{"id":"https://openalex.org/W4414738417","doi":"https://doi.org/10.48550/arxiv.2507.10142","title":"Toward Adaptable Multi-Agent Reinforcement Learning: An Assumption-Aware Review","display_name":"Toward Adaptable Multi-Agent Reinforcement Learning: An Assumption-Aware Review","publication_year":2025,"publication_date":"2025-07-14","ids":{"openalex":"https://openalex.org/W4414738417","doi":"https://doi.org/10.48550/arxiv.2507.10142"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2507.10142","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2507.10142","pdf_url":"https://arxiv.org/pdf/2507.10142","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.10142","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103162510","display_name":"Siyi Hu","orcid":"https://orcid.org/0000-0002-5945-8943","observed_orcids":["https://orcid.org/0000-0002-5945-8943"]},"institutions":[{"id":"https://openalex.org/I205640436","display_name":"Curtin University","ror":"https://ror.org/02n415q13","country_code":"AU","type":"education","lineage":["https://openalex.org/I205640436"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hu, Siyi","raw_affiliation_strings":["Curtin University , Perth , Western Australia , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Curtin University , Perth , Western Australia , Australia","institution_ids":["https://openalex.org/I205640436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040070511","display_name":"Mohamad Abdul Hady","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405259444","display_name":"Adelaide University","ror":"https://ror.org/028g18b61","country_code":"AU","type":"education","lineage":["https://openalex.org/I4405259444"]},{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I4405259444","https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hady, Mohamad A","raw_affiliation_strings":["Adelaide University , Adelaide , South Australia , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adelaide University , Adelaide , South Australia , Australia","institution_ids":["https://openalex.org/I4405259444","https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043934955","display_name":"Jianglin Qiao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qiao, Jianglin","raw_affiliation_strings":["The University of Sydney , Sydney , New South Wales , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Sydney , Sydney , New South Wales , Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030589099","display_name":"Jimmy Cao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Jimmy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036928886","display_name":"Mahardhika Pratama","orcid":"https://orcid.org/0000-0001-6531-5087","observed_orcids":["https://orcid.org/0000-0001-6531-5087"]},"institutions":[{"id":"https://openalex.org/I4405259444","display_name":"Adelaide University","ror":"https://ror.org/028g18b61","country_code":"AU","type":"education","lineage":["https://openalex.org/I4405259444"]},{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I4405259444","https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Pratama, Mahardhika","raw_affiliation_strings":["Adelaide University , Adelaide , South Australia , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adelaide University , Adelaide , South Australia , Australia","institution_ids":["https://openalex.org/I4405259444","https://openalex.org/I5681781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024220409","display_name":"Ryszard Kowalczyk","orcid":"https://orcid.org/0000-0003-0937-4028","observed_orcids":["https://orcid.org/0000-0003-0937-4028"]},"institutions":[{"id":"https://openalex.org/I4405259444","display_name":"Adelaide University","ror":"https://ror.org/028g18b61","country_code":"AU","type":"education","lineage":["https://openalex.org/I4405259444"]},{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I4405259444","https://openalex.org/I5681781"]},{"id":"https://openalex.org/I66083562","display_name":"Systems Research Institute","ror":"https://ror.org/0111cp837","country_code":"PL","type":"facility","lineage":["https://openalex.org/I66083562","https://openalex.org/I99542240"]},{"id":"https://openalex.org/I99542240","display_name":"Polish Academy of Sciences","ror":"https://ror.org/01dr6c206","country_code":"PL","type":"government","lineage":["https://openalex.org/I99542240"]}],"countries":["AU","PL"],"is_corresponding":false,"raw_author_name":"Kowalczyk, Ryszard","raw_affiliation_strings":["Adelaide University , Adelaide , South Australia , Australia","Systems Research Institute Polish Academy of Sciences , Warsaw , Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adelaide University , Adelaide , South Australia , Australia","institution_ids":["https://openalex.org/I4405259444","https://openalex.org/I5681781"]},{"raw_affiliation_string":"Systems Research Institute Polish Academy of Sciences , Warsaw , Poland","institution_ids":["https://openalex.org/I66083562","https://openalex.org/I99542240"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":1.0,"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":1.0,"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":0.0,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":1.0},{"id":"https://openalex.org/keywords/adaptability","display_name":"adaptability","score":0.9470000267028809},{"id":"https://openalex.org/keywords/learning-adaptability","display_name":"learning adaptability","score":0.796999990940094},{"id":"https://openalex.org/keywords/policy-adaptability","display_name":"policy adaptability","score":0.9919999837875366},{"id":"https://openalex.org/keywords/distribution-shift","display_name":"distribution shift","score":0.8100000023841858},{"id":"https://openalex.org/keywords/structural-change","display_name":"structural change","score":0.48100000619888306},{"id":"https://openalex.org/keywords/benchmark-evaluation","display_name":"benchmark evaluation","score":0.3580000102519989},{"id":"https://openalex.org/keywords/scalability","display_name":"scalability","score":0.3310000002384186},{"id":"https://openalex.org/keywords/robustness","display_name":"robustness","score":0.9769999980926514},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.9100000262260437},{"id":"https://openalex.org/keywords/transferability","display_name":"transferability","score":0.8360000252723694}],"concepts":[{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.8598999977111816},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.7742000222206116},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.738099992275238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6830000281333923},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6097000241279602},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5764999985694885},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.47589999437332153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.454800009727478},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35690000653266907},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C43091099","wikidata":"https://www.wikidata.org/wiki/Q1067788","display_name":"Through-the-lens metering","level":3,"score":0.3409999907016754},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3091000020503998},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29809999465942383},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.26829999685287476},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2507.10142","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2507.10142","pdf_url":"https://arxiv.org/pdf/2507.10142","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.10142","doi":"https://doi.org/10.48550/arxiv.2507.10142","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.10142","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.10142","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2507.10142","pdf_url":"https://arxiv.org/pdf/2507.10142","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414738417.pdf","grobid_xml":"https://content.openalex.org/works/W4414738417.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W2740377041","https://openalex.org/W2892310660","https://openalex.org/W2913103105","https://openalex.org/W2913662073","https://openalex.org/W2975343435","https://openalex.org/W2982041656","https://openalex.org/W3093963693","https://openalex.org/W3099689767","https://openalex.org/W3113142401","https://openalex.org/W3193101426","https://openalex.org/W3205794883","https://openalex.org/W4297726143","https://openalex.org/W4300443914","https://openalex.org/W4306295215","https://openalex.org/W4312227587","https://openalex.org/W4319653773","https://openalex.org/W4365395843","https://openalex.org/W4380714553","https://openalex.org/W4386081870","https://openalex.org/W4387687183","https://openalex.org/W4389363346","https://openalex.org/W4389674424","https://openalex.org/W4392762590","https://openalex.org/W4402402057","https://openalex.org/W4402669738","https://openalex.org/W4402671198","https://openalex.org/W4402705366","https://openalex.org/W4404782996","https://openalex.org/W4409362604","https://openalex.org/W4412945638","https://openalex.org/W4414123240","https://openalex.org/W4415333307","https://openalex.org/W4415800716","https://openalex.org/W4416036811","https://openalex.org/W7124267618","https://openalex.org/W7124272497","https://openalex.org/W7124298089","https://openalex.org/W7125776132","https://openalex.org/W7130540429","https://openalex.org/W7135195786","https://openalex.org/W7148549932","https://openalex.org/W7157897902","https://openalex.org/W7162253840","https://openalex.org/W7162254017","https://openalex.org/W7163079716","https://openalex.org/W7165806824"],"related_works":["https://openalex.org/W2099618002","https://openalex.org/W7081972261","https://openalex.org/W7197013338","https://openalex.org/W4405546960","https://openalex.org/W7130389591","https://openalex.org/W7099980355","https://openalex.org/W4200120727","https://openalex.org/W3130259242","https://openalex.org/W2990227818","https://openalex.org/W4389814224"],"abstract_inverted_index":{"Multi-Agent":[0],"Reinforcement":[1],"Learning":[2],"(MARL)":[3],"has":[4],"achieved":[5],"strong":[6],"performance":[7],"in":[8,101],"simulated":[9],"benchmarks,":[10],"yet":[11],"real":[12],"deployments":[13],"often":[14,62],"violate":[15],"the":[16,112,127,157,168],"assumptions":[17],"under":[18,117,134],"which":[19,110,125,140],"algorithms":[20],"are":[21],"designed":[22],"and":[23,41,57,69,137,144,164,176],"evaluated.":[24],"Agent":[25],"populations":[26],"may":[27,30,34,38,44],"change,":[28],"objectives":[29],"shift,":[31],"centralized":[32],"information":[33],"be":[35,45],"unavailable,":[36],"execution":[37],"become":[39],"asynchronous,":[40],"partner":[42],"policies":[43,133],"unfamiliar.":[46],"Existing":[47],"surveys":[48],"discuss":[49],"related":[50],"desiderata":[51],"such":[52],"as":[53,81,91],"scalability,":[54],"robustness,":[55],"generalization,":[56],"transferability,":[58],"but":[59],"these":[60,87],"terms":[61],"refer":[63],"to":[64],"different":[65,70],"objects":[66],"of":[67,72,114,131],"analysis":[68],"kinds":[71],"distributional":[73],"or":[74,120,129],"structural":[75],"shift.":[76],"This":[77],"survey":[78],"proposes":[79],"\\textit{adaptability}":[80],"an":[82],"assumption-aware":[83],"taxonomy":[84],"for":[85],"organizing":[86],"shifts,":[88],"rather":[89],"than":[90],"a":[92],"universal":[93],"requirement":[94],"that":[95],"every":[96,102],"MARL":[97,180],"algorithm":[98],"should":[99],"succeed":[100],"setting.":[103],"We":[104],"distinguish":[105],"three":[106],"dimensions:":[107],"\\textit{learning":[108],"adaptability},":[109,124,139],"concerns":[111,126,141],"applicability":[113],"learning":[115],"paradigms":[116],"changed":[118],"training":[119],"system":[121],"assumptions;":[122],"\\textit{policy":[123],"reuse":[128],"adaptation":[130,161],"learned":[132],"deployment-time":[135],"changes;":[136],"\\textit{scenario-driven":[138],"whether":[142],"benchmarks":[143],"evaluation":[145,181],"protocols":[146],"expose":[147],"controlled,":[148],"diagnostically":[149],"useful":[150],"shifts.":[151],"By":[152],"separating":[153],"what":[154,160,165],"changes,":[155],"when":[156],"change":[158],"occurs,":[159],"is":[162],"allowed,":[163],"success":[166],"means,":[167],"framework":[169],"clarifies":[170],"how":[171],"established":[172],"concepts":[173],"fit":[174],"together":[175],"identifies":[177],"where":[178],"current":[179],"remains":[182],"underspecified.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":4}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}
