{"id":"https://openalex.org/W4385488845","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191136","title":"Learning Cooperative Policies with Graph Networks in Distributed Swarm Systems","display_name":"Learning Cooperative Policies with Graph Networks in Distributed Swarm Systems","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385488845","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191136"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","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/A5074422885","display_name":"Tianle Zhang","orcid":"https://orcid.org/0000-0002-0779-5905"},"institutions":[{"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"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianle Zhang","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China,100049","Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China,100049","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"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/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"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Liu","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China,100049","Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China,100049","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"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/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"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"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Pu","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China,100049","Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China,100049","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"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":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"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":["School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China,100049","Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China,100049","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047050212","display_name":"Xiaolin Ai","orcid":"https://orcid.org/0000-0001-7943-8336"},"institutions":[{"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/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolin Ai","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,Beijing,China,100190"],"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,Beijing,China,100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045244118","display_name":"Wanmai Yuan","orcid":"https://orcid.org/0000-0002-7140-1835"},"institutions":[{"id":"https://openalex.org/I2800372957","display_name":"China Electronics Technology Group Corporation","ror":"https://ror.org/0098hst83","country_code":"CN","type":"company","lineage":["https://openalex.org/I2800372957"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanmai Yuan","raw_affiliation_strings":["Information Science Academy of China Electronics Technology Group Corporation,Beijing,China,100081"],"affiliations":[{"raw_affiliation_string":"Information Science Academy of China Electronics Technology Group Corporation,Beijing,China,100081","institution_ids":["https://openalex.org/I2800372957"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5074422885"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.1748,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5447659,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10482","display_name":"Mathematical and Theoretical Epidemiology and Ecology Models","score":0.9718999862670898,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7682735323905945},{"id":"https://openalex.org/keywords/swarm-behaviour","display_name":"Swarm behaviour","score":0.6832824945449829},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5802760720252991},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5635109543800354},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5424625873565674},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.527269721031189},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5264754295349121},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.45613178610801697},{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.4519850015640259},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.42546534538269043},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4120280146598816},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.13467788696289062},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10815739631652832}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7682735323905945},{"id":"https://openalex.org/C181335050","wikidata":"https://www.wikidata.org/wiki/Q14915018","display_name":"Swarm behaviour","level":2,"score":0.6832824945449829},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5802760720252991},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5635109543800354},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5424625873565674},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.527269721031189},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5264754295349121},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.45613178610801697},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.4519850015640259},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.42546534538269043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4120280146598816},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.13467788696289062},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10815739631652832},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10191136","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191136","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3275963075","display_name":null,"funder_award_id":"2018AAA0102402","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4868535377","display_name":null,"funder_award_id":"62073323","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W1968701406","https://openalex.org/W2296073425","https://openalex.org/W2588790649","https://openalex.org/W2627013614","https://openalex.org/W2736601468","https://openalex.org/W2791251528","https://openalex.org/W2803155336","https://openalex.org/W2883532348","https://openalex.org/W2902857859","https://openalex.org/W2906413107","https://openalex.org/W2963762747","https://openalex.org/W2965857891","https://openalex.org/W2992533698","https://openalex.org/W2997536466","https://openalex.org/W2997940961","https://openalex.org/W2998367975","https://openalex.org/W3090059281","https://openalex.org/W3171954428","https://openalex.org/W3209101326","https://openalex.org/W4212814156","https://openalex.org/W4288336223","https://openalex.org/W4297733535","https://openalex.org/W4299802797","https://openalex.org/W4385245566","https://openalex.org/W6738796088","https://openalex.org/W6739901393","https://openalex.org/W6741002519","https://openalex.org/W6745537798","https://openalex.org/W6751139674","https://openalex.org/W6757586295","https://openalex.org/W6763173156","https://openalex.org/W6766805167","https://openalex.org/W6797233888"],"related_works":["https://openalex.org/W4288714711","https://openalex.org/W3200708550","https://openalex.org/W2736680465","https://openalex.org/W2079049982","https://openalex.org/W1490949538","https://openalex.org/W1598820299","https://openalex.org/W2751205960","https://openalex.org/W2180200293","https://openalex.org/W2292721517","https://openalex.org/W2754830870"],"abstract_inverted_index":{"Deriving":[0],"efficient":[1,135],"cooperative":[2,53,151],"policies":[3,54,153],"in":[4],"uncertain":[5],"dynamic":[6],"environments":[7],"poses":[8],"huge":[9],"challenges":[10],"for":[11,55,92,133],"a":[12,34,61,98,117,139,165],"distributed":[13,36,57,140,156],"swarm":[14,58,152],"system":[15],"due":[16],"to":[17,51,70,106,149],"the":[18,22,25,29,56,109,160,172,177,183],"limited":[19],"capability":[20],"of":[21,28,75,85,162,176],"agents":[23,128],"and":[24,45,82,115,124,174,180,192],"complex":[26],"dynamics":[27],"environment.":[30],"In":[31],"this":[32],"paper,":[33],"novel":[35],"method":[37,185],"based":[38],"on":[39,190],"deep":[40],"reinforcement":[41],"learning":[42],"using":[43,155],"observation-level":[44,72],"communication-level":[46,131],"graph":[47,64,101],"networks":[48],"is":[49,68,104,147],"proposed":[50,178,184],"learn":[52,150],"system.":[59],"Specifically,":[60],"relational":[62,77,95],"directed":[63,100],"attention":[65,102],"neural":[66],"network":[67,103],"designed":[69],"model":[71,116],"graphs":[73,78],"composed":[74],"heterogeneous":[76],"among":[79,112],"each":[80,83,122],"agent":[81,123],"type":[84],"entities":[86],"(e.g.,":[87],"obstacles,":[88],"other":[89],"teammates,":[90],"opponents),":[91],"extracting":[93],"different":[94],"representations.":[96],"Moreover,":[97],"relevant":[99,118,125],"presented":[105],"cut":[107],"off":[108],"ineffective":[110],"communication":[111,119],"irrelevant":[113],"agents,":[114],"topology":[120],"between":[121],"homogeneous":[126],"neighbor":[127],"as":[129],"an":[130],"graph,":[132],"promoting":[134],"inter-agent":[136],"interactions.":[137],"Furthermore,":[138],"actor-critic":[141],"algorithm":[142],"with":[143],"full":[144],"parameter":[145],"sharing":[146],"implemented":[148],"by":[154],"critics,":[157],"which":[158],"avoids":[159],"curse":[161],"dimensionality":[163],"under":[164],"centralized":[166],"critic.":[167],"Various":[168],"simulation":[169],"results":[170],"validate":[171],"effectiveness":[173],"generalization":[175],"method,":[179],"demonstrate":[181],"that":[182],"outperforms":[186],"existing":[187],"state-of-the-art":[188],"methods":[189],"coverage":[191],"pursuit":[193],"tasks.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}