{"id":"https://openalex.org/W4402582372","doi":"https://doi.org/10.1109/tnnls.2024.3420791","title":"Efficient Communication via Self-Supervised Information Aggregation for Online and Offline Multiagent Reinforcement Learning","display_name":"Efficient Communication via Self-Supervised Information Aggregation for Online and Offline Multiagent Reinforcement Learning","publication_year":2024,"publication_date":"2024-09-16","ids":{"openalex":"https://openalex.org/W4402582372","doi":"https://doi.org/10.1109/tnnls.2024.3420791","pmid":"https://pubmed.ncbi.nlm.nih.gov/39283788"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3420791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3420791","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":"Cong Guan","orcid":"https://orcid.org/0000-0002-5198-9141"},"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":"Cong Guan","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology and the School of Artificial Intelligence, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-5198-9141","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology and the School of Artificial Intelligence, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102969813","display_name":"Feng Chen","orcid":"https://orcid.org/0009-0003-8164-3410"},"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":"Feng Chen","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology and the School of Artificial Intelligence, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0003-8164-3410","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology and the School of Artificial Intelligence, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lei Yuan","orcid":"https://orcid.org/0000-0002-7803-0766"},"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":"Lei Yuan","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology and the School of Artificial Intelligence, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-7803-0766","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology and the School of Artificial Intelligence, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035138959","display_name":"Zongzhang Zhang","orcid":"https://orcid.org/0000-0002-9238-4747"},"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":"Zongzhang Zhang","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology and the School of Artificial Intelligence, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-9238-4747","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology and the School of Artificial Intelligence, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yang Yu","orcid":"https://orcid.org/0000-0002-1052-5447"},"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 Yu","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology and the School of Artificial Intelligence, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-1052-5447","affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology and the School of Artificial Intelligence, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":2.2228,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.89494278,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"36","issue":"5","first_page":"9044","last_page":"9056"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8913000226020813,"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":0.8913000226020813,"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/T10702","display_name":"Insect and Arachnid Ecology and Behavior","score":0.8335000276565552,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8264589309692383},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8039020299911499},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4963284134864807},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.4636557996273041},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.4411375820636749},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.4314185380935669},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4298044443130493},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.418337881565094},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4078259766101837},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3597038686275482},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3487066626548767},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.11052098870277405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8264589309692383},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8039020299911499},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4963284134864807},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.4636557996273041},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.4411375820636749},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.4314185380935669},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4298044443130493},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.418337881565094},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4078259766101837},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3597038686275482},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3487066626548767},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.11052098870277405},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3420791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3420791","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:39283788","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39283788","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":[{"display_name":"Peace, Justice and strong institutions","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G3091702697","display_name":null,"funder_award_id":"61876119","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4366907579","display_name":null,"funder_award_id":"2020AAA0107200","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G528746023","display_name":null,"funder_award_id":"61921006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6406246630","display_name":null,"funder_award_id":"62276126","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2292533394","https://openalex.org/W2617547828","https://openalex.org/W2747213132","https://openalex.org/W2991046523","https://openalex.org/W2998489261","https://openalex.org/W3106649810","https://openalex.org/W3119097918","https://openalex.org/W3200561352","https://openalex.org/W3210169707","https://openalex.org/W4313291205","https://openalex.org/W4360584316","https://openalex.org/W4382202976","https://openalex.org/W4386470330","https://openalex.org/W4387171915","https://openalex.org/W6677939520","https://openalex.org/W6712181171","https://openalex.org/W6713411898","https://openalex.org/W6749304979","https://openalex.org/W6752380930","https://openalex.org/W6755542948","https://openalex.org/W6767328439","https://openalex.org/W6768617876","https://openalex.org/W6769091550","https://openalex.org/W6770110395","https://openalex.org/W6776438516","https://openalex.org/W6776601253","https://openalex.org/W6779265984","https://openalex.org/W6779753894","https://openalex.org/W6780470247","https://openalex.org/W6781750019","https://openalex.org/W6784951334","https://openalex.org/W6792413377","https://openalex.org/W6796258226","https://openalex.org/W6796436736","https://openalex.org/W6796861069","https://openalex.org/W6796880758","https://openalex.org/W6802325372","https://openalex.org/W6804100093","https://openalex.org/W6810168854","https://openalex.org/W6838682728","https://openalex.org/W6852554612","https://openalex.org/W6859152455","https://openalex.org/W6859731961"],"related_works":["https://openalex.org/W2883256816","https://openalex.org/W2171408034","https://openalex.org/W3003320923","https://openalex.org/W2106140982","https://openalex.org/W2152313554","https://openalex.org/W2064303750","https://openalex.org/W1509300825","https://openalex.org/W3092582874","https://openalex.org/W2338718585","https://openalex.org/W4225619808"],"abstract_inverted_index":{"Utilizing":[0],"messages":[1,18,77,102],"from":[2,101],"teammates":[3,20],"can":[4,73],"improve":[5],"coordination":[6,55],"in":[7,42,56,112,169,182,197],"cooperative":[8,57],"multiagent":[9,152],"reinforcement":[10],"learning":[11,143],"(MARL).":[12],"Previous":[13],"works":[14],"typically":[15],"combine":[16],"raw":[17],"of":[19,125,141,166],"with":[21,81],"local":[22,87],"information":[23,111],"as":[24,158,185],"inputs":[25],"for":[26,35,53,129,144,151,188],"policy.":[27,88],"However,":[28],"neglecting":[29],"message":[30,49,94,134],"aggregation":[31,50],"poses":[32],"significant":[33],"inefficiency":[34],"policy":[36],"learning.":[37],"Motivated":[38],"by":[39,131],"recent":[40],"advances":[41],"representation":[43,100,128],"learning,":[44],"we":[45,62,90,147,159],"argue":[46],"that":[47],"efficient":[48],"is":[51,155],"essential":[52],"good":[54],"MARL.":[58],"In":[59],"this":[60,183,198],"article,":[61],"propose":[63],"Multiagent":[64],"communication":[65,189],"via":[66,106],"Self-supervised":[67],"Information":[68],"Aggregation":[69],"(MASIA),":[70],"where":[71],"agents":[72],"aggregate":[74],"the":[75,86,121,126,139,156,164,178],"received":[76],"into":[78],"compact":[79],"representations":[80],"high":[82],"relevance":[83],"to":[84,96,192],"augment":[85],"Specifically,":[89],"design":[91],"a":[92,113,132,186],"permutation-invariant":[93],"encoder":[95],"generate":[97],"common":[98],"information-aggregated":[99],"and":[103,108,172],"optimize":[104],"it":[105],"reconstructing":[107],"shooting":[109],"future":[110,195],"self-supervised":[114],"manner.":[115],"Hence,":[116],"each":[117],"agent":[118],"would":[119],"utilize":[120],"most":[122],"relevant":[123],"parts":[124],"aggregated":[127],"decision-making":[130],"novel":[133],"extraction":[135],"mechanism.":[136],"Furthermore,":[137],"considering":[138],"potential":[140],"offline":[142,149,173,180],"real-world":[145],"applications,":[146],"build":[148],"benchmarks":[150,181],"communication,":[153],"which":[154],"first":[157],"know.":[160],"Empirical":[161],"results":[162],"demonstrate":[163],"superiority":[165],"our":[167],"method":[168],"both":[170],"online":[171],"settings.":[174],"We":[175],"also":[176],"release":[177],"built":[179],"article":[184],"testbed":[187],"ability":[190],"validation":[191],"facilitate":[193],"further":[194],"research":[196],"direction.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}