{"id":"https://openalex.org/W4387185165","doi":"https://doi.org/10.3233/faia230493","title":"Learning to Collaborate by Grouping: A Consensus-Oriented Strategy for Multi-Agent Reinforcement Learning","display_name":"Learning to Collaborate by Grouping: A Consensus-Oriented Strategy for Multi-Agent Reinforcement Learning","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387185165","doi":"https://doi.org/10.3233/faia230493"},"language":"en","primary_location":{"id":"doi:10.3233/faia230493","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230493","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230493","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/FAIA230493","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076546255","display_name":"Jingqing Ruan","orcid":"https://orcid.org/0000-0002-4857-9053"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingqing Ruan","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103137659","display_name":"Xiaotian Hao","orcid":"https://orcid.org/0000-0002-3084-8366"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaotian Hao","raw_affiliation_strings":["Tianjin University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101672127","display_name":"Dong Li","orcid":"https://orcid.org/0000-0002-3144-5104"},"institutions":[{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Dong Li","raw_affiliation_strings":["Noah\u2019s Ark Lab, Huawei","Noah's Ark Lab, Huawei d SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Noah\u2019s Ark Lab, Huawei","institution_ids":["https://openalex.org/I4210159102"]},{"raw_affiliation_string":"Noah's Ark Lab, Huawei d SenseTime Research","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076505011","display_name":"Hangyu Mao","orcid":"https://orcid.org/0000-0002-4499-7581"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hangyu Mao","raw_affiliation_strings":["SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.3582,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.96814491,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9743000268936157,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9743000268936157,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9433000087738037,"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":0.7245645523071289},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6825881600379944},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6004874110221863},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4599742889404297},{"id":"https://openalex.org/keywords/group","display_name":"Group (periodic table)","score":0.44362515211105347},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.43883663415908813},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3372630178928375},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3024880886077881}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7245645523071289},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6825881600379944},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6004874110221863},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4599742889404297},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.44362515211105347},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.43883663415908813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3372630178928375},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3024880886077881},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia230493","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230493","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230493","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/faia230493","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3233/faia230493","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230493","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":[{"score":0.6899999976158142,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387185165.pdf","grobid_xml":"https://content.openalex.org/works/W4387185165.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W164791823","https://openalex.org/W1597623052","https://openalex.org/W1898986177","https://openalex.org/W1967890032","https://openalex.org/W2143842650","https://openalex.org/W2296033070","https://openalex.org/W2404646363","https://openalex.org/W2623431351","https://openalex.org/W2752796333","https://openalex.org/W2803155336","https://openalex.org/W2904453761","https://openalex.org/W2963243556","https://openalex.org/W2963799213","https://openalex.org/W2975343435","https://openalex.org/W2995937146","https://openalex.org/W2997502221","https://openalex.org/W3012445938","https://openalex.org/W3029401208","https://openalex.org/W3034971464","https://openalex.org/W3035098634","https://openalex.org/W3089778445","https://openalex.org/W3093524531","https://openalex.org/W3119486431","https://openalex.org/W3129170303","https://openalex.org/W3137260861","https://openalex.org/W3170381145","https://openalex.org/W3173215816","https://openalex.org/W3194351817","https://openalex.org/W3211445425","https://openalex.org/W3213679214","https://openalex.org/W3214748135","https://openalex.org/W4221149741","https://openalex.org/W4224266469","https://openalex.org/W4225495521","https://openalex.org/W4229001981","https://openalex.org/W4280525693","https://openalex.org/W4285436760","https://openalex.org/W4285603540","https://openalex.org/W4285605187","https://openalex.org/W4286970222","https://openalex.org/W4293518929","https://openalex.org/W4296512951","https://openalex.org/W4298007478","https://openalex.org/W4299802797","https://openalex.org/W4303941905","https://openalex.org/W4310512676","https://openalex.org/W4312689789","https://openalex.org/W4320458133","https://openalex.org/W4382202883","https://openalex.org/W4382461758","https://openalex.org/W4394642966","https://openalex.org/W6783196708"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W2110523656","https://openalex.org/W1482209366","https://openalex.org/W2521627374"],"abstract_inverted_index":{"Multi-agent":[0],"systems":[1],"require":[2],"effective":[3,152],"coordination":[4,106,153],"between":[5],"groups":[6],"and":[7,26,52,78,82,96,111,124,141],"individuals":[8],"to":[9,35],"achieve":[10],"common":[11],"goals.":[12],"However,":[13],"current":[14],"multi-agent":[15,155],"reinforcement":[16],"learning":[17],"(MARL)":[18],"methods":[19],"primarily":[20],"focus":[21],"on":[22,117],"improving":[23],"individual":[24,53,98,112],"policies":[25,54,99],"do":[27],"not":[28],"adequately":[29],"address":[30,39],"group-level":[31],"policies,":[32],"which":[33,69,88],"leads":[34],"weak":[36],"cooperation.":[37],"To":[38],"this":[40],"issue,":[41],"we":[42,133],"propose":[43],"a":[44,94,147],"novel":[45],"Consensus-oriented":[46],"Strategy":[47],"(CoS)":[48],"that":[49,74,135],"emphasizes":[50],"group":[51,66,80,85,91,102,110],"simultaneously.":[55],"Specifically,":[56],"CoS":[57,136],"comprises":[58],"two":[59],"main":[60],"components:":[61],"(a)":[62],"the":[63,76,84,90,97,101,109],"vector":[64],"quantized":[65],"consensus":[67],"module,":[68],"extracts":[70],"discrete":[71,123],"latent":[72],"embeddings":[73],"represent":[75],"stable":[77],"discriminative":[79],"consensus,":[81,103],"(b)":[83],"consensus-oriented":[86],"strategy,":[87],"integrates":[89],"policy":[92],"using":[93,100],"hypernet":[95],"thereby":[104],"promoting":[105],"at":[107],"both":[108,122],"levels.":[113],"Through":[114],"empirical":[115],"experiments":[116],"cooperative":[118],"navigation":[119],"tasks":[120],"with":[121],"continuous":[125],"spaces,":[126],"as":[127,129],"well":[128],"google":[130],"research":[131],"football,":[132],"demonstrate":[134],"outperforms":[137],"state-of-the-art":[138],"MARL":[139],"algorithms":[140],"achieves":[142],"better":[143],"collaboration,":[144],"thus":[145],"providing":[146],"promising":[148],"solution":[149],"for":[150],"achieving":[151],"in":[154],"systems.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}