{"id":"https://openalex.org/W4207065959","doi":"https://doi.org/10.1109/ssci50451.2021.9660008","title":"Hierarchical Cooperative Swarm Policy Learning with Role Emergence","display_name":"Hierarchical Cooperative Swarm Policy Learning with Role Emergence","publication_year":2021,"publication_date":"2021-12-05","ids":{"openalex":"https://openalex.org/W4207065959","doi":"https://doi.org/10.1109/ssci50451.2021.9660008"},"language":"en","primary_location":{"id":"doi:10.1109/ssci50451.2021.9660008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci50451.2021.9660008","pdf_url":null,"source":{"id":"https://openalex.org/S4363604921","display_name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","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/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/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/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianle Zhang","raw_affiliation_strings":["Institute of Automation,Chinese Academy of Sciences,Beijing,China,100190","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation,Chinese Academy of Sciences,Beijing,China,100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"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/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":"funder","lineage":["https://openalex.org/I19820366"]},{"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/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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Liu","raw_affiliation_strings":["Institute of Automation,Chinese Academy of Sciences,Beijing,China,100190","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation,Chinese Academy of Sciences,Beijing,China,100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"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/A5060319097","display_name":"Zhiqiang Pu","orcid":"https://orcid.org/0000-0002-4841-4048"},"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/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/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Pu","raw_affiliation_strings":["Institute of Automation,Chinese Academy of Sciences,Beijing,China,100190","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation,Chinese Academy of Sciences,Beijing,China,100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"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/A5043281824","display_name":"Tenghai Qiu","orcid":"https://orcid.org/0000-0002-0312-5728"},"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":"Tenghai Qiu","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/A5019541846","display_name":"Jianqiang Yi","orcid":"https://orcid.org/0000-0003-3268-9482"},"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"]},{"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":"Jianqiang Yi","raw_affiliation_strings":["Institute of Automation,Chinese Academy of Sciences,Beijing,China,100190","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Automation,Chinese Academy of Sciences,Beijing,China,100190","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]},{"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":5,"corresponding_author_ids":["https://openalex.org/A5074422885"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210100255","https://openalex.org/I4210112150","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.2513,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.5330903,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"20","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":0.9991000294685364,"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":0.9991000294685364,"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/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9785000085830688,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9435999989509583,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/swarm-behaviour","display_name":"Swarm behaviour","score":0.9143392443656921},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7570379376411438},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7503119707107544},{"id":"https://openalex.org/keywords/swarm-robotics","display_name":"Swarm robotics","score":0.663559079170227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5434373617172241},{"id":"https://openalex.org/keywords/swarm-intelligence","display_name":"Swarm intelligence","score":0.45240339636802673},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4514148235321045},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.37319740653038025},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34380608797073364},{"id":"https://openalex.org/keywords/particle-swarm-optimization","display_name":"Particle swarm optimization","score":0.3138730525970459}],"concepts":[{"id":"https://openalex.org/C181335050","wikidata":"https://www.wikidata.org/wiki/Q14915018","display_name":"Swarm behaviour","level":2,"score":0.9143392443656921},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7570379376411438},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7503119707107544},{"id":"https://openalex.org/C169337768","wikidata":"https://www.wikidata.org/wiki/Q2446723","display_name":"Swarm robotics","level":3,"score":0.663559079170227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5434373617172241},{"id":"https://openalex.org/C119487961","wikidata":"https://www.wikidata.org/wiki/Q863960","display_name":"Swarm intelligence","level":3,"score":0.45240339636802673},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4514148235321045},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37319740653038025},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34380608797073364},{"id":"https://openalex.org/C85617194","wikidata":"https://www.wikidata.org/wiki/Q2072794","display_name":"Particle swarm optimization","level":2,"score":0.3138730525970459},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ssci50451.2021.9660008","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci50451.2021.9660008","pdf_url":null,"source":{"id":"https://openalex.org/S4363604921","display_name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W655010059","https://openalex.org/W1191599655","https://openalex.org/W1542941925","https://openalex.org/W2033588051","https://openalex.org/W2155027007","https://openalex.org/W2157331557","https://openalex.org/W2498529546","https://openalex.org/W2617547828","https://openalex.org/W2736601468","https://openalex.org/W2786572318","https://openalex.org/W2791251528","https://openalex.org/W2803155336","https://openalex.org/W2883532348","https://openalex.org/W2902857859","https://openalex.org/W2950614095","https://openalex.org/W2953444180","https://openalex.org/W2973525135","https://openalex.org/W2994864869","https://openalex.org/W2997070234","https://openalex.org/W2997536466","https://openalex.org/W3034971464","https://openalex.org/W3037148280","https://openalex.org/W3043763914","https://openalex.org/W3209101326","https://openalex.org/W4288091739","https://openalex.org/W4299802797","https://openalex.org/W4385245566","https://openalex.org/W6627932998","https://openalex.org/W6683204974","https://openalex.org/W6737849119","https://openalex.org/W6738796088","https://openalex.org/W6739901393","https://openalex.org/W6741002519","https://openalex.org/W6751139674","https://openalex.org/W6752089545","https://openalex.org/W6765166828","https://openalex.org/W6767919266","https://openalex.org/W6769091550","https://openalex.org/W6771235960","https://openalex.org/W6771817571","https://openalex.org/W6775529125","https://openalex.org/W6780801319","https://openalex.org/W7039202139"],"related_works":["https://openalex.org/W4233987368","https://openalex.org/W65954170","https://openalex.org/W1988876749","https://openalex.org/W2182522217","https://openalex.org/W4386001959","https://openalex.org/W4234675952","https://openalex.org/W2048054807","https://openalex.org/W4304182880","https://openalex.org/W4362659455","https://openalex.org/W2789344126"],"abstract_inverted_index":{"Swarm":[0],"systems":[1,222],"can":[2,45,210],"cooperatively":[3],"and":[4,52,91,124,160,168,212,216,225],"efficiently":[5,226],"accomplish":[6,227],"specified":[7],"complex":[8,36,50,228],"tasks.":[9],"Recent":[10],"works":[11],"have":[12],"shown":[13],"the":[14,95,139,142,200],"potential":[15],"of":[16,25,141],"multi-agent":[17],"reinforcement":[18,79],"learning":[19,70,80],"methods":[20],"to":[21,34,99,113,137,174,186,190,223],"study":[22],"behavior":[23],"policies":[24,153],"swarm":[26,37,68,83,111,135,152,221],"systems.":[27,84],"However,":[28],"it":[29,131],"is":[30,184],"difficult":[31],"for":[32,81,118],"them":[33,54],"complete":[35,101],"tasks":[38,51,229],"efficiently.":[39],"In":[40,85,179],"human":[41],"society,":[42],"role":[43,73,97,117,122,144],"assignment":[44],"effectively":[46],"help":[47],"humans":[48],"understand":[49],"decompose":[53],"into":[55],"simple":[56],"certain":[57,103],"subtasks.":[58],"Inspired":[59],"by":[60,193],"this,":[61],"we":[62],"propose":[63],"a":[64,102,109,116,121,126,133,146,231],"two-level":[65],"hierarchical":[66,77,151],"cooperative":[67],"policy":[69,112,136],"framework":[71],"with":[72,94,154,202],"emergence":[74],"based":[75],"on":[76],"deep":[78],"distributed":[82],"this":[86],"framework,":[87],"roles":[88,189,201],"are":[89,157,172],"dynamic":[90,215],"emergent.":[92],"Agents":[93],"same":[96],"tend":[98],"collectively":[100],"subtask.":[104],"Specifically,":[105],"each":[106],"agent":[107],"uses":[108,132],"higher-level":[110],"dynamically":[114],"select":[115],"itself":[119],"in":[120,145,230],"space":[123],"at":[125],"higher":[127],"temporal":[128],"scale,":[129],"while":[130],"lower-level":[134],"perform":[138],"responsibilities":[140],"selected":[143],"primitive":[147],"action":[148],"space.":[149],"Meanwhile,":[150],"partial":[155],"observation":[156],"centrally":[158],"trained":[159],"decentrally":[161],"executed,":[162],"where":[163],"agents'":[164,194],"local":[165],"interaction":[166],"modules":[167],"extrinsic":[169],"team":[170],"rewards":[171],"designed":[173],"promote":[175],"cooperation":[176],"among":[177],"agents.":[178],"addition,":[180],"an":[181],"intrinsic":[182],"reward":[183],"defined":[185],"enable":[187],"different":[188],"be":[191],"identified":[192],"longer-term":[195],"behaviors,":[196],"which":[197,219],"implicitly":[198],"associates":[199],"responsibilities.":[203],"Simulation":[204],"results":[205],"show":[206],"that":[207],"our":[208],"method":[209],"learn":[211],"generate":[213],"emergent,":[214],"identifiable":[217],"roles,":[218],"helps":[220],"reliably":[224],"shorter":[232],"time.":[233]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}