{"id":"https://openalex.org/W3091909253","doi":"https://doi.org/10.1109/case48305.2020.9216877","title":"A Soft Graph Attention Reinforcement Learning for Multi-Agent Cooperation","display_name":"A Soft Graph Attention Reinforcement Learning for Multi-Agent Cooperation","publication_year":2020,"publication_date":"2020-08-01","ids":{"openalex":"https://openalex.org/W3091909253","doi":"https://doi.org/10.1109/case48305.2020.9216877","mag":"3091909253"},"language":"en","primary_location":{"id":"doi:10.1109/case48305.2020.9216877","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case48305.2020.9216877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5075244395","display_name":"Huimu Wang","orcid":"https://orcid.org/0000-0001-7115-8831"},"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/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/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"]},{"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":"Huimu Wang","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Automation, Beijing, China","Scholl of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Automation, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Scholl 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/A5060319097","display_name":"Zhiqiang Pu","orcid":"https://orcid.org/0000-0002-4841-4048"},"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/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/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"]},{"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":"Zhiqiang Pu","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Automation, Beijing, China","Scholl of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Automation, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Scholl 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/A5100412085","display_name":"Zhen Liu","orcid":"https://orcid.org/0000-0003-1610-2338"},"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":"Zhen Liu","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Automation, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Automation, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019541846","display_name":"Jianqiang Yi","orcid":"https://orcid.org/0000-0003-3268-9482"},"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/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/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"]},{"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":"Jianqiang Yi","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Automation, Beijing, China","Scholl of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Automation, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"Scholl 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/A5043281824","display_name":"Tenghai Qiu","orcid":"https://orcid.org/0000-0002-0312-5728"},"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":"Tenghai Qiu","raw_affiliation_strings":["Chinese Academy of Sciences, Institute of Automation, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences, Institute of Automation, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9670000076293945,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9595999717712402,"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":0.84879469871521},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7921875715255737},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.6023165583610535},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5098311305046082},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.423678994178772},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3317716717720032}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.84879469871521},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7921875715255737},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.6023165583610535},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5098311305046082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.423678994178772},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3317716717720032}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/case48305.2020.9216877","is_oa":false,"landing_page_url":"https://doi.org/10.1109/case48305.2020.9216877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W1771410628","https://openalex.org/W2145339207","https://openalex.org/W2173248099","https://openalex.org/W2257979135","https://openalex.org/W2311051510","https://openalex.org/W2617547828","https://openalex.org/W2726187156","https://openalex.org/W2736601468","https://openalex.org/W2785315072","https://openalex.org/W2803155336","https://openalex.org/W2894976951","https://openalex.org/W2896451037","https://openalex.org/W2903006607","https://openalex.org/W2920426271","https://openalex.org/W2948342290","https://openalex.org/W2949794851","https://openalex.org/W2962938168","https://openalex.org/W2962966033","https://openalex.org/W2963039558","https://openalex.org/W2963403868","https://openalex.org/W2963407617","https://openalex.org/W2963588154","https://openalex.org/W2963858333","https://openalex.org/W2963864421","https://openalex.org/W2982316857","https://openalex.org/W4288336223","https://openalex.org/W4289363497","https://openalex.org/W4297733535","https://openalex.org/W4299802797","https://openalex.org/W4385245566","https://openalex.org/W6638018090","https://openalex.org/W6684921986","https://openalex.org/W6738796088","https://openalex.org/W6739901393","https://openalex.org/W6740222838","https://openalex.org/W6741002519","https://openalex.org/W6747941106","https://openalex.org/W6751139674","https://openalex.org/W6755069753","https://openalex.org/W6755542948","https://openalex.org/W6755662481","https://openalex.org/W6756851941","https://openalex.org/W6760783655","https://openalex.org/W6763173156"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435","https://openalex.org/W20361778"],"abstract_inverted_index":{"The":[0,158],"multi-agent":[1],"reinforcement":[2,70],"learning":[3,71],"(MARL)":[4],"suffers":[5],"from":[6],"several":[7],"issues":[8],"when":[9],"it":[10],"is":[11,22,73,131],"applied":[12],"to":[13,46,57,105,133,147],"large-scale":[14,39,156,177],"environments.":[15,157,178],"Specifically,":[16],"the":[17,20,25,31,34,51,77,80,94,97,101,107,111,122,149,161,165],"communication":[18,26,98],"among":[19,33,110],"agents":[21,35,53,166],"limited":[23],"by":[24],"distance":[27],"or":[28],"bandwidth.":[29],"Besides,":[30],"interactions":[32],"are":[36],"complex":[37],"in":[38,176],"environments,":[40],"which":[41,119,139],"makes":[42],"each":[43,135,142],"agent":[44,143],"hard":[45],"take":[47],"different":[48],"influences":[49],"of":[50,79,84,96,160],"other":[52,150],"into":[54,124],"consideration":[55,125],"and":[56,99,170],"learn":[58,134,145,168],"a":[59,66,127],"stable":[60,169],"policy.":[61],"To":[62],"address":[63],"these":[64],"issues,":[65],"soft":[67,128],"graph":[68,85,89],"attention":[69,117,129,136],"(SGA-RL)":[72],"proposed.":[74],"By":[75],"taking":[76],"advantage":[78],"chain":[81],"propagation":[82],"characteristics":[83],"neural":[86],"networks,":[87],"stacked":[88],"convolution":[90],"layers":[91],"can":[92,144,167],"overcome":[93],"limitation":[95],"enlarge":[100],"agents'":[102,151],"receptive":[103],"field":[104],"promote":[106],"cooperation":[108],"behavior":[109],"agents.":[112],"Moreover,":[113],"unlike":[114],"traditional":[115],"multi-head":[116],"mechanism":[118,130],"takes":[120],"all":[121],"heads":[123],"equally,":[126],"designed":[132],"head's":[137],"importance,":[138],"means":[140],"that":[141,164],"how":[146],"treat":[148],"influence":[152],"more":[153],"effectively":[154],"during":[155],"results":[159],"simulations":[162],"indicate":[163],"complicated":[171],"cooperative":[172],"strategies":[173],"with":[174],"SGA-RL":[175]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}