{"id":"https://openalex.org/W4407950249","doi":"https://doi.org/10.1109/tnnls.2025.3540758","title":"Meta Learning Task Representation in Multiagent Reinforcement Learning: From Global Inference to Local Inference","display_name":"Meta Learning Task Representation in Multiagent Reinforcement Learning: From Global Inference to Local Inference","publication_year":2025,"publication_date":"2025-02-26","ids":{"openalex":"https://openalex.org/W4407950249","doi":"https://doi.org/10.1109/tnnls.2025.3540758","pmid":"https://pubmed.ncbi.nlm.nih.gov/40031655"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3540758","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3540758","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/A5031316464","display_name":"Zijie Zhao","orcid":"https://orcid.org/0000-0001-7756-7046"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijie Zhao","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7756-7046","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103161416","display_name":"Yuqian Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqian Fu","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-9031-9889","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073383645","display_name":"Jiajun Chai","orcid":"https://orcid.org/0000-0002-7611-064X"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Chai","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7611-064X","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080193690","display_name":"Yuanheng Zhu","orcid":"https://orcid.org/0000-0001-5384-423X"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanheng Zhu","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5384-423X","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100624298","display_name":"Dongbin Zhao","orcid":"https://orcid.org/0000-0001-8218-9633"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbin Zhao","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8218-9633","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.376,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.97060088,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"36","issue":"8","first_page":"14908","last_page":"14921"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9932000041007996,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9908000230789185,"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":0.7909935712814331},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.756173849105835},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7268650531768799},{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.5956507921218872},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5310390591621399},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5031406283378601},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48909860849380493},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48839420080184937},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.46993690729141235},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44881361722946167}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7909935712814331},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.756173849105835},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7268650531768799},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.5956507921218872},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5310390591621399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5031406283378601},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48909860849380493},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48839420080184937},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.46993690729141235},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44881361722946167},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3540758","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3540758","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:40031655","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40031655","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/G1654400865","display_name":null,"funder_award_id":"XDA27030400","funder_id":"https://openalex.org/F4320326956","funder_display_name":"Chinese Research Academy of Environmental Sciences"},{"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/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/F4320326956","display_name":"Chinese Research Academy of Environmental Sciences","ror":"https://ror.org/05t8xvx87"},{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W2578206533","https://openalex.org/W2747213132","https://openalex.org/W2842511635","https://openalex.org/W2945020056","https://openalex.org/W3084241738","https://openalex.org/W3153573172","https://openalex.org/W3176624977","https://openalex.org/W3196869853","https://openalex.org/W3197671932","https://openalex.org/W3210013777","https://openalex.org/W4200632612","https://openalex.org/W4211024777","https://openalex.org/W4226323298","https://openalex.org/W4284888955","https://openalex.org/W4297808394","https://openalex.org/W4367663369","https://openalex.org/W4383899300","https://openalex.org/W4386470330","https://openalex.org/W4391919254","https://openalex.org/W4404293755","https://openalex.org/W4405521252","https://openalex.org/W6627932998","https://openalex.org/W6729906282","https://openalex.org/W6731982132","https://openalex.org/W6736057607","https://openalex.org/W6736572398","https://openalex.org/W6738796088","https://openalex.org/W6755477022","https://openalex.org/W6760698134","https://openalex.org/W6762796984","https://openalex.org/W6762959241","https://openalex.org/W6779101081","https://openalex.org/W6795908048","https://openalex.org/W6810655720","https://openalex.org/W6838225815","https://openalex.org/W6838836181","https://openalex.org/W6838838702","https://openalex.org/W6840380725","https://openalex.org/W6844225899"],"related_works":["https://openalex.org/W2046459260","https://openalex.org/W2967463586","https://openalex.org/W2074679142","https://openalex.org/W2765830098","https://openalex.org/W1971989957","https://openalex.org/W2517338020","https://openalex.org/W3157641275","https://openalex.org/W4312300846","https://openalex.org/W2104042711","https://openalex.org/W4206221578"],"abstract_inverted_index":{"Multiagent":[0],"meta":[1],"reinforcement":[2],"learning":[3],"(MAMRL)":[4],"enables":[5],"multiagent":[6],"systems":[7],"(MASs)":[8],"to":[9,11,63,89,122,166,169],"adapt":[10],"multiple":[12],"tasks.":[13],"However,":[14],"partial":[15],"observability":[16],"poses":[17],"a":[18,37,41,67,99,148,157],"significant":[19],"challenge":[20],"by":[21,103,133],"hindering":[22],"efficient":[23],"task":[24,69,76,91,112,164],"inference":[25],"from":[26],"agents'":[27],"limited":[28],"local":[29,75,115,131],"experiences.":[30],"To":[31],"address":[32],"this,":[33],"we":[34,117,155],"propose":[35],"MG2L,":[36],"novel":[38],"algorithm":[39],"featuring":[40],"global-to-local":[42],"(G2L)":[43],"training":[44,57,143],"scheme":[45,84,139],"based":[46],"on":[47,79],"mutual":[48],"information":[49],"optimization":[50],"(MIO).":[51],"We":[52],"first":[53],"extend":[54],"the":[55,82,96,105,108,111,124,130,163],"centralized":[56,100,142],"and":[58,65,74,110,181],"decentralized":[59,145],"execution":[60],"(CTDE)":[61],"framework":[62],"MAMRL,":[64],"introduce":[66],"multilevel":[68],"encoder":[70,165],"for":[71,151],"joint":[72],"global":[73,94,101],"inference.":[77],"Building":[78],"this":[80,135],"encoder,":[81],"MG2L":[83,138,188],"employs":[85],"tailored":[86],"loss":[87],"functions":[88],"optimize":[90],"representations.":[92],"For":[93,114],"inference,":[95,116],"MAS":[97],"learns":[98],"representation":[102,109,132],"maximizing":[104],"MI":[106,120],"between":[107],"context.":[113],"formulate":[118],"conditional":[119],"reduction":[121],"quantify":[123],"G2L":[125],"gap.":[126],"Agents":[127],"then":[128],"learn":[129],"minimizing":[134],"reduction.":[136],"The":[137,185],"effectively":[140],"harmonizes":[141],"with":[144],"execution,":[146],"offering":[147],"versatile":[149],"solution":[150],"MAMRL":[152],"challenges.":[153],"Additionally,":[154],"integrate":[156],"permutation-invariant":[158],"attention":[159],"(PIA)":[160],"module":[161],"into":[162],"reduce":[167],"sensitivity":[168],"behavior":[170],"policy":[171],"variations.":[172],"Extensive":[173],"experiments-including":[174],"comparative":[175],"analyses,":[176],"ablation":[177],"studies,":[178],"meta-test":[179],"evaluations,":[180],"visualizations-demonstrate":[182],"MG2L's":[183],"effectiveness.":[184],"implementation":[186],"of":[187],"is":[189],"publicly":[190],"available":[191],"at":[192],"https://github.com/zhaozijie2022/mg2l.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}