{"id":"https://openalex.org/W4390638728","doi":"https://doi.org/10.1007/s10458-023-09633-6","title":"A survey of multi-agent deep reinforcement learning with communication","display_name":"A survey of multi-agent deep reinforcement learning with communication","publication_year":2024,"publication_date":"2024-01-06","ids":{"openalex":"https://openalex.org/W4390638728","doi":"https://doi.org/10.1007/s10458-023-09633-6"},"language":"en","primary_location":{"id":"doi:10.1007/s10458-023-09633-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10458-023-09633-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10458-023-09633-6.pdf","source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10458-023-09633-6.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053438680","display_name":"Changxi Zhu","orcid":"https://orcid.org/0000-0002-2910-5506"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Changxi Zhu","raw_affiliation_strings":["Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-2910-5506","affiliations":[{"raw_affiliation_string":"Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028760842","display_name":"Mehdi Dastani","orcid":"https://orcid.org/0000-0002-4641-4087"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Mehdi Dastani","raw_affiliation_strings":["Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107808323","display_name":"Shihan Wang","orcid":"https://orcid.org/0000-0001-5971-7522"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Shihan Wang","raw_affiliation_strings":["Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands","institution_ids":["https://openalex.org/I193662353"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5028760842","https://openalex.org/A5053438680","https://openalex.org/A5107808323"],"corresponding_institution_ids":["https://openalex.org/I193662353"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":34.3369,"has_fulltext":true,"cited_by_count":114,"citation_normalized_percentile":{"value":0.99825101,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"38","issue":"1","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":0.9993000030517578,"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":0.9993000030517578,"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":0.9950000047683716,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9800999760627747,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8308247923851013},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7008196115493774},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.6547604203224182},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5539820194244385},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5426791310310364},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.5125460624694824},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.457361102104187},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.44863057136535645},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4043992757797241},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3261869549751282},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16429021954536438},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05568781495094299}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8308247923851013},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7008196115493774},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.6547604203224182},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5539820194244385},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5426791310310364},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.5125460624694824},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.457361102104187},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.44863057136535645},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4043992757797241},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3261869549751282},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16429021954536438},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05568781495094299},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10458-023-09633-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10458-023-09633-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10458-023-09633-6.pdf","source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},{"id":"pmh:oai:dspace.library.uu.nl:1874/435362","is_oa":true,"landing_page_url":"https://dspace.library.uu.nl/handle/1874/435362","pdf_url":null,"source":{"id":"https://openalex.org/S4306401649","display_name":"Utrecht University Repository (Utrecht University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193662353","host_organization_name":"Utrecht University","host_organization_lineage":["https://openalex.org/I193662353"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1007/s10458-023-09633-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10458-023-09633-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10458-023-09633-6.pdf","source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390638728.pdf"},"referenced_works_count":119,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1191599655","https://openalex.org/W1528676759","https://openalex.org/W1641379095","https://openalex.org/W1691676988","https://openalex.org/W1908253641","https://openalex.org/W1970554353","https://openalex.org/W1974812331","https://openalex.org/W1977655452","https://openalex.org/W2002072045","https://openalex.org/W2064675550","https://openalex.org/W2096145798","https://openalex.org/W2099618002","https://openalex.org/W2104602264","https://openalex.org/W2107544712","https://openalex.org/W2141017267","https://openalex.org/W2145339207","https://openalex.org/W2147492008","https://openalex.org/W2156578004","https://openalex.org/W2172933221","https://openalex.org/W2292533394","https://openalex.org/W2395575420","https://openalex.org/W2402402867","https://openalex.org/W2530849036","https://openalex.org/W2547416798","https://openalex.org/W2592798481","https://openalex.org/W2602275733","https://openalex.org/W2604283518","https://openalex.org/W2617547828","https://openalex.org/W2619383789","https://openalex.org/W2621379712","https://openalex.org/W2623431351","https://openalex.org/W2635153012","https://openalex.org/W2747213132","https://openalex.org/W2749807327","https://openalex.org/W2766447205","https://openalex.org/W2773525213","https://openalex.org/W2776126823","https://openalex.org/W2794643322","https://openalex.org/W2803155336","https://openalex.org/W2807741983","https://openalex.org/W2809665100","https://openalex.org/W2891757722","https://openalex.org/W2903006607","https://openalex.org/W2903475313","https://openalex.org/W2904455790","https://openalex.org/W2906394285","https://openalex.org/W2907606902","https://openalex.org/W2908261578","https://openalex.org/W2914351253","https://openalex.org/W2919115771","https://openalex.org/W2942454454","https://openalex.org/W2946606218","https://openalex.org/W2947748865","https://openalex.org/W2948342290","https://openalex.org/W2949464762","https://openalex.org/W2960876848","https://openalex.org/W2964937097","https://openalex.org/W2970687683","https://openalex.org/W2971027212","https://openalex.org/W2971094937","https://openalex.org/W2979408248","https://openalex.org/W2981038142","https://openalex.org/W2981641565","https://openalex.org/W2988210831","https://openalex.org/W2988490775","https://openalex.org/W2991046523","https://openalex.org/W2995815314","https://openalex.org/W2996525917","https://openalex.org/W2997502221","https://openalex.org/W2997556607","https://openalex.org/W2998367975","https://openalex.org/W2998489261","https://openalex.org/W3009077467","https://openalex.org/W3014436489","https://openalex.org/W3016815617","https://openalex.org/W3017287770","https://openalex.org/W3029971428","https://openalex.org/W3033076904","https://openalex.org/W3034622111","https://openalex.org/W3034977961","https://openalex.org/W3092226501","https://openalex.org/W3096358451","https://openalex.org/W3100019413","https://openalex.org/W3101572197","https://openalex.org/W3107615218","https://openalex.org/W3118993660","https://openalex.org/W3122959491","https://openalex.org/W3126457215","https://openalex.org/W3128366769","https://openalex.org/W3132143885","https://openalex.org/W3137027505","https://openalex.org/W3156295478","https://openalex.org/W3171124906","https://openalex.org/W3173215816","https://openalex.org/W3175812804","https://openalex.org/W3187260173","https://openalex.org/W3189582301","https://openalex.org/W3189960040","https://openalex.org/W3194351817","https://openalex.org/W3205480420","https://openalex.org/W3208045904","https://openalex.org/W4255104966","https://openalex.org/W4281653158","https://openalex.org/W4283789768","https://openalex.org/W4286744073","https://openalex.org/W4294032666","https://openalex.org/W4306179383","https://openalex.org/W4319984167","https://openalex.org/W6683195989","https://openalex.org/W6729448088","https://openalex.org/W6735677848","https://openalex.org/W6748307079","https://openalex.org/W6755542948","https://openalex.org/W6758846586","https://openalex.org/W6760290758","https://openalex.org/W6768539364","https://openalex.org/W6774262652","https://openalex.org/W6781750019"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2089013912","https://openalex.org/W2076061571","https://openalex.org/W1987513656","https://openalex.org/W2145821588"],"abstract_inverted_index":{"Abstract":[0],"Communication":[1],"is":[2,80],"an":[3],"effective":[4],"mechanism":[5],"for":[6,163],"coordinating":[7],"the":[8,17,25,36,68,104,150,173],"behaviors":[9],"of":[10,16,27,51,71,83,111,172],"multiple":[11],"agents,":[12],"broadening":[13],"their":[14,22,42],"views":[15],"environment,":[18],"and":[19,40,86,91,107,120,143],"to":[20,54,58,89],"support":[21],"collaborations.":[23],"In":[24,96],"field":[26,106],"multi-agent":[28,122],"deep":[29],"reinforcement":[30,123],"learning":[31,38,124],"(MADRL),":[32],"agents":[33,56],"can":[34,47,114,139],"improve":[35],"overall":[37],"performance":[39],"achieve":[41],"objectives":[43],"by":[44],"communication.":[45],"Agents":[46],"communicate":[48],"various":[49,109],"types":[50],"messages,":[52],"either":[53],"all":[55],"or":[57,62],"specific":[59,65],"agent":[60],"groups,":[61],"conditioned":[63],"on":[64],"constraints.":[66],"With":[67,126],"growing":[69],"body":[70],"research":[72],"work":[73],"in":[74,103,118,129],"MADRL":[75],"with":[76],"communication":[77,112],"(Comm-MADRL),":[78],"there":[79],"a":[81,84,116],"lack":[82],"systematic":[85],"structural":[87],"approach":[88],"distinguish":[90],"classify":[92],"existing":[93,147],"Comm-MADRL":[94,105,137,166],"approaches.":[95],"this":[97],"paper,":[98],"we":[99,131,153],"survey":[100],"recent":[101],"works":[102,148],"consider":[108],"aspects":[110,128],"that":[113],"play":[115],"role":[117],"designing":[119,164],"developing":[121],"systems.":[125],"these":[127],"mind,":[130],"propose":[132,159],"9":[133],"dimensions":[134],"along":[135],"which":[136],"approaches":[138],"be":[140],"analyzed,":[141],"developed,":[142],"compared.":[144],"By":[145],"projecting":[146],"into":[149],"multi-dimensional":[151],"space,":[152],"discover":[154],"interesting":[155],"trends.":[156],"We":[157],"also":[158],"some":[160],"novel":[161],"directions":[162],"future":[165],"systems":[167],"through":[168],"exploring":[169],"possible":[170],"combinations":[171],"dimensions.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":31},{"year":2025,"cited_by_count":66},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}