{"id":"https://openalex.org/W2402402867","doi":"https://doi.org/10.48550/arxiv.1605.07736","title":"Learning Multiagent Communication with Backpropagation","display_name":"Learning Multiagent Communication with Backpropagation","publication_year":2016,"publication_date":"2016-05-25","ids":{"openalex":"https://openalex.org/W2402402867","doi":"https://doi.org/10.48550/arxiv.1605.07736","mag":"2402402867"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1605.07736","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1605.07736","pdf_url":"https://arxiv.org/pdf/1605.07736","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/1605.07736","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060255128","display_name":"Sainbayar Sukhbaatar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36672615","display_name":"Courant Institute of Mathematical Sciences","ror":"https://ror.org/037tm7f56","country_code":"US","type":"education","lineage":["https://openalex.org/I36672615","https://openalex.org/I57206974"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sukhbaatar, Sainbayar","raw_affiliation_strings":["Dept. of Computer Science Courant Institute , New York University","Department of Computer Science, Courant Institute, New York University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science Courant Institute , New York University","institution_ids":["https://openalex.org/I36672615","https://openalex.org/I57206974"]},{"raw_affiliation_string":"Department of Computer Science, Courant Institute, New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053145694","display_name":"Arthur D. Szlam","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Szlam, Arthur","raw_affiliation_strings":["Facebook AI Research New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research New York","institution_ids":["https://openalex.org/I4210114444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089960673","display_name":"Rob Fergus","orcid":"https://orcid.org/0009-0005-3077-2495","observed_orcids":["https://orcid.org/0009-0005-3077-2495"]},"institutions":[{"id":"https://openalex.org/I4210114444","display_name":"Meta (United States)","ror":"https://ror.org/01zbnvs85","country_code":"US","type":"company","lineage":["https://openalex.org/I4210114444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fergus, Rob","raw_affiliation_strings":["Facebook AI Research New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research New York","institution_ids":["https://openalex.org/I4210114444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":649,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"29","issue":null,"first_page":"2252","last_page":"2260"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9779999852180481,"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":0.9779999852180481,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.010099999606609344,"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":0.000699999975040555,"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/neural-network-agents","display_name":"neural network agents","score":0.4830000102519989},{"id":"https://openalex.org/keywords/backpropagation","display_name":"backpropagation","score":0.6669999957084656},{"id":"https://openalex.org/keywords/continuous-communication","display_name":"continuous communication","score":0.6489999890327454}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8121151328086853},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.7481160759925842},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7368431091308594},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.7006750106811523},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.5689418911933899},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5357204079627991},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.46961766481399536},{"id":"https://openalex.org/C12269588","wikidata":"https://www.wikidata.org/wiki/Q132364","display_name":"Communications protocol","level":2,"score":0.42040857672691345},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4193337559700012},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37719136476516724},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36780524253845215},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07302984595298767},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.05814525485038757},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:1605.07736","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1605.07736","pdf_url":"https://arxiv.org/pdf/1605.07736","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":"mag:2402402867","doi":null,"is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1605.07736","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1605.07736","doi":"https://doi.org/10.48550/arxiv.1605.07736","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1605.07736","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"},{"id":"mag:2964338167","doi":null,"is_oa":false,"landing_page_url":"http://papers.nips.cc/paper/6398-learning-multiagent-communication-with-backpropagation.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1605.07736","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1605.07736","pdf_url":"https://arxiv.org/pdf/1605.07736","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":[{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2402402867.pdf","grobid_xml":"https://content.openalex.org/works/W2402402867.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W6043852","https://openalex.org/W1450304033","https://openalex.org/W1507591516","https://openalex.org/W1515851193","https://openalex.org/W1560074431","https://openalex.org/W1574700590","https://openalex.org/W1607316222","https://openalex.org/W1641379095","https://openalex.org/W1793121960","https://openalex.org/W1947291763","https://openalex.org/W1973039793","https://openalex.org/W2012812921","https://openalex.org/W2043931021","https://openalex.org/W2099618002","https://openalex.org/W2116341502","https://openalex.org/W2119717200","https://openalex.org/W2126222949","https://openalex.org/W2128453677","https://openalex.org/W2133585753","https://openalex.org/W2134779831","https://openalex.org/W2145067550","https://openalex.org/W2145339207","https://openalex.org/W2148831627","https://openalex.org/W2151210636","https://openalex.org/W2156094048","https://openalex.org/W2160643434","https://openalex.org/W2172933221","https://openalex.org/W2173051530","https://openalex.org/W2174196774","https://openalex.org/W2244807774","https://openalex.org/W2255045308","https://openalex.org/W2257979135","https://openalex.org/W2293453011","https://openalex.org/W2296073425","https://openalex.org/W2962790689","https://openalex.org/W2964121744","https://openalex.org/W2964161785"],"related_works":["https://openalex.org/W2906394285","https://openalex.org/W2912158309","https://openalex.org/W4385637469","https://openalex.org/W3034977961","https://openalex.org/W4396944845","https://openalex.org/W3029065915","https://openalex.org/W2943556788","https://openalex.org/W2933085415","https://openalex.org/W2626305543","https://openalex.org/W2803155336"],"abstract_inverted_index":{"Many":[0],"tasks":[1],"in":[2],"AI":[3],"require":[4],"the":[5,11,50,70,73,97,101,110],"collaboration":[6],"of":[7,46,67,72],"multiple":[8,47],"agents.":[9],"Typically,":[10],"communication":[12,38,51],"protocol":[13],"between":[14,52],"agents":[15,48,74,86],"is":[16,54,93],"manually":[17],"specified":[18],"and":[19,49,87],"not":[20],"altered":[21],"during":[22],"training.":[23],"In":[24,89],"this":[25,61],"paper":[26],"we":[27],"explore":[28],"a":[29,64],"simple":[30,104],"neural":[31],"model,":[32],"called":[33],"CommNet,":[34],"that":[35],"uses":[36],"continuous":[37],"for":[39,108],"fully":[40],"cooperative":[41],"tasks.":[42],"The":[43],"model":[44,62],"consists":[45],"them":[53],"learned":[55],"alongside":[56],"their":[57],"policy.":[58],"We":[59],"apply":[60],"to":[63,75,77,95],"diverse":[65],"set":[66],"tasks,":[68],"demonstrating":[69],"ability":[71],"learn":[76],"communicate":[78],"amongst":[79],"themselves,":[80],"yielding":[81],"improved":[82],"performance":[83],"over":[84],"non-communicative":[85],"baselines.":[88],"some":[90],"cases,":[91],"it":[92],"possible":[94],"interpret":[96],"language":[98],"devised":[99],"by":[100],"agents,":[102],"revealing":[103],"but":[105],"effective":[106],"strategies":[107],"solving":[109],"task":[111],"at":[112],"hand.":[113]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":52},{"year":2024,"cited_by_count":93},{"year":2023,"cited_by_count":103},{"year":2022,"cited_by_count":85},{"year":2021,"cited_by_count":84},{"year":2020,"cited_by_count":73},{"year":2019,"cited_by_count":71},{"year":2018,"cited_by_count":38},{"year":2017,"cited_by_count":27},{"year":2016,"cited_by_count":9}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-06-24T00:00:00"}