{"id":"https://openalex.org/W4387172174","doi":"https://doi.org/10.3233/faia230609","title":"ESP: Exploiting Symmetry Prior for Multi-Agent Reinforcement Learning","display_name":"ESP: Exploiting Symmetry Prior for Multi-Agent Reinforcement Learning","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387172174","doi":"https://doi.org/10.3233/faia230609"},"language":"en","primary_location":{"id":"doi:10.3233/faia230609","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230609","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230609","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://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230609","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111766888","display_name":"Xin Yu","orcid":"https://orcid.org/0000-0002-3354-8625"},"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":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":true,"raw_author_name":"Rongye Shi","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","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":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028701003","display_name":"Jie Luo","orcid":"https://orcid.org/0000-0002-4157-9931"},"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":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","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":["Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5031139851"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":6.9864,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.97251934,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"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":0.9965000152587891,"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":0.9965000152587891,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9509000182151794,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9280999898910522,"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":0.9007841348648071},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.7706605195999146},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7133249044418335},{"id":"https://openalex.org/keywords/marl","display_name":"Marl","score":0.6400780081748962},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6104870438575745},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5287047624588013},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4510587155818939},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3502193093299866},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1144363284111023}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9007841348648071},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.7706605195999146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7133249044418335},{"id":"https://openalex.org/C92927620","wikidata":"https://www.wikidata.org/wiki/Q184053","display_name":"Marl","level":3,"score":0.6400780081748962},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6104870438575745},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5287047624588013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4510587155818939},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3502193093299866},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1144363284111023},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C109007969","wikidata":"https://www.wikidata.org/wiki/Q749565","display_name":"Structural basin","level":2,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia230609","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230609","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230609","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/faia230609","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230609","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230609","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387172174.pdf","grobid_xml":"https://content.openalex.org/works/W4387172174.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1533853869","https://openalex.org/W1542941925","https://openalex.org/W1604363237","https://openalex.org/W2062017050","https://openalex.org/W2240585996","https://openalex.org/W2279221249","https://openalex.org/W2602275733","https://openalex.org/W2615547864","https://openalex.org/W2623431351","https://openalex.org/W2769152880","https://openalex.org/W2794643322","https://openalex.org/W2913871909","https://openalex.org/W2975343435","https://openalex.org/W2982238751","https://openalex.org/W2991479173","https://openalex.org/W2995937146","https://openalex.org/W2996037775","https://openalex.org/W2998367975","https://openalex.org/W2998923516","https://openalex.org/W3015437096","https://openalex.org/W3021708257","https://openalex.org/W3023640063","https://openalex.org/W3031798691","https://openalex.org/W3034218175","https://openalex.org/W3035454705","https://openalex.org/W3039459278","https://openalex.org/W3093345403","https://openalex.org/W3098082936","https://openalex.org/W3115293622","https://openalex.org/W3140147451","https://openalex.org/W3157286395","https://openalex.org/W3168972368","https://openalex.org/W3177261102","https://openalex.org/W3178092445","https://openalex.org/W3193576605","https://openalex.org/W3199139896","https://openalex.org/W3207681582","https://openalex.org/W3213974477","https://openalex.org/W3214936187","https://openalex.org/W4206309409","https://openalex.org/W4221154377","https://openalex.org/W4224874620","https://openalex.org/W4286748781","https://openalex.org/W4286850040","https://openalex.org/W4286907648","https://openalex.org/W4287749615","https://openalex.org/W4287811291","https://openalex.org/W4293246336","https://openalex.org/W4293763266","https://openalex.org/W4295598622","https://openalex.org/W4297688279","https://openalex.org/W4299802797","https://openalex.org/W4304731240","https://openalex.org/W4383567286"],"related_works":["https://openalex.org/W2126019709","https://openalex.org/W1702901972","https://openalex.org/W4249798507","https://openalex.org/W2069775250","https://openalex.org/W2152754392","https://openalex.org/W2196316523","https://openalex.org/W1989172970","https://openalex.org/W1899363654","https://openalex.org/W2507089433","https://openalex.org/W2883256816"],"abstract_inverted_index":{"Multi-agent":[0],"reinforcement":[1,14,29],"learning":[2,15,30],"(MARL)":[3],"has":[4],"achieved":[5],"promising":[6],"results":[7],"in":[8,41,51],"recent":[9],"years.":[10],"However,":[11],"most":[12,89],"existing":[13,74],"methods":[16],"require":[17],"a":[18,57,68,115],"large":[19],"amount":[20],"of":[21,34,90,104],"data":[22,65],"for":[23,59],"model":[24],"training.":[25],"In":[26,77],"addition,":[27,78],"data-efficient":[28],"requires":[31],"the":[32,42,48,73,79,91,102,105,109],"construction":[33],"strong":[35],"inductive":[36],"biases,":[37],"which":[38],"are":[39],"ignored":[40],"current":[43,92],"MARL":[44,75,93],"approaches.":[45],"Inspired":[46],"by":[47,63],"symmetry":[49],"phenomenon":[50],"multi-agent":[52],"systems,":[53],"this":[54],"paper":[55],"proposes":[56],"framework":[58,81,111],"exploiting":[60],"prior":[61],"knowledge":[62],"integrating":[64],"augmentation":[66],"and":[67,84],"well-designed":[69],"consistency":[70],"loss":[71],"into":[72],"methods.":[76],"proposed":[80,106,110],"is":[82,112],"model-agnostic":[83],"can":[85],"be":[86],"applied":[87,113],"to":[88,114,119],"algorithms.":[94],"Experimental":[95],"tests":[96],"on":[97],"multiple":[98],"challenging":[99],"tasks":[100],"demonstrate":[101],"effectiveness":[103],"framework.":[107],"Moreover,":[108],"physical":[116],"multi-robot":[117],"testbed":[118],"show":[120],"its":[121],"superiority.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}