{"id":"https://openalex.org/W7214923403","doi":"https://doi.org/10.48550/arxiv.2609.37566","title":"RAVEN: Receiver-Conditioned Action-Value Encoding for Finite-Alphabet Multi-Agent Communication","display_name":"RAVEN: Receiver-Conditioned Action-Value Encoding for Finite-Alphabet Multi-Agent Communication","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214923403","doi":"https://doi.org/10.48550/arxiv.2609.37566"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.37566","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37566","pdf_url":"https://arxiv.org/pdf/2609.37566","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.37566","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153641321","display_name":"Shuwei Sun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sun, Shuwei","raw_affiliation_strings":["Xi'an Jiaotong University Xi'an , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University Xi'an , China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153607351","display_name":"Chenxi Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Chenxi","raw_affiliation_strings":["Xi'an Jiaotong University Xi'an , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University Xi'an , China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153627656","display_name":"Jian Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Jian","raw_affiliation_strings":["Xi'an Jiaotong University Xi'an , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University Xi'an , China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114514215","display_name":"Weiyun Ru","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ru, Weiyun","raw_affiliation_strings":["Xi'an Jiaotong University Xi'an , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University Xi'an , China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153590059","display_name":"Hui Cao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cao, Hui","raw_affiliation_strings":["Xi'an Jiaotong University Xi'an , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University Xi'an , China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9878000020980835,"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":0.9878000020980835,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.00279999990016222,"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/T11031","display_name":"Game Theory and Applications","score":0.0015999999595806003,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/multi-agent-communication","display_name":"multi-agent communication","score":0.8880000114440918},{"id":"https://openalex.org/keywords/qmix","display_name":"QMIX","score":0.5120000243186951},{"id":"https://openalex.org/keywords/codebook-selection","display_name":"codebook selection","score":0.5849999785423279},{"id":"https://openalex.org/keywords/offline-communication","display_name":"offline communication","score":0.414000004529953},{"id":"https://openalex.org/keywords/smac","display_name":"Smac/DIABLO","score":0.6949999928474426},{"id":"https://openalex.org/keywords/mpe","display_name":"MPE","score":0.7120000123977661},{"id":"https://openalex.org/keywords/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.5220000147819519}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6884999871253967},{"id":"https://openalex.org/C198104137","wikidata":"https://www.wikidata.org/wiki/Q974688","display_name":"Communication source","level":2,"score":0.5885000228881836},{"id":"https://openalex.org/C134400042","wikidata":"https://www.wikidata.org/wiki/Q2372244","display_name":"Symbol (formal)","level":2,"score":0.5480999946594238},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.46219998598098755},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.4381999969482422},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41350001096725464},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4129999876022339},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3846000134944916},{"id":"https://openalex.org/C2778858076","wikidata":"https://www.wikidata.org/wiki/Q5249539","display_name":"Decodes","level":3,"score":0.3709000051021576},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33320000767707825},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C112876837","wikidata":"https://www.wikidata.org/wiki/Q837518","display_name":"Alphabet","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.26260000467300415},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26089999079704285},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.37566","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37566","pdf_url":"https://arxiv.org/pdf/2609.37566","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.37566","doi":"https://doi.org/10.48550/arxiv.2609.37566","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.37566","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.37566","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37566","pdf_url":"https://arxiv.org/pdf/2609.37566","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214923403.pdf","grobid_xml":"https://content.openalex.org/works/W7214923403.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2016381774","https://openalex.org/W2150412388","https://openalex.org/W2150593711","https://openalex.org/W2242818861","https://openalex.org/W2584377191","https://openalex.org/W2746553466","https://openalex.org/W2747213132","https://openalex.org/W2964121744","https://openalex.org/W2979408248","https://openalex.org/W3046288222","https://openalex.org/W3094456479","https://openalex.org/W3145052169","https://openalex.org/W3175698408","https://openalex.org/W4254197176","https://openalex.org/W4283789768","https://openalex.org/W4313139387","https://openalex.org/W4386473019","https://openalex.org/W4390306608","https://openalex.org/W4393147227","https://openalex.org/W4399911351","https://openalex.org/W4400792723","https://openalex.org/W4406249890","https://openalex.org/W4409348008","https://openalex.org/W4413387548","https://openalex.org/W7133188823","https://openalex.org/W7133226216","https://openalex.org/W7154143517","https://openalex.org/W7161946724"],"related_works":["https://openalex.org/W4294956331","https://openalex.org/W7222673228","https://openalex.org/W4214873649","https://openalex.org/W2169431391","https://openalex.org/W2997556607","https://openalex.org/W4385944431","https://openalex.org/W7152371516","https://openalex.org/W7214722332","https://openalex.org/W7154017435","https://openalex.org/W6908397368"],"abstract_inverted_index":{"A":[0],"message":[1,211],"drawn":[2],"from":[3,177],"a":[4,8,49,90,108,122,128,136],"small":[5],"alphabet":[6],"helps":[7],"teammate":[9],"only":[10],"if":[11],"it":[12,106,193],"keeps":[13],"the":[14,32,61,73,95,113,131,156,182,195],"distinctions":[15],"that":[16,18,24,71,97,140,205],"change":[17],"teammate's":[19],"next":[20],"decision.":[21],"We":[22,82],"show":[23],"scoring":[25],"messages":[26],"by":[27],"action":[28],"values":[29],"averaged":[30],"over":[31,181],"receiver's":[33,56,62],"situation":[34],"can":[35],"erase":[36],"exactly":[37,98],"these":[38],"distinctions,":[39],"and":[40,104,117,161,188,191,222],"we":[41,111],"propose":[42],"RAVEN":[43,93,125,154,172,210],"(Receiver-conditioned":[44],"Action-Value":[45],"ENcoding),":[46],"which":[47],"trains":[48],"four-symbol,":[50],"one-step-delayed":[51],"channel":[52],"to":[53,69,179],"preserve":[54],"each":[55],"centered":[57],"action-value":[58],"profile":[59],"within":[60],"own":[63],"context.":[64],"The":[65],"sender":[66],"never":[67],"needs":[68],"know":[70],"context:":[72],"receiver":[74,163],"decodes":[75],"every":[76],"symbol":[77,133],"with":[78,135],"its":[79,142,168],"private":[80],"information.":[81],"give":[83],"two":[84],"estimators":[85],"of":[86,167,200,219],"this":[87],"target.":[88],"With":[89],"teacher,":[91,123],"offline":[92,153],"selects":[94],"codebook":[96],"minimizes":[99],"an":[100],"empirical":[101],"conditional":[102],"distortion":[103],"distills":[105],"into":[107],"frozen":[109],"sender;":[110],"bound":[112],"resulting":[114],"codebook-selection":[115],"error":[116],"one-step":[118],"decision":[119],"loss.":[120],"Without":[121],"online":[124],"aligns,":[126],"inside":[127],"QMIX":[129,184],"learner,":[130],"deployed":[132],"pathway":[134],"training-only":[137],"continuous":[138],"reference":[139],"shares":[141],"routing.":[143],"Against":[144],"five":[145],"recent":[146],"communication":[147,169],"methods":[148,204],"on":[149,189,224],"eight":[150],"navigation":[151],"settings,":[152],"attains":[155,194],"highest":[157],"return":[158],"in":[159],"seven,":[160],"removing":[162],"conditioning":[164],"forfeits":[165],"83%":[166],"gain.":[170],"Online":[171],"raises":[173],"predator-prey":[174],"capture":[175],"success":[176],"53.2%":[178],"96.0%":[180],"same":[183],"backbone":[185],"without":[186],"communication,":[187],"SMAC":[190],"MPE":[192],"best":[196],"mean":[197],"normalized":[198],"score":[199],"14":[201],"methods,":[202],"including":[203],"exchange":[206],"kilobit":[207],"messages.":[208],"Every":[209],"costs":[212],"2":[213],"bits,":[214],"12-1,024x":[215],"fewer":[216],"than":[217],"those":[218],"NDQ,":[220],"CACOM":[221],"ExpoComm":[223],"navigation.":[225]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-01T00:00:00"}