{"id":"https://openalex.org/W2977730262","doi":"https://doi.org/10.1109/ijcnn.2019.8852293","title":"Multi-Agent Deep Reinforcement Learning with Emergent Communication","display_name":"Multi-Agent Deep Reinforcement Learning with Emergent Communication","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2977730262","doi":"https://doi.org/10.1109/ijcnn.2019.8852293","mag":"2977730262"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2019.8852293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","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/A5081040128","display_name":"David Sim\u00f5es","orcid":"https://orcid.org/0000-0002-6464-8012"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"David Simoes","raw_affiliation_strings":["LIACC - Artificial Intelligence and Computer Science Lab, Oporto, Portugal"],"affiliations":[{"raw_affiliation_string":"LIACC - Artificial Intelligence and Computer Science Lab, Oporto, Portugal","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055569781","display_name":"Nuno Lau","orcid":"https://orcid.org/0000-0003-0513-158X"},"institutions":[{"id":"https://openalex.org/I60858718","display_name":"University of Aveiro","ror":"https://ror.org/00nt41z93","country_code":"PT","type":"education","lineage":["https://openalex.org/I60858718"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Nuno Lau","raw_affiliation_strings":["IEETA - Institute of Electronics and Informatics Engineering of Aveiro, University of Aveiro, Portugal"],"affiliations":[{"raw_affiliation_string":"IEETA - Institute of Electronics and Informatics Engineering of Aveiro, University of Aveiro, Portugal","institution_ids":["https://openalex.org/I60858718"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089812166","display_name":"Lu\u00eds Paulo Reis","orcid":"https://orcid.org/0000-0002-4709-1718"},"institutions":[{"id":"https://openalex.org/I182534213","display_name":"Universidade do Porto","ror":"https://ror.org/043pwc612","country_code":"PT","type":"education","lineage":["https://openalex.org/I182534213"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Luis Paulo Reis","raw_affiliation_strings":["DEI/FEUP - Informatics Engineering Department, University of Porto, Portugal"],"affiliations":[{"raw_affiliation_string":"DEI/FEUP - Informatics Engineering Department, University of Porto, Portugal","institution_ids":["https://openalex.org/I182534213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081040128"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9801,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.82457502,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"323","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9839000105857849,"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":0.9761999845504761,"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/observability","display_name":"Observability","score":0.9670937061309814},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9040096998214722},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7666369676589966},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5752091407775879},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5335614681243896},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.462760865688324},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.45305174589157104},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4274802803993225},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3745627999305725},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16530999541282654},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07958129048347473}],"concepts":[{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.9670937061309814},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9040096998214722},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7666369676589966},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5752091407775879},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5335614681243896},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.462760865688324},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.45305174589157104},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4274802803993225},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3745627999305725},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16530999541282654},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07958129048347473},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2019.8852293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W65045497","https://openalex.org/W1191599655","https://openalex.org/W1498436455","https://openalex.org/W1521003796","https://openalex.org/W1522301498","https://openalex.org/W1528676759","https://openalex.org/W1533861849","https://openalex.org/W1534818666","https://openalex.org/W1542941925","https://openalex.org/W1815076433","https://openalex.org/W1993688584","https://openalex.org/W2104602264","https://openalex.org/W2107280071","https://openalex.org/W2119717200","https://openalex.org/W2160851181","https://openalex.org/W2164397152","https://openalex.org/W2281257727","https://openalex.org/W2395575420","https://openalex.org/W2416279312","https://openalex.org/W2602275733","https://openalex.org/W2603266952","https://openalex.org/W2604283518","https://openalex.org/W2617547828","https://openalex.org/W2758244370","https://openalex.org/W2962852262","https://openalex.org/W2962938168","https://openalex.org/W2963000099","https://openalex.org/W2963881016","https://openalex.org/W2964043796","https://openalex.org/W2964338167","https://openalex.org/W4231000797","https://openalex.org/W4252284432","https://openalex.org/W4295846245","https://openalex.org/W6602668577","https://openalex.org/W6627932998","https://openalex.org/W6631137000","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6638545294","https://openalex.org/W6675811377","https://openalex.org/W6692846177","https://openalex.org/W6712181171","https://openalex.org/W6713411898","https://openalex.org/W6731193076","https://openalex.org/W6736622323","https://openalex.org/W6744474358"],"related_works":["https://openalex.org/W2046459260","https://openalex.org/W2765830098","https://openalex.org/W2967463586","https://openalex.org/W1971989957","https://openalex.org/W2517338020","https://openalex.org/W3157641275","https://openalex.org/W4312300846","https://openalex.org/W4206221578","https://openalex.org/W3029572990","https://openalex.org/W2615757685"],"abstract_inverted_index":{"When":[0],"compared":[1],"with":[2,140],"their":[3],"single-agent":[4],"counterpart,":[5],"multi-agent":[6,58],"systems":[7],"have":[8],"an":[9],"additional":[10],"set":[11],"of":[12,84,137],"challenges":[13],"for":[14,65,73,118],"reinforcement":[15,31,53],"learning":[16,32,54],"algorithms,":[17],"including":[18],"increased":[19],"complexity,":[20],"non-stationary":[21],"environments,":[22],"credit":[23],"assignment,":[24],"partial":[25],"observability,":[26],"and":[27,68,75,96,114],"achieving":[28],"coordination.":[29,78],"Deep":[30],"has":[33],"been":[34],"shown":[35],"to":[36,109],"achieve":[37],"successful":[38],"policies":[39,64,113],"through":[40],"implicit":[41],"coordination,":[42],"but":[43],"does":[44],"not":[45],"handle":[46],"partial-observability.":[47],"This":[48],"paper":[49],"describes":[50],"a":[51],"deep":[52],"algorithm,":[55],"based":[56],"on":[57],"actor-critic,":[59],"that":[60,71,98,133],"simultaneously":[61],"learns":[62],"action":[63],"each":[66],"agent,":[67],"communication":[69,116,142],"protocols":[70,117],"compensate":[72],"partial-observability":[74],"help":[76],"enforce":[77],"We":[79,103,123],"also":[80,124],"research":[81],"the":[82,100],"effects":[83],"noisy":[85,141],"communication,":[86,138],"where":[87],"messages":[88],"can":[89],"be":[90],"late,":[91],"lost,":[92],"noisy,":[93],"or":[94],"jumbled,":[95],"how":[97,105,126],"affects":[99],"learned":[101],"policies.":[102],"show":[104,125],"agents":[106],"are":[107],"able":[108],"learn":[110],"both":[111],"high-level":[112],"complex":[115],"several":[119],"different":[120],"partially-observable":[121],"environments.":[122],"our":[127],"proposal":[128],"outperforms":[129],"other":[130],"state-of-the-art":[131],"algorithms":[132],"don't":[134],"take":[135],"advantage":[136],"even":[139],"channels.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}