{"id":"https://openalex.org/W3156295478","doi":"https://doi.org/10.1007/s10462-021-09996-w","title":"Multi-agent deep reinforcement learning: a survey","display_name":"Multi-agent deep reinforcement learning: a survey","publication_year":2021,"publication_date":"2021-04-15","ids":{"openalex":"https://openalex.org/W3156295478","doi":"https://doi.org/10.1007/s10462-021-09996-w","mag":"3156295478"},"language":"en","primary_location":{"id":"doi:10.1007/s10462-021-09996-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-021-09996-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-021-09996-w.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/s10462-021-09996-w.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020980906","display_name":"Sven Gronauer","orcid":"https://orcid.org/0000-0002-0047-5116"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Sven Gronauer","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Technical University of Munich (TUM), Arcisstr. 21, 80333, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0002-0047-5116","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Technical University of Munich (TUM), Arcisstr. 21, 80333, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074346065","display_name":"Klaus Diepold","orcid":"https://orcid.org/0000-0003-0439-7511"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Klaus Diepold","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Technical University of Munich (TUM), Arcisstr. 21, 80333, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Technical University of Munich (TUM), Arcisstr. 21, 80333, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020980906"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":{"value":2490,"currency":"EUR","value_usd":3090},"apc_paid":{"value":2490,"currency":"EUR","value_usd":3090},"fwci":62.553,"has_fulltext":true,"cited_by_count":813,"citation_normalized_percentile":{"value":0.99935719,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"55","issue":"2","first_page":"895","last_page":"943"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9700000286102295,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9667999744415283,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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":0.8858934640884399},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7122007012367249},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.48242148756980896},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4564315378665924},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4517020285129547},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.34246909618377686},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08391794562339783}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8858934640884399},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7122007012367249},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.48242148756980896},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4564315378665924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4517020285129547},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34246909618377686},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08391794562339783},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s10462-021-09996-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-021-09996-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-021-09996-w.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:mediatum.ub.tum.de:node/1618457","is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1618457","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"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"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1639959","is_oa":false,"landing_page_url":"https://mediatum.ub.tum.de/1639959","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1734945","is_oa":false,"landing_page_url":"https://mediatum.ub.tum.de/1734945","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s10462-021-09996-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-021-09996-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-021-09996-w.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":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323383","display_name":"Technische Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/02kkvpp62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3156295478.pdf","grobid_xml":"https://content.openalex.org/works/W3156295478.grobid-xml"},"referenced_works_count":237,"referenced_works":["https://openalex.org/W56117469","https://openalex.org/W137071854","https://openalex.org/W156814138","https://openalex.org/W345119801","https://openalex.org/W567721252","https://openalex.org/W1192553058","https://openalex.org/W1457482454","https://openalex.org/W1513468570","https://openalex.org/W1518858799","https://openalex.org/W1528676759","https://openalex.org/W1537415400","https://openalex.org/W1542941925","https://openalex.org/W1555689267","https://openalex.org/W1560074431","https://openalex.org/W1564534945","https://openalex.org/W1579184372","https://openalex.org/W1641379095","https://openalex.org/W1777239053","https://openalex.org/W1845972764","https://openalex.org/W1908253641","https://openalex.org/W1933349210","https://openalex.org/W1963523946","https://openalex.org/W1973039793","https://openalex.org/W1982678075","https://openalex.org/W2000514530","https://openalex.org/W2012812921","https://openalex.org/W2034806191","https://openalex.org/W2044212084","https://openalex.org/W2048382412","https://openalex.org/W2064675550","https://openalex.org/W2076337359","https://openalex.org/W2087322096","https://openalex.org/W2088956500","https://openalex.org/W2096145798","https://openalex.org/W2097381042","https://openalex.org/W2098432798","https://openalex.org/W2099618002","https://openalex.org/W2102764452","https://openalex.org/W2103561211","https://openalex.org/W2105695492","https://openalex.org/W2106713015","https://openalex.org/W2107544712","https://openalex.org/W2107726111","https://openalex.org/W2108449787","https://openalex.org/W2108892923","https://openalex.org/W2109910161","https://openalex.org/W2110906765","https://openalex.org/W2120327309","https://openalex.org/W2120846115","https://openalex.org/W2122253967","https://openalex.org/W2122763142","https://openalex.org/W2126222949","https://openalex.org/W2129633982","https://openalex.org/W2129936995","https://openalex.org/W2132683224","https://openalex.org/W2134779831","https://openalex.org/W2136202932","https://openalex.org/W2142505627","https://openalex.org/W2145339207","https://openalex.org/W2147492008","https://openalex.org/W2147539438","https://openalex.org/W2151710526","https://openalex.org/W2154902490","https://openalex.org/W2162022118","https://openalex.org/W2166533447","https://openalex.org/W2171026506","https://openalex.org/W2171234133","https://openalex.org/W2171863654","https://openalex.org/W2226396244","https://openalex.org/W2257979135","https://openalex.org/W2290743114","https://openalex.org/W2291986326","https://openalex.org/W2292533394","https://openalex.org/W2296073425","https://openalex.org/W2395575420","https://openalex.org/W2396783599","https://openalex.org/W2402402867","https://openalex.org/W2417786368","https://openalex.org/W2419612459","https://openalex.org/W2462906003","https://openalex.org/W2466211196","https://openalex.org/W2475089067","https://openalex.org/W2476301537","https://openalex.org/W2480004914","https://openalex.org/W2507578125","https://openalex.org/W2530849036","https://openalex.org/W2535584654","https://openalex.org/W2550182557","https://openalex.org/W2562637642","https://openalex.org/W2563399268","https://openalex.org/W2564324149","https://openalex.org/W2575731723","https://openalex.org/W2581240229","https://openalex.org/W2602275733","https://openalex.org/W2603088459","https://openalex.org/W2603266952","https://openalex.org/W2604283518","https://openalex.org/W2604402446","https://openalex.org/W2604704722","https://openalex.org/W2614309179","https://openalex.org/W2615688110","https://openalex.org/W2617547828","https://openalex.org/W2620645529","https://openalex.org/W2623431351","https://openalex.org/W2730328371","https://openalex.org/W2736601468","https://openalex.org/W2740377041","https://openalex.org/W2745868649","https://openalex.org/W2747213132","https://openalex.org/W2747402019","https://openalex.org/W2749807327","https://openalex.org/W2750605955","https://openalex.org/W2750866482","https://openalex.org/W2754517384","https://openalex.org/W2758442112","https://openalex.org/W2763208138","https://openalex.org/W2766184602","https://openalex.org/W2768629321","https://openalex.org/W2776126823","https://openalex.org/W2776777826","https://openalex.org/W2781238083","https://openalex.org/W2783268317","https://openalex.org/W2789386227","https://openalex.org/W2798511001","https://openalex.org/W2807741983","https://openalex.org/W2810602713","https://openalex.org/W2813428123","https://openalex.org/W2886000153","https://openalex.org/W2889987506","https://openalex.org/W2891287243","https://openalex.org/W2892013712","https://openalex.org/W2894389820","https://openalex.org/W2895896816","https://openalex.org/W2895921264","https://openalex.org/W2898035736","https://openalex.org/W2902907165","https://openalex.org/W2904455790","https://openalex.org/W2904948755","https://openalex.org/W2908261578","https://openalex.org/W2909611215","https://openalex.org/W2911616846","https://openalex.org/W2912793366","https://openalex.org/W2913326990","https://openalex.org/W2913654295","https://openalex.org/W2914351253","https://openalex.org/W2915117209","https://openalex.org/W2920700222","https://openalex.org/W2921955147","https://openalex.org/W2932081708","https://openalex.org/W2944827102","https://openalex.org/W2945582565","https://openalex.org/W2946606218","https://openalex.org/W2948099544","https://openalex.org/W2949201811","https://openalex.org/W2949267040","https://openalex.org/W2949464762","https://openalex.org/W2950395160","https://openalex.org/W2951896791","https://openalex.org/W2962764167","https://openalex.org/W2962766710","https://openalex.org/W2962852262","https://openalex.org/W2962869735","https://openalex.org/W2962938168","https://openalex.org/W2962938178","https://openalex.org/W2963041255","https://openalex.org/W2963065757","https://openalex.org/W2963147362","https://openalex.org/W2963155490","https://openalex.org/W2963162637","https://openalex.org/W2963170138","https://openalex.org/W2963293542","https://openalex.org/W2963368198","https://openalex.org/W2963385935","https://openalex.org/W2963390684","https://openalex.org/W2963455109","https://openalex.org/W2963485523","https://openalex.org/W2963497400","https://openalex.org/W2963536577","https://openalex.org/W2963627051","https://openalex.org/W2963637944","https://openalex.org/W2963658727","https://openalex.org/W2963681240","https://openalex.org/W2963689090","https://openalex.org/W2963715810","https://openalex.org/W2963717208","https://openalex.org/W2963788414","https://openalex.org/W2963809389","https://openalex.org/W2963881016","https://openalex.org/W2963887494","https://openalex.org/W2964014087","https://openalex.org/W2964043796","https://openalex.org/W2964161785","https://openalex.org/W2964321324","https://openalex.org/W2964345382","https://openalex.org/W2964915587","https://openalex.org/W2964937097","https://openalex.org/W2965433979","https://openalex.org/W2966371608","https://openalex.org/W2967558504","https://openalex.org/W2968526727","https://openalex.org/W2969456553","https://openalex.org/W2970603867","https://openalex.org/W2971094937","https://openalex.org/W2981038142","https://openalex.org/W2982041656","https://openalex.org/W2982316857","https://openalex.org/W2982320652","https://openalex.org/W2987046690","https://openalex.org/W2989068617","https://openalex.org/W2991046523","https://openalex.org/W2994864869","https://openalex.org/W2995453501","https://openalex.org/W2995520132","https://openalex.org/W2995815314","https://openalex.org/W2995874959","https://openalex.org/W2996037775","https://openalex.org/W2996343955","https://openalex.org/W3009413787","https://openalex.org/W3012445938","https://openalex.org/W3033076904","https://openalex.org/W3037207827","https://openalex.org/W3037211759","https://openalex.org/W3037940279","https://openalex.org/W3048435052","https://openalex.org/W3098163860","https://openalex.org/W3099134564","https://openalex.org/W3099518626","https://openalex.org/W3100789280","https://openalex.org/W3104860527","https://openalex.org/W3110309042","https://openalex.org/W3127047144","https://openalex.org/W3133280296","https://openalex.org/W4206354906","https://openalex.org/W4232967792","https://openalex.org/W4246078117","https://openalex.org/W4252284432","https://openalex.org/W4254547512"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Abstract":[0],"The":[1],"advances":[2],"in":[3,10,51,118,132,163],"reinforcement":[4,28,57,70],"learning":[5,29,71],"have":[6],"recorded":[7],"sublime":[8],"success":[9],"various":[11],"domains.":[12],"Although":[13],"the":[14,34,48,52,79,83,86,97,112,133],"multi-agent":[15,27,55,75,134],"domain":[16,135],"has":[17],"been":[18],"overshadowed":[19],"by":[20],"its":[21],"single-agent":[22],"counterpart":[23],"during":[24],"this":[25,149,164],"progress,":[26],"gains":[30],"rapid":[31],"traction,":[32],"and":[33,121,136,156],"latest":[35],"accomplishments":[36],"address":[37],"problems":[38],"with":[39,73,144],"real-world":[40],"complexity.":[41],"This":[42],"article":[43],"provides":[44],"an":[45],"overview":[46],"of":[47,54,99,115],"current":[49],"developments":[50],"field":[53],"deep":[56,69],"learning.":[58],"We":[59],"focus":[60],"primarily":[61],"on":[62],"literature":[63],"from":[64],"recent":[65],"years":[66],"that":[67,81,102,129,139],"combines":[68],"methods":[72,138],"a":[74],"scenario.":[76],"To":[77,147],"survey":[78],"works":[80],"constitute":[82],"contemporary":[84],"landscape,":[85],"main":[87],"contents":[88],"are":[89,103,140],"divided":[90],"into":[91],"three":[92],"parts.":[93],"First,":[94],"we":[95,110,125,151],"analyze":[96],"structure":[98],"training":[100],"schemes":[101],"applied":[104],"to":[105,142],"train":[106],"multiple":[107],"agents.":[108],"Second,":[109],"consider":[111],"emergent":[113],"patterns":[114],"agent":[116],"behavior":[117],"cooperative,":[119],"competitive":[120],"mixed":[122],"scenarios.":[123],"Third,":[124],"systematically":[126],"enumerate":[127],"challenges":[128],"exclusively":[130],"arise":[131],"review":[137],"leveraged":[141],"cope":[143],"these":[145],"challenges.":[146],"conclude":[148],"survey,":[150],"discuss":[152],"advances,":[153],"identify":[154],"trends,":[155],"outline":[157],"possible":[158],"directions":[159],"for":[160],"future":[161],"work":[162],"research":[165],"area.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":97},{"year":2025,"cited_by_count":269},{"year":2024,"cited_by_count":223},{"year":2023,"cited_by_count":149},{"year":2022,"cited_by_count":60},{"year":2021,"cited_by_count":15}],"updated_date":"2026-06-05T09:01:59.212387","created_date":"2025-10-10T00:00:00"}