{"id":"https://openalex.org/W3132645056","doi":"https://doi.org/10.1109/icra46639.2022.9812285","title":"Learning Emergent Discrete Message Communication for Cooperative Reinforcement Learning","display_name":"Learning Emergent Discrete Message Communication for Cooperative Reinforcement Learning","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W3132645056","doi":"https://doi.org/10.1109/icra46639.2022.9812285","mag":"3132645056"},"language":"en","primary_location":{"id":"doi:10.1109/icra46639.2022.9812285","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9812285","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100359839","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0003-1205-8632"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["Stanford University,Department of Aeronautics and Astronautics","Department of Aeronautics and Astronautics, Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University,Department of Aeronautics and Astronautics","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Aeronautics and Astronautics, Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069248471","display_name":"Yutai Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yutai Zhou","raw_affiliation_strings":["Massachusetts Institute of Technology,Lincoln Laboratory","Lincoln Laboratory, Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Lincoln Laboratory","institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]},{"raw_affiliation_string":"Lincoln Laboratory, Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005883173","display_name":"Ross Allen","orcid":"https://orcid.org/0000-0003-3730-641X"},"institutions":[{"id":"https://openalex.org/I4210122954","display_name":"MIT Lincoln Laboratory","ror":"https://ror.org/022z6jk58","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ross Allen","raw_affiliation_strings":["Massachusetts Institute of Technology,Lincoln Laboratory","Lincoln Laboratory, Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology,Lincoln Laboratory","institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]},{"raw_affiliation_string":"Lincoln Laboratory, Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I4210122954","https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068326377","display_name":"Mykel J. Kochenderfer","orcid":"https://orcid.org/0000-0002-7238-9663"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mykel J. Kochenderfer","raw_affiliation_strings":["Stanford University,Department of Aeronautics and Astronautics","Department of Aeronautics and Astronautics, Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University,Department of Aeronautics and Astronautics","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Department of Aeronautics and Astronautics, Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"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":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5511","last_page":"5517"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.991599977016449,"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/T10028","display_name":"Topic Modeling","score":0.9739000201225281,"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/interpretability","display_name":"Interpretability","score":0.9080840349197388},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7462296485900879},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6721614599227905},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.5291106104850769},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5268591642379761},{"id":"https://openalex.org/keywords/models-of-communication","display_name":"Models of communication","score":0.4719644784927368},{"id":"https://openalex.org/keywords/human-communication","display_name":"Human communication","score":0.4525638222694397},{"id":"https://openalex.org/keywords/communications-system","display_name":"Communications system","score":0.4426746070384979},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.37606871128082275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36913496255874634},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3298821449279785},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.23797744512557983},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.10951158404350281}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9080840349197388},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7462296485900879},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6721614599227905},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.5291106104850769},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5268591642379761},{"id":"https://openalex.org/C158156997","wikidata":"https://www.wikidata.org/wiki/Q1416645","display_name":"Models of communication","level":2,"score":0.4719644784927368},{"id":"https://openalex.org/C30539005","wikidata":"https://www.wikidata.org/wiki/Q1066689","display_name":"Human communication","level":2,"score":0.4525638222694397},{"id":"https://openalex.org/C101765175","wikidata":"https://www.wikidata.org/wiki/Q577764","display_name":"Communications system","level":2,"score":0.4426746070384979},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37606871128082275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36913496255874634},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3298821449279785},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.23797744512557983},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.10951158404350281},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra46639.2022.9812285","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9812285","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6600000262260437,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1902237438","https://openalex.org/W2187089797","https://openalex.org/W2267186426","https://openalex.org/W2337822097","https://openalex.org/W2736601468","https://openalex.org/W2747213132","https://openalex.org/W2756196406","https://openalex.org/W2768629321","https://openalex.org/W2803155336","https://openalex.org/W2894976951","https://openalex.org/W2914351253","https://openalex.org/W2947287992","https://openalex.org/W2963147362","https://openalex.org/W2963155490","https://openalex.org/W2963170456","https://openalex.org/W2963184621","https://openalex.org/W2963403868","https://openalex.org/W2963588154","https://openalex.org/W2963717208","https://openalex.org/W2964014087","https://openalex.org/W2964338167","https://openalex.org/W2968378480","https://openalex.org/W2981165461","https://openalex.org/W2995937146","https://openalex.org/W3035250588","https://openalex.org/W3036295212","https://openalex.org/W3090386093","https://openalex.org/W3173782550","https://openalex.org/W4288416871","https://openalex.org/W4289100326","https://openalex.org/W4289363497","https://openalex.org/W4297795114","https://openalex.org/W4385245566","https://openalex.org/W6627932998","https://openalex.org/W6713411898","https://openalex.org/W6739901393","https://openalex.org/W6747595794","https://openalex.org/W6751139674","https://openalex.org/W6755069753","https://openalex.org/W6755542948","https://openalex.org/W6757784512","https://openalex.org/W6758763022","https://openalex.org/W6760290758","https://openalex.org/W6768539364","https://openalex.org/W6779416026"],"related_works":["https://openalex.org/W2135105983","https://openalex.org/W2924910580","https://openalex.org/W2115237264","https://openalex.org/W2951568860","https://openalex.org/W4288413083","https://openalex.org/W2107729822","https://openalex.org/W4307317035","https://openalex.org/W2963943254","https://openalex.org/W4312101228","https://openalex.org/W2479429978"],"abstract_inverted_index":{"Communication":[0],"is":[1,70],"an":[2],"important":[3],"factor":[4],"that":[5,81],"en-ables":[6],"agents":[7,34],"to":[8,35,59,64,88],"work":[9,18],"cooperatively":[10],"in":[11],"multi-agent":[12],"reinforcement":[13],"learning":[14],"(MARL)":[15],"contexts.":[16],"Prior":[17],"used":[19,106],"continuous":[20,89],"message":[21,41,68,83,90,100],"communication":[22,42,69,84,91,101],"whose":[23],"high":[24],"representational":[25],"capacity":[26],"comes":[27],"at":[28],"the":[29,46],"expense":[30],"of":[31],"interpretability.":[32],"Allowing":[33],"learn":[36],"their":[37],"own":[38],"discrete":[39,61,82],"emergent":[40],"protocols":[43,102],"can":[44,103],"increase":[45],"interpretability":[47],"for":[48,107],"human":[49,65],"designers":[50],"and":[51],"other":[52],"agents.":[53],"This":[54],"paper":[55],"proposes":[56],"a":[57,73,94],"method":[58],"generate":[60],"messages":[62],"analogous":[63],"languages.":[66],"Discrete":[67,99],"achieved":[71],"by":[72],"broadcast-and-listen":[74],"mecha-nism":[75],"based":[76],"on":[77],"self-attention.":[78],"We":[79],"show":[80],"has":[85],"performance":[86],"comparable":[87],"but":[92],"with":[93],"much":[95],"smaller":[96],"vocabulary":[97],"size.":[98],"potentially":[104],"be":[105],"human-agent":[108],"interaction.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
