,232,236,296,318],"tasks,":[34,76,237],"training":[37],"imbalance":[38],"caused":[39],"by":[40],"task":[42,65,79,111,153,174,178,287,304],"difficulty":[43],"levels.":[44],"To":[45,147],"address":[46],"these":[47],"issues,":[48],"we":[49,151],"propose":[50],"a":[51,129,281,360],"novel":[52],"framework":[53],"named":[54],"Task-Entity":[55,69,87],"Transformer":[56,70,88],"Qmix":[57],"(TETQmix),":[58],"which":[59,308],"employs":[60],"pretrained":[61],"language":[62,279,299],"models":[63,234,300],"for":[64,123,235,273,317,338],"encoding,":[66],"utilizes":[67],"proposed":[68,343],"handle":[72],"observations":[73],"across":[74],"various":[75],"adjusts":[78],"weights":[81],"achieve":[83,331],"balanced":[84],"multi-task":[85,93,149,203,274,350],"training.":[86,277],"not":[89,198],"only":[90,199],"enables":[91],"handling":[92],"scenarios":[94],"with":[95,193],"numbers":[97],"but":[102,206],"also":[103,207],"leverages":[104],"cross-attention":[105],"modules":[106],"integrate":[108],"observation":[109],"embeddings,":[112],"so":[113],"that":[114],"each":[115,173],"agent":[116],"can":[117,244,256,301,312],"obtain":[118],"individual":[119,136],"values":[120],"decisions":[122,324],"We":[126],"then":[127],"utilize":[128],"transformer-based":[130],"mixer":[131],"monotonically":[133],"combine":[134],"values,":[137],"train":[139],"whole":[141],"network\u2019s":[142],"parameters":[143],"using":[144],"temporal-difference":[145],"errors.":[146],"facilitate":[148],"training,":[150],"define":[152],"regret":[154],"as":[155],"difference":[157],"between":[158],"current-stage":[160],"return":[161],"candidate":[164],"best":[165],"one,":[166],"adjust":[168,313],"weight":[171],"based":[175,306],"its":[177,314],"regret.":[179],"Experiments":[180],"are":[181,271,346],"conducted":[182],"both":[184],"simulated":[185],"multi-particle":[186],"environments":[187],"real-world":[189],"multi-robot":[190],"systems.":[191],"Compared":[192,229],"existing":[194,326],"baselines,":[195],"our":[196,342],"method":[197],"is":[200,239],"superior":[201],"efficiency,":[205],"shows":[208],"promising":[209,332],"transfer":[210,336],"ability":[211],"unseen":[213,339],"Note":[215],"Practitioners\u2014The":[217],"flexibility":[218],"systems":[221,354],"makes":[222],"them":[223],"quite":[224],"fit":[225],"designing":[231],"decision":[233,248,275,310],"it":[238,255],"more":[240],"convenient":[241],"if":[242],"one":[243,247],"use":[245],"just":[246],"model":[249,276,311],"resolve":[251],"Besides,":[254],"make":[257],"maximum":[259],"utilization":[260],"trajectory":[262],"data":[263,270],"coming":[264],"from":[265,325],"similar":[266,328],"tasks":[267,319,329],"when":[268],"integrated":[272],"Natural":[278],"provides":[280],"powerful":[282],"tool":[283],"describe":[285],"context":[288],"emphasize":[290],"similarities":[292],"or":[293],"differences":[294],"Pretrained":[298],"encode":[302],"context,":[305],"output":[315],"distribution":[316],"even":[321],"synthesize":[322],"zero-shot":[333],"few-shot":[335],"performance":[337],"With":[341],"TETQmix,":[344],"practitioners":[345],"able":[347],"realize":[349],"capability":[351],"increase":[356],"generalization":[358],"variety":[361],"scenarios.":[363]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":7}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}