{"id":"https://openalex.org/W4403919320","doi":"https://doi.org/10.1109/tnnls.2024.3475216","title":"Multi-Task Multi-Agent Reinforcement Learning With Interaction and Task Representations","display_name":"Multi-Task Multi-Agent Reinforcement Learning With Interaction and Task Representations","publication_year":2024,"publication_date":"2024-10-30","ids":{"openalex":"https://openalex.org/W4403919320","doi":"https://doi.org/10.1109/tnnls.2024.3475216","pmid":"https://pubmed.ncbi.nlm.nih.gov/39475745"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3475216","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3475216","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/A5100323308","display_name":"Chao Li","orcid":"https://orcid.org/0009-0005-5499-4965"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Li","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0005-5499-4965","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shaokang Dong","orcid":"https://orcid.org/0000-0002-8493-1501"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaokang Dong","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-8493-1501","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100764370","display_name":"Shangdong Yang","orcid":"https://orcid.org/0000-0001-5379-9539"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangdong Yang","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-5379-9539","affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018405065","display_name":"Yujing Hu","orcid":"https://orcid.org/0000-0002-2714-0092"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujing Hu","raw_affiliation_strings":["NetEase Fuxi AI Lab, NetEase Inc., Hangzhou, China","NetEase Fuxi AI Lab, NetEase Inc, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Fuxi AI Lab, NetEase Inc., Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"NetEase Fuxi AI Lab, NetEase Inc, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103030122","display_name":"Tianyu Ding","orcid":"https://orcid.org/0000-0001-8445-4330"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianyu Ding","raw_affiliation_strings":["Applied Sciences Group, Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0001-8445-4330","affiliations":[{"raw_affiliation_string":"Applied Sciences Group, Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100462996","display_name":"Wenbin Li","orcid":"https://orcid.org/0000-0002-0935-7124"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbin Li","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-0935-7124","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yang Gao","orcid":"https://orcid.org/0000-0002-2488-1813"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Gao","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-2488-1813","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5006,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.9079821,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"36","issue":"7","first_page":"13431","last_page":"13445"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5806000232696533,"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":0.5806000232696533,"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":0.5454999804496765,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7566319704055786},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6947362422943115},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5689294934272766},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5178504586219788},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.48106956481933594},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25199538469314575},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.24142563343048096},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.10960686206817627},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09810790419578552}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7566319704055786},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6947362422943115},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5689294934272766},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5178504586219788},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.48106956481933594},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25199538469314575},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.24142563343048096},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.10960686206817627},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09810790419578552},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3475216","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3475216","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:39475745","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39475745","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":0.4099999964237213,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G2339888215","display_name":null,"funder_award_id":"62106100","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2767813700","display_name":null,"funder_award_id":"62192783","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5929282161","display_name":null,"funder_award_id":"2021ZD0113303","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G7153191022","display_name":null,"funder_award_id":"BK20221441","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G7334411499","display_name":null,"funder_award_id":"62206133","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/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1641379095","https://openalex.org/W2012812921","https://openalex.org/W2487898712","https://openalex.org/W2602275733","https://openalex.org/W2617547828","https://openalex.org/W2768629321","https://openalex.org/W2907492528","https://openalex.org/W2972122474","https://openalex.org/W2997536466","https://openalex.org/W3003498399","https://openalex.org/W3033770108","https://openalex.org/W3036329728","https://openalex.org/W3108439758","https://openalex.org/W3110102330","https://openalex.org/W3141797743","https://openalex.org/W3153573172","https://openalex.org/W3173211893","https://openalex.org/W3174406242","https://openalex.org/W3211700439","https://openalex.org/W4211220176","https://openalex.org/W4385245566","https://openalex.org/W4389473504","https://openalex.org/W6674600207","https://openalex.org/W6736572398","https://openalex.org/W6738796088","https://openalex.org/W6740879895","https://openalex.org/W6741002519","https://openalex.org/W6749304979","https://openalex.org/W6752380930","https://openalex.org/W6758846586","https://openalex.org/W6762491519","https://openalex.org/W6771904302","https://openalex.org/W6775529125","https://openalex.org/W6779101081","https://openalex.org/W6781750019","https://openalex.org/W6784778700","https://openalex.org/W6789172296","https://openalex.org/W6791079441","https://openalex.org/W6802732210","https://openalex.org/W6838682728","https://openalex.org/W6840380725"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W3196817267","https://openalex.org/W1976600725"],"abstract_inverted_index":{"Multi-task":[0],"multi-agent":[1,53,159],"reinforcement":[2],"learning":[3,30],"(MT-MARL)":[4],"is":[5],"capable":[6],"of":[7,116,154],"leveraging":[8],"useful":[9],"knowledge":[10,156],"across":[11,157],"multiple":[12,176],"related":[13],"tasks":[14,54],"to":[15,98],"improve":[16],"performance":[17,186],"on":[18,33,133],"any":[19],"single":[20],"task.":[21],"While":[22],"recent":[23],"studies":[24],"have":[25],"tentatively":[26],"achieved":[27],"this":[28,63,65],"by":[29,46],"independent":[31],"policies":[32],"a":[34,73,147],"shared":[35],"representation":[36],"space,":[37],"we":[38,128],"pinpoint":[39],"that":[40,77,111],"further":[41],"advancements":[42],"can":[43],"be":[44],"realized":[45],"explicitly":[47,99],"characterizing":[48,89],"agent":[49,81,90,118,125],"interactions":[50,82],"within":[51],"these":[52],"and":[55,70,83,141,183,190],"identifying":[56],"task":[57,85,130,139,144],"relations":[58],"for":[59,88,167],"selective":[60],"reuse.":[61],"To":[62],"end,":[64],"article":[66],"proposes":[67],"Representing":[68],"Interactions":[69],"Tasks":[71],"(RIT),":[72],"novel":[74],"MT-MARL":[75],"algorithm":[76],"characterizes":[78],"both":[79,188],"intra-task":[80],"inter-task":[84],"relations.":[86,145],"Specifically,":[87],"interactions,":[91],"RIT":[92,149,162,174],"presents":[93],"the":[94,101,112,151],"interactive":[95],"value":[96,115],"decomposition":[97],"take":[100],"dependency":[102],"among":[103],"agents":[104],"into":[105],"policy":[106,165,170],"learning.":[107,171],"Theoretical":[108],"analysis":[109],"demonstrates":[110,193],"learned":[113],"utility":[114],"each":[117],"approximates":[119],"its":[120,184,194],"Shapley":[121],"value,":[122],"thus":[123],"representing":[124],"interactions.":[126],"Moreover,":[127],"learn":[129],"representations":[131],"based":[132],"per-agent":[134],"local":[135],"trajectories,":[136],"which":[137],"assess":[138],"similarities":[140],"accordingly":[142],"identify":[143],"As":[146],"result,":[148],"facilitates":[150],"effective":[152],"transfer":[153],"interaction":[155],"similar":[158],"tasks.":[160],"Structurally,":[161],"develops":[163],"universal":[164],"structure":[166],"scalable":[168],"multi-task":[169,189],"We":[172],"evaluate":[173],"against":[175],"state-of-the-art":[177],"baselines":[178],"in":[179],"various":[180],"cooperative":[181],"tasks,":[182],"significant":[185],"under":[187],"zero-shot":[191],"settings":[192],"effectiveness.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}