{"id":"https://openalex.org/W4394994771","doi":"https://doi.org/10.1109/tnnls.2024.3387397","title":"SATF: A Scalable Attentive Transfer Framework for Efficient Multiagent Reinforcement Learning","display_name":"SATF: A Scalable Attentive Transfer Framework for Efficient Multiagent Reinforcement Learning","publication_year":2024,"publication_date":"2024-04-22","ids":{"openalex":"https://openalex.org/W4394994771","doi":"https://doi.org/10.1109/tnnls.2024.3387397","pmid":"https://pubmed.ncbi.nlm.nih.gov/38648131"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3387397","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3387397","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/A5091983087","display_name":"Bin Chen","orcid":"https://orcid.org/0000-0002-5239-596X"},"institutions":[{"id":"https://openalex.org/I170239107","display_name":"University of South Australia","ror":"https://ror.org/01p93h210","country_code":"AU","type":"education","lineage":["https://openalex.org/I170239107"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Bin Chen","raw_affiliation_strings":["STEM, University of South Australia, Adelaide, SA, Australia"],"affiliations":[{"raw_affiliation_string":"STEM, University of South Australia, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I170239107"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007077356","display_name":"Zehong Cao","orcid":"https://orcid.org/0000-0003-3656-0328"},"institutions":[{"id":"https://openalex.org/I170239107","display_name":"University of South Australia","ror":"https://ror.org/01p93h210","country_code":"AU","type":"education","lineage":["https://openalex.org/I170239107"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zehong Cao","raw_affiliation_strings":["STEM, University of South Australia, Adelaide, SA, Australia"],"affiliations":[{"raw_affiliation_string":"STEM, University of South Australia, Adelaide, SA, Australia","institution_ids":["https://openalex.org/I170239107"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029548157","display_name":"Quan Bai","orcid":"https://orcid.org/0000-0003-1214-6317"},"institutions":[{"id":"https://openalex.org/I129801699","display_name":"University of Tasmania","ror":"https://ror.org/01nfmeh72","country_code":"AU","type":"education","lineage":["https://openalex.org/I129801699"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Quan Bai","raw_affiliation_strings":["School of ICT, University of Tasmania, Hobart, TAS, Australia"],"affiliations":[{"raw_affiliation_string":"School of ICT, University of Tasmania, Hobart, TAS, Australia","institution_ids":["https://openalex.org/I129801699"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091983087"],"corresponding_institution_ids":["https://openalex.org/I170239107"],"apc_list":null,"apc_paid":null,"fwci":1.3901,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.83290529,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"36","issue":"4","first_page":"6627","last_page":"6641"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9958000183105469,"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":0.9958000183105469,"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":0.8216413855552673},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6858208179473877},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6813136339187622},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6040337681770325},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5167931318283081},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.417180597782135},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10956078767776489},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.03468829393386841}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8216413855552673},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6858208179473877},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6813136339187622},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6040337681770325},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5167931318283081},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.417180597782135},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10956078767776489},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.03468829393386841},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3387397","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3387397","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:38648131","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38648131","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1641379095","https://openalex.org/W1992222410","https://openalex.org/W2149347032","https://openalex.org/W2165698076","https://openalex.org/W2617547828","https://openalex.org/W2747213132","https://openalex.org/W2769567824","https://openalex.org/W2788862220","https://openalex.org/W2889326414","https://openalex.org/W2921955147","https://openalex.org/W2963390684","https://openalex.org/W2963890729","https://openalex.org/W2965163470","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W3022749764","https://openalex.org/W3107153805","https://openalex.org/W3153676008","https://openalex.org/W3156295478","https://openalex.org/W3193544356","https://openalex.org/W4206706211","https://openalex.org/W4212814156","https://openalex.org/W4246078117","https://openalex.org/W4283372584","https://openalex.org/W4308365139","https://openalex.org/W4309367642","https://openalex.org/W4321021823","https://openalex.org/W4366310810","https://openalex.org/W4367721858","https://openalex.org/W4383112908","https://openalex.org/W4385245566","https://openalex.org/W4386470330","https://openalex.org/W4386869541","https://openalex.org/W6629521478","https://openalex.org/W6692846177","https://openalex.org/W6712951187","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6743756900","https://openalex.org/W6752380930","https://openalex.org/W6758846586","https://openalex.org/W6762491519","https://openalex.org/W6766805167","https://openalex.org/W6767361173","https://openalex.org/W6775529125","https://openalex.org/W6780287401","https://openalex.org/W6781750019","https://openalex.org/W6784152626","https://openalex.org/W6802002411","https://openalex.org/W6840380725","https://openalex.org/W6847213728","https://openalex.org/W6862919653"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","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/W3123837699"],"abstract_inverted_index":{"It":[0],"is":[1],"challenging":[2],"to":[3,69,76,115,148,164,185,196],"train":[4],"an":[5],"efficient":[6,43],"learning":[7,12],"procedure":[8],"with":[9,104,121,168],"multiagent":[10,29],"reinforcement":[11],"(MARL)":[13],"when":[14,188],"the":[15,21,82,85,95,117,127,132,135,158,165,190,204,209],"number":[16,65,72,191],"of":[17,66,73,84,93,183,192,200,211],"agents":[18,67,74,193],"increases":[19],"as":[20,109],"observation":[22,111],"space":[23],"exponentially":[24],"expands,":[25],"especially":[26],"in":[27,52,143,214],"large-scale":[28,215],"systems.":[30],"In":[31],"this":[32],"article,":[33],"we":[34],"proposed":[35,96],"a":[36,63,70,99,105,179],"scalable":[37],"attentive":[38],"transfer":[39],"framework":[40],"(SATF)":[41],"for":[42,207],"MARL,":[44],"which":[45],"achieved":[46],"goals":[47],"faster":[48],"and":[49,54,80,141],"more":[50],"accurately":[51],"homogeneous":[53],"heterogeneous":[55],"combat":[56,217],"tasks":[57],"by":[58,90,173],"transferring":[59],"learned":[60],"knowledge":[61],"from":[62,146,194],"small":[64],"(4)":[68],"large":[71],"(up":[75],"64).":[77],"To":[78],"reduce":[79],"align":[81],"dimensionality":[83],"observed":[86,119],"state":[87,101],"variations":[88],"caused":[89],"increasing":[91,189],"numbers":[92],"agents,":[94],"SATF":[97,133,159],"deployed":[98],"novel":[100],"representation":[102,112],"network":[103,113],"self-attention":[106],"mechanism,":[107],"known":[108],"dynamic":[110],"(DorNet),":[114],"extract":[116],"dominant":[118],"information":[120],"excellent":[122],"cost-effectiveness.":[123],"The":[124,151,198],"experiments":[125,152],"on":[126,153],"MAgent":[128],"platform":[129],"showed":[130,156,203],"that":[131,157],"outperformed":[134],"distributed":[136],"MARL":[137,171,212],"(independent":[138],"Q-learning":[139],"(IQL)":[140],"A2C)":[142],"task":[144],"sequences":[145],"8":[147],"64":[149],"agents.":[150],"StarCraft":[154],"II":[155],"demonstrated":[160],"superior":[161],"performance":[162],"relative":[163],"centralized":[166],"training":[167,176,213],"decentralized":[169],"execution":[170],"(QMIX)":[172],"presenting":[174],"shorter":[175],"steps,":[177],"achieving":[178],"desired":[180],"win":[181],"rate":[182],"up":[184],"approximately":[186],"90%":[187],"4":[195],"32.":[197],"findings":[199],"our":[201],"study":[202],"great":[205],"potential":[206],"enhancing":[208],"efficiency":[210],"agent":[216],"missions.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}