{"id":"https://openalex.org/W4306786778","doi":"https://doi.org/10.1007/s10462-022-10299-x","title":"Deep multiagent reinforcement learning: challenges and directions","display_name":"Deep multiagent reinforcement learning: challenges and directions","publication_year":2022,"publication_date":"2022-10-19","ids":{"openalex":"https://openalex.org/W4306786778","doi":"https://doi.org/10.1007/s10462-022-10299-x"},"language":"en","primary_location":{"id":"doi:10.1007/s10462-022-10299-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-022-10299-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-022-10299-x.pdf","source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"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":"Artificial Intelligence Review","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/s10462-022-10299-x.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010989991","display_name":"Annie Wong","orcid":"https://orcid.org/0000-0002-8698-974X"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Annie Wong","raw_affiliation_strings":["Leiden Institute of Advanced Computer Science, Leiden University, Leiden, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science, Leiden University, Leiden, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062646838","display_name":"Thomas B\u00e4ck","orcid":"https://orcid.org/0000-0001-6768-1478"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Thomas B\u00e4ck","raw_affiliation_strings":["Leiden Institute of Advanced Computer Science, Leiden University, Leiden, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science, Leiden University, Leiden, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004203337","display_name":"Anna V. Kononova","orcid":"https://orcid.org/0000-0002-4138-7024"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Anna V. Kononova","raw_affiliation_strings":["Leiden Institute of Advanced Computer Science, Leiden University, Leiden, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science, Leiden University, Leiden, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085542421","display_name":"Aske Plaat","orcid":"https://orcid.org/0000-0001-7202-3322"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Aske Plaat","raw_affiliation_strings":["Leiden Institute of Advanced Computer Science, Leiden University, Leiden, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Leiden Institute of Advanced Computer Science, Leiden University, Leiden, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5010989991"],"corresponding_institution_ids":["https://openalex.org/I121797337"],"apc_list":{"value":2490,"currency":"EUR","value_usd":3090},"apc_paid":{"value":2490,"currency":"EUR","value_usd":3090},"fwci":20.1297,"has_fulltext":true,"cited_by_count":160,"citation_normalized_percentile":{"value":0.99534178,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"56","issue":"6","first_page":"5023","last_page":"5056"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9908999800682068,"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":0.9908999800682068,"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/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.97079998254776,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8200342655181885},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.759048342704773},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5706750750541687},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5324417352676392},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5120113492012024},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4947340190410614},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4243229925632477},{"id":"https://openalex.org/keywords/intelligent-agent","display_name":"Intelligent agent","score":0.419086217880249}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8200342655181885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.759048342704773},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5706750750541687},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5324417352676392},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5120113492012024},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4947340190410614},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4243229925632477},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.419086217880249},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s10462-022-10299-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-022-10299-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-022-10299-x.pdf","source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"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":"Artificial Intelligence Review","raw_type":"journal-article"},{"id":"pmh:oai:scholarlypublications.universiteitleiden.nl:item_3486272","is_oa":true,"landing_page_url":"https://hdl.handle.net/1887/3486272","pdf_url":null,"source":{"id":"https://openalex.org/S4306400850","display_name":"Leiden Repository (Leiden University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I121797337","host_organization_name":"Leiden University","host_organization_lineage":["https://openalex.org/I121797337"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Artificial Intelligence Review","raw_type":"Article / Letter to editor"},{"id":"pmh:ul:oai:scholarlypublications.universiteitleiden.nl:item_3486272","is_oa":true,"landing_page_url":"http://hdl.handle.net/1887/3486272","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Artificial Intelligence Review. SPRINGER","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/s10462-022-10299-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-022-10299-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-022-10299-x.pdf","source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"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":"Artificial Intelligence Review","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4306786778.pdf","grobid_xml":"https://content.openalex.org/works/W4306786778.grobid-xml"},"referenced_works_count":125,"referenced_works":["https://openalex.org/W107583932","https://openalex.org/W169931978","https://openalex.org/W285701945","https://openalex.org/W329015778","https://openalex.org/W1192553058","https://openalex.org/W1528459956","https://openalex.org/W1542941925","https://openalex.org/W1641379095","https://openalex.org/W1914583973","https://openalex.org/W1968093658","https://openalex.org/W2006791053","https://openalex.org/W2009303086","https://openalex.org/W2010931158","https://openalex.org/W2011418219","https://openalex.org/W2019714294","https://openalex.org/W2020009149","https://openalex.org/W2024998154","https://openalex.org/W2045031658","https://openalex.org/W2046376809","https://openalex.org/W2062663664","https://openalex.org/W2076337359","https://openalex.org/W2088956500","https://openalex.org/W2095564494","https://openalex.org/W2099618002","https://openalex.org/W2119232430","https://openalex.org/W2120327309","https://openalex.org/W2132994929","https://openalex.org/W2141538250","https://openalex.org/W2145339207","https://openalex.org/W2159071801","https://openalex.org/W2160519132","https://openalex.org/W2172968643","https://openalex.org/W2242842357","https://openalex.org/W2257979135","https://openalex.org/W2292533394","https://openalex.org/W2322316662","https://openalex.org/W2519481221","https://openalex.org/W2546571074","https://openalex.org/W2559655401","https://openalex.org/W2572491855","https://openalex.org/W2574978968","https://openalex.org/W2575731723","https://openalex.org/W2583993537","https://openalex.org/W2589804868","https://openalex.org/W2603266952","https://openalex.org/W2617547828","https://openalex.org/W2746553466","https://openalex.org/W2747329762","https://openalex.org/W2758442112","https://openalex.org/W2766447205","https://openalex.org/W2768629321","https://openalex.org/W2771779761","https://openalex.org/W2773381986","https://openalex.org/W2783268317","https://openalex.org/W2788125442","https://openalex.org/W2794711922","https://openalex.org/W2804360326","https://openalex.org/W2810602713","https://openalex.org/W2877093712","https://openalex.org/W2904455790","https://openalex.org/W2908261578","https://openalex.org/W2912222576","https://openalex.org/W2915117209","https://openalex.org/W2919115771","https://openalex.org/W2921955147","https://openalex.org/W2952258289","https://openalex.org/W2960876848","https://openalex.org/W2962764167","https://openalex.org/W2962887844","https://openalex.org/W2962975462","https://openalex.org/W2963041255","https://openalex.org/W2963157343","https://openalex.org/W2963390684","https://openalex.org/W2963658727","https://openalex.org/W2964289358","https://openalex.org/W2964937097","https://openalex.org/W2976108375","https://openalex.org/W2981038142","https://openalex.org/W2982316857","https://openalex.org/W2989847975","https://openalex.org/W2990850608","https://openalex.org/W2991046523","https://openalex.org/W2994214683","https://openalex.org/W3022808291","https://openalex.org/W3029901419","https://openalex.org/W3038150710","https://openalex.org/W3089506933","https://openalex.org/W3091492359","https://openalex.org/W3095556657","https://openalex.org/W3098184036","https://openalex.org/W3099518626","https://openalex.org/W3100789280","https://openalex.org/W3100944043","https://openalex.org/W3101552411","https://openalex.org/W3103752844","https://openalex.org/W3106649810","https://openalex.org/W3118210634","https://openalex.org/W3129616587","https://openalex.org/W3133735442","https://openalex.org/W3134916406","https://openalex.org/W3143966685","https://openalex.org/W3147079603","https://openalex.org/W3156295478","https://openalex.org/W3166816823","https://openalex.org/W3174282399","https://openalex.org/W3176265013","https://openalex.org/W3177669185","https://openalex.org/W3197328309","https://openalex.org/W3206082228","https://openalex.org/W4212774754","https://openalex.org/W4231809946","https://openalex.org/W4243655891","https://openalex.org/W4245903027","https://openalex.org/W4252284432","https://openalex.org/W4300576158","https://openalex.org/W6600020652","https://openalex.org/W6600135713","https://openalex.org/W6600194071","https://openalex.org/W6600339457","https://openalex.org/W6608803649","https://openalex.org/W6609795279","https://openalex.org/W6768386388","https://openalex.org/W6776992756","https://openalex.org/W6814003322","https://openalex.org/W6829155664"],"related_works":["https://openalex.org/W3074294383","https://openalex.org/W4206669594","https://openalex.org/W2156763598","https://openalex.org/W4200522217","https://openalex.org/W4301400512","https://openalex.org/W2018749324","https://openalex.org/W2134281179","https://openalex.org/W2169620061","https://openalex.org/W120558734","https://openalex.org/W2160164772"],"abstract_inverted_index":{"Abstract":[0],"This":[1],"paper":[2],"surveys":[3],"the":[4,31,48,59,65,122],"field":[5],"of":[6,14,85,124],"deep":[7,15],"multiagent":[8,36,68,149,155,176],"reinforcement":[9],"learning":[10],"(RL).":[11],"The":[12],"combination":[13],"neural":[16],"networks":[17],"with":[18,39,166],"RL":[19,156],"has":[20],"gained":[21],"increased":[22],"traction":[23],"in":[24,148,175],"recent":[25],"years":[26],"and":[27,57,71,75,90,98,131,140],"is":[28,42],"slowly":[29],"shifting":[30],"focus":[32],"from":[33,129],"single-agent":[34],"to":[35,115,120,142,157,170],"environments.":[37],"Dealing":[38],"multiple":[40,53],"agents":[41,144],"inherently":[43],"more":[44,84],"complex":[45],"as":[46,138],"(a)":[47],"future":[49,160],"rewards":[50],"depend":[51],"on":[52,108],"players\u2019":[54],"joint":[55],"actions":[56],"(b)":[58],"computational":[60,105],"complexity":[61],"increases.":[62],"We":[63,101,151],"present":[64],"most":[66],"common":[67],"problem":[69],"representations":[70],"their":[72],"main":[73],"challenges,":[74],"identify":[76],"five":[77],"research":[78,161],"areas":[79],"that":[80,103],"address":[81,163],"one":[82],"or":[83,111,126],"these":[86,164],"challenges:":[87],"centralised":[88],"training":[89],"decentralised":[91],"execution,":[92],"opponent":[93],"modelling,":[94],"communication,":[95],"efficient":[96],"coordination,":[97,141],"reward":[99],"shaping.":[100],"find":[102],"many":[104],"studies":[106],"rely":[107],"unrealistic":[109],"assumptions":[110],"are":[112],"not":[113],"generalisable":[114],"other":[116],"settings;":[117],"they":[118],"struggle":[119],"overcome":[121],"curse":[123],"dimensionality":[125],"nonstationarity.":[127],"Approaches":[128],"psychology":[130],"sociology":[132],"capture":[133],"promising":[134],"relevant":[135],"behaviours,":[136],"such":[137],"communication":[139],"help":[143],"achieve":[145],"better":[146],"performance":[147],"settings.":[150],"suggest":[152],"that,":[153],"for":[154],"be":[158],"successful,":[159],"should":[162],"challenges":[165],"an":[167],"interdisciplinary":[168],"approach":[169],"open":[171],"up":[172],"new":[173],"possibilities":[174],"RL.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":15},{"year":2025,"cited_by_count":72},{"year":2024,"cited_by_count":46},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":4}],"updated_date":"2026-04-06T07:47:59.780226","created_date":"2025-10-10T00:00:00"}