{"id":"https://openalex.org/W4385767399","doi":"https://doi.org/10.24963/ijcai.2023/15","title":"Scalable Communication for Multi-Agent Reinforcement Learning via Transformer-Based Email Mechanism","display_name":"Scalable Communication for Multi-Agent Reinforcement Learning via Transformer-Based Email Mechanism","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385767399","doi":"https://doi.org/10.24963/ijcai.2023/15"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/15","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/15","pdf_url":"https://www.ijcai.org/proceedings/2023/0015.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0015.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101582967","display_name":"Xudong Guo","orcid":"https://orcid.org/0000-0002-5634-6380"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xudong Guo","raw_affiliation_strings":["Tsinghua University","Department of Automation, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087677543","display_name":"Daming Shi","orcid":"https://orcid.org/0000-0001-8508-4845"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daming Shi","raw_affiliation_strings":["Tsinghua University","Department of Automation, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100693811","display_name":"Wenhui Fan","orcid":"https://orcid.org/0000-0002-0040-5759"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenhui Fan","raw_affiliation_strings":["Tsinghua unviersity","Department of Automation, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua unviersity","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Automation, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100693811"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.2607,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78055325,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"126","last_page":"134"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9789999723434448,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9789999723434448,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9763000011444092,"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/T12592","display_name":"Opinion Dynamics and Social Influence","score":0.9704999923706055,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8357417583465576},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7704517841339111},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7611608505249023},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6019960045814514},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6005693078041077},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5489429235458374},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5194922685623169},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.4146340489387512},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2691274583339691},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10273459553718567}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8357417583465576},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7704517841339111},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7611608505249023},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6019960045814514},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6005693078041077},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5489429235458374},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5194922685623169},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.4146340489387512},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2691274583339691},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10273459553718567},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/15","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/15","pdf_url":"https://www.ijcai.org/proceedings/2023/0015.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/15","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/15","pdf_url":"https://www.ijcai.org/proceedings/2023/0015.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385767399.pdf"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W1977655452","https://openalex.org/W2395575420","https://openalex.org/W2736601468","https://openalex.org/W2756196406","https://openalex.org/W2803155336","https://openalex.org/W2949963774","https://openalex.org/W2963864421","https://openalex.org/W2971727319","https://openalex.org/W2982316857","https://openalex.org/W2983178256","https://openalex.org/W2996037775","https://openalex.org/W3096358451","https://openalex.org/W3100930738","https://openalex.org/W4281622133","https://openalex.org/W4283789768","https://openalex.org/W4286748781","https://openalex.org/W4288594419","https://openalex.org/W4288601262","https://openalex.org/W4289100326","https://openalex.org/W4289363497","https://openalex.org/W4295598622","https://openalex.org/W4299802797","https://openalex.org/W4301501993","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2988126442","https://openalex.org/W1974414866","https://openalex.org/W2057568687","https://openalex.org/W2063982682","https://openalex.org/W2338543196","https://openalex.org/W2133886031"],"abstract_inverted_index":{"Communication":[0],"can":[1,83],"impressively":[2],"improve":[3],"cooperation":[4,94],"in":[5],"multi-agent":[6],"reinforcement":[7],"learning":[8],"(MARL),":[9],"especially":[10],"for":[11,58],"partially-observed":[12,59],"tasks.":[13],"However,":[14],"existing":[15],"works":[16],"either":[17],"broadcast":[18],"the":[19,32,42,52,80,89,108,111,121,126,133,141],"messages":[20,77],"leading":[21],"to":[22,50,75,79,102,105,117,124],"information":[23,104],"redundancy,":[24],"or":[25],"learn":[26],"targeted":[27],"communication":[28,57,74],"by":[29,92],"modeling":[30,87],"all":[31,88],"other":[33],"agents":[34,45,71,109,144],"as":[35],"targets,":[36],"which":[37],"is":[38],"not":[39],"scalable":[40],"when":[41],"number":[43,142],"of":[44,55,143],"varies.":[46],"In":[47],"this":[48],"work,":[49],"tackle":[51],"scalability":[53],"problem":[54],"MARL":[56,138],"tasks,":[60],"we":[61,98],"propose":[62],"a":[63],"novel":[64],"framework":[65],"Transformer-based":[66],"Email":[67],"Mechanism":[68],"(TEM).":[69],"The":[70],"adopt":[72],"local":[73],"send":[76],"only":[78],"ones":[81],"that":[82],"be":[84],"observed":[85],"without":[86,150],"agents.":[90],"Inspired":[91],"human":[93],"with":[95,107],"email":[96],"forwarding,":[97],"design":[99],"message":[100,122],"chains":[101],"forward":[103],"cooperate":[106],"outside":[110],"observation":[112],"range.":[113],"We":[114],"introduce":[115],"Transformer":[116],"encode":[118],"and":[119],"decode":[120],"chain":[123],"choose":[125],"next":[127],"receiver":[128],"selectively.":[129],"Empirically,":[130],"TEM":[131,146],"outperforms":[132],"baselines":[134],"on":[135],"multiple":[136],"cooperative":[137],"benchmarks.":[139],"When":[140],"varies,":[145],"maintains":[147],"superior":[148],"performance":[149],"further":[151],"training.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
