{"id":"https://openalex.org/W4403487523","doi":"https://doi.org/10.3233/faia240741","title":"Exploiting Hierarchical Symmetry in Multi-Agent Reinforcement Learning","display_name":"Exploiting Hierarchical Symmetry in Multi-Agent Reinforcement Learning","publication_year":2024,"publication_date":"2024-10-16","ids":{"openalex":"https://openalex.org/W4403487523","doi":"https://doi.org/10.3233/faia240741"},"language":"en","primary_location":{"id":"doi:10.3233/faia240741","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240741","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia240741","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014464986","display_name":"Yongkai Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongkai Tian","raw_affiliation_strings":["State Key Laboratory of Complex & Critical Software Environment, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Complex & Critical Software Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100738015","display_name":"Xin Yu","orcid":"https://orcid.org/0000-0002-3901-1335"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Yu","raw_affiliation_strings":["State Key Laboratory of Complex & Critical Software Environment, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Complex & Critical Software Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101491985","display_name":"Yue Qi","orcid":"https://orcid.org/0000-0001-9304-1933"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yirong Qi","raw_affiliation_strings":["State Key Laboratory of Complex & Critical Software Environment, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Complex & Critical Software Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115695478","display_name":"Li Wang","orcid":"https://orcid.org/0000-0002-0496-9500"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Wang","raw_affiliation_strings":["Institute of Artificial Intelligence, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100900707","display_name":"Pu Feng","orcid":"https://orcid.org/0000-0002-6219-1741"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pu Feng","raw_affiliation_strings":["State Key Laboratory of Complex & Critical Software Environment, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Complex & Critical Software Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114911190","display_name":"Wenjun Wu","orcid":"https://orcid.org/0000-0003-2998-8828"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjun Wu","raw_affiliation_strings":["Institute of Artificial Intelligence, Beihang University, Beijing, China","State Key Laboratory of Complex & Critical Software Environment, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"State Key Laboratory of Complex & Critical Software Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031139851","display_name":"Rongye Shi","orcid":"https://orcid.org/0000-0003-4298-9358"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongye Shi","raw_affiliation_strings":["Institute of Artificial Intelligence, Beihang University, Beijing, China","State Key Laboratory of Complex & Critical Software Environment, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"State Key Laboratory of Complex & Critical Software Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107300921","display_name":"Jie Luo","orcid":"https://orcid.org/0009-0005-2948-9262"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Luo","raw_affiliation_strings":["State Key Laboratory of Complex & Critical Software Environment, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Complex & Critical Software Environment, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":2.598,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.91795324,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"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":0.2818000018596649,"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":0.2818000018596649,"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":0.6984901428222656},{"id":"https://openalex.org/keywords/symmetry","display_name":"Symmetry (geometry)","score":0.5830074548721313},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5283342599868774},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.46388891339302063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32851195335388184},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2003237009048462},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19480949640274048},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.08872926235198975},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.06737625598907471}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6984901428222656},{"id":"https://openalex.org/C2779886137","wikidata":"https://www.wikidata.org/wiki/Q21030012","display_name":"Symmetry (geometry)","level":2,"score":0.5830074548721313},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5283342599868774},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46388891339302063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32851195335388184},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2003237009048462},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19480949640274048},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.08872926235198975},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.06737625598907471}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia240741","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240741","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia240741","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240741","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"Achieving":[0],"high":[1],"sample":[2,56],"efficiency":[3],"is":[4,63,117],"a":[5,84,104,172],"critical":[6],"research":[7],"area":[8],"in":[9,16,92,128,171,179],"reinforcement":[10,18],"learning.":[11],"This":[12,95],"becomes":[13],"extremely":[14],"difficult":[15],"multi-agent":[17,85,99,145],"learning":[19],"(MARL),":[20],"as":[21],"the":[22,25,34,52,72,110],"capacity":[23],"of":[24,36,40,54,74,83],"joint":[26],"state":[27],"and":[28,45,102,130,157],"action":[29],"space":[30],"grows":[31],"exponentially":[32],"with":[33],"number":[35],"agents.":[37],"The":[38,147],"reliance":[39],"MARL":[41,62],"solely":[42],"on":[43,98],"exploration":[44],"trial-and-error,":[46],"without":[47],"incorporating":[48,106],"prior":[49],"knowledge,":[50],"exacerbates":[51],"issue":[53],"low":[55],"efficiency.":[57],"Currently,":[58],"introducing":[59],"symmetry":[60,79],"into":[61],"an":[64],"effective":[65],"approach":[66],"to":[67,123,135,162],"address":[68],"this":[69],"issue.":[70],"Yet":[71],"concept":[73],"hierarchical":[75,107,125],"symmetry,":[76,108],"which":[77,116],"maintains":[78],"across":[80,143],"different":[81],"levels":[82],"system":[86],"(MAS),":[87],"has":[88],"not":[89],"been":[90],"explored":[91],"existing":[93],"methods.":[94],"paper":[96],"focuses":[97],"cooperative":[100],"tasks":[101],"proposes":[103],"method":[105,152],"termed":[109],"Hierarchical":[111],"Equivariant":[112],"Policy":[113],"Network":[114],"(HEPN)":[115],"O(n)-equivariant.":[118],"Specifically,":[119],"HEPN":[120],"utilizes":[121],"clustering":[122],"perform":[124],"information":[126],"extraction":[127],"MAS,":[129],"employs":[131],"graph":[132],"neural":[133],"networks":[134],"model":[136],"agent":[137],"interactions.":[138],"We":[139],"conducted":[140],"extensive":[141],"experiments":[142],"various":[144],"tasks.":[146],"results":[148],"indicate":[149],"that":[150],"our":[151,169],"achieves":[153],"faster":[154],"convergence":[155,159],"speeds":[156],"higher":[158],"rewards":[160],"compared":[161],"baseline":[163],"algorithms.":[164],"Additionally,":[165],"we":[166],"have":[167],"deployed":[168],"algorithm":[170],"physical":[173],"multi-robot":[174],"system,":[175],"confirming":[176],"its":[177],"effectiveness":[178],"real-world":[180],"environments.":[181],"Supplementary":[182],"materials":[183],"are":[184],"available":[185],"at":[186],"https://yongkai-tian.github.io/HEPN/.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}
