{"id":"https://openalex.org/W4413736352","doi":"https://doi.org/10.1007/s10462-025-11340-5","title":"Multi-agent reinforcement learning for resources allocation optimization: a survey","display_name":"Multi-agent reinforcement learning for resources allocation optimization: a survey","publication_year":2025,"publication_date":"2025-08-27","ids":{"openalex":"https://openalex.org/W4413736352","doi":"https://doi.org/10.1007/s10462-025-11340-5"},"language":"en","primary_location":{"id":"doi:10.1007/s10462-025-11340-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-025-11340-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-025-11340-5.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/s10462-025-11340-5.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040070511","display_name":"Mohamad Abdul Hady","orcid":null},"institutions":[{"id":"https://openalex.org/I170239107","display_name":"University of South Australia","ror":"https://ror.org/01p93h210","country_code":"AU","type":"education","lineage":["https://openalex.org/I170239107"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Mohamad A. Hady","raw_affiliation_strings":["STEM, University of South Australia, Mawson Lakes Blvd, Mawson Lakes, SA, 5095, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STEM, University of South Australia, Mawson Lakes Blvd, Mawson Lakes, SA, 5095, Australia","institution_ids":["https://openalex.org/I170239107"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103162510","display_name":"Siyi Hu","orcid":"https://orcid.org/0000-0002-5945-8943"},"institutions":[{"id":"https://openalex.org/I170239107","display_name":"University of South Australia","ror":"https://ror.org/01p93h210","country_code":"AU","type":"education","lineage":["https://openalex.org/I170239107"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Siyi Hu","raw_affiliation_strings":["STEM, University of South Australia, Mawson Lakes Blvd, Mawson Lakes, SA, 5095, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STEM, University of South Australia, Mawson Lakes Blvd, Mawson Lakes, SA, 5095, Australia","institution_ids":["https://openalex.org/I170239107"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036928886","display_name":"Mahardhika Pratama","orcid":"https://orcid.org/0000-0001-6531-5087"},"institutions":[{"id":"https://openalex.org/I170239107","display_name":"University of South Australia","ror":"https://ror.org/01p93h210","country_code":"AU","type":"education","lineage":["https://openalex.org/I170239107"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mahardhika Pratama","raw_affiliation_strings":["STEM, University of South Australia, Mawson Lakes Blvd, Mawson Lakes, SA, 5095, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STEM, University of South Australia, Mawson Lakes Blvd, Mawson Lakes, SA, 5095, Australia","institution_ids":["https://openalex.org/I170239107"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007077356","display_name":"Zehong Cao","orcid":"https://orcid.org/0000-0003-3656-0328"},"institutions":[{"id":"https://openalex.org/I170239107","display_name":"University of South Australia","ror":"https://ror.org/01p93h210","country_code":"AU","type":"education","lineage":["https://openalex.org/I170239107"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zehong Cao","raw_affiliation_strings":["STEM, University of South Australia, Mawson Lakes Blvd, Mawson Lakes, SA, 5095, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STEM, University of South Australia, Mawson Lakes Blvd, Mawson Lakes, SA, 5095, Australia","institution_ids":["https://openalex.org/I170239107"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024220409","display_name":"Ryszard Kowalczyk","orcid":"https://orcid.org/0000-0003-0937-4028"},"institutions":[{"id":"https://openalex.org/I170239107","display_name":"University of South Australia","ror":"https://ror.org/01p93h210","country_code":"AU","type":"education","lineage":["https://openalex.org/I170239107"]},{"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":"funder","lineage":["https://openalex.org/I99542240"]}],"countries":["AU","PL"],"is_corresponding":false,"raw_author_name":"Ryszard Kowalczyk","raw_affiliation_strings":["STEM, University of South Australia, Mawson Lakes Blvd, Mawson Lakes, SA, 5095, Australia","Systems Research Institute, Polish Academy of Sciences, Warsaw, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STEM, University of South Australia, Mawson Lakes Blvd, Mawson Lakes, SA, 5095, Australia","institution_ids":["https://openalex.org/I170239107"]},{"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":5,"corresponding_author_ids":["https://openalex.org/A5040070511"],"corresponding_institution_ids":["https://openalex.org/I170239107"],"apc_list":{"value":2490,"currency":"EUR","value_usd":3090},"apc_paid":{"value":2490,"currency":"EUR","value_usd":3090},"fwci":39.5136,"has_fulltext":true,"cited_by_count":31,"citation_normalized_percentile":{"value":0.99830094,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"58","issue":"11","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12288","display_name":"Optimization and Search Problems","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9965000152587891,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9959999918937683,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8021747469902039},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7690133452415466},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.43342095613479614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3914836347103119},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.36042770743370056},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.34694525599479675},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08096307516098022},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07219728827476501},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.04756626486778259}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8021747469902039},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7690133452415466},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.43342095613479614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3914836347103119},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.36042770743370056},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.34694525599479675},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08096307516098022},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07219728827476501},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.04756626486778259}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10462-025-11340-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-025-11340-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-025-11340-5.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"}],"best_oa_location":{"id":"doi:10.1007/s10462-025-11340-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-025-11340-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10462-025-11340-5.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":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320320979","display_name":"University of South Australia","ror":"https://ror.org/01p93h210"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413736352.pdf","grobid_xml":"https://content.openalex.org/works/W4413736352.grobid-xml"},"referenced_works_count":169,"referenced_works":["https://openalex.org/W189789383","https://openalex.org/W634973347","https://openalex.org/W911028829","https://openalex.org/W1980314979","https://openalex.org/W1992619185","https://openalex.org/W1995279652","https://openalex.org/W1997204636","https://openalex.org/W1999244290","https://openalex.org/W2024060531","https://openalex.org/W2034332963","https://openalex.org/W2043597464","https://openalex.org/W2064788562","https://openalex.org/W2065356639","https://openalex.org/W2071465750","https://openalex.org/W2095385797","https://openalex.org/W2098469827","https://openalex.org/W2099618002","https://openalex.org/W2100677568","https://openalex.org/W2114725328","https://openalex.org/W2119050029","https://openalex.org/W2136822103","https://openalex.org/W2139386984","https://openalex.org/W2152195021","https://openalex.org/W2153807213","https://openalex.org/W2159623780","https://openalex.org/W2170621602","https://openalex.org/W2314419339","https://openalex.org/W2546571074","https://openalex.org/W2590858232","https://openalex.org/W2737359858","https://openalex.org/W2746553466","https://openalex.org/W2793763890","https://openalex.org/W2795021318","https://openalex.org/W2883037762","https://openalex.org/W2898189018","https://openalex.org/W2908261578","https://openalex.org/W2913775178","https://openalex.org/W2944464036","https://openalex.org/W2945991855","https://openalex.org/W2964749398","https://openalex.org/W2967474307","https://openalex.org/W2969195240","https://openalex.org/W2971727319","https://openalex.org/W3000445347","https://openalex.org/W3005335721","https://openalex.org/W3005761304","https://openalex.org/W3006577290","https://openalex.org/W3007687131","https://openalex.org/W3011182939","https://openalex.org/W3017275226","https://openalex.org/W3030840723","https://openalex.org/W3036160090","https://openalex.org/W3046988891","https://openalex.org/W3048217314","https://openalex.org/W3048983622","https://openalex.org/W3081405700","https://openalex.org/W3083092406","https://openalex.org/W3083695346","https://openalex.org/W3091760249","https://openalex.org/W3094493698","https://openalex.org/W3096739060","https://openalex.org/W3109858579","https://openalex.org/W3122780823","https://openalex.org/W3123582921","https://openalex.org/W3130425349","https://openalex.org/W3133735442","https://openalex.org/W3142875962","https://openalex.org/W3153842551","https://openalex.org/W3161618639","https://openalex.org/W3162079807","https://openalex.org/W3166737224","https://openalex.org/W3167586364","https://openalex.org/W3167897655","https://openalex.org/W3170397984","https://openalex.org/W3179018212","https://openalex.org/W3181869286","https://openalex.org/W3188452735","https://openalex.org/W3195766133","https://openalex.org/W3203789000","https://openalex.org/W3205260830","https://openalex.org/W3207692912","https://openalex.org/W4206179170","https://openalex.org/W4206321341","https://openalex.org/W4210445430","https://openalex.org/W4210941603","https://openalex.org/W4213190850","https://openalex.org/W4213451426","https://openalex.org/W4214717370","https://openalex.org/W4214833058","https://openalex.org/W4214866088","https://openalex.org/W4220763773","https://openalex.org/W4220906859","https://openalex.org/W4221103247","https://openalex.org/W4224874620","https://openalex.org/W4226071977","https://openalex.org/W4284711157","https://openalex.org/W4285184341","https://openalex.org/W4286893914","https://openalex.org/W4292259710","https://openalex.org/W4294842416","https://openalex.org/W4304615560","https://openalex.org/W4304692597","https://openalex.org/W4306786778","https://openalex.org/W4307261638","https://openalex.org/W4308436316","https://openalex.org/W4308487886","https://openalex.org/W4312451049","https://openalex.org/W4312532452","https://openalex.org/W4313068113","https://openalex.org/W4313655082","https://openalex.org/W4313886730","https://openalex.org/W4315473069","https://openalex.org/W4319165238","https://openalex.org/W4319878926","https://openalex.org/W4320002923","https://openalex.org/W4321438421","https://openalex.org/W4322704128","https://openalex.org/W4322766100","https://openalex.org/W4323022381","https://openalex.org/W4327719810","https://openalex.org/W4361222181","https://openalex.org/W4362519817","https://openalex.org/W4376464656","https://openalex.org/W4376481074","https://openalex.org/W4379875406","https://openalex.org/W4379986188","https://openalex.org/W4380152116","https://openalex.org/W4380925176","https://openalex.org/W4381733136","https://openalex.org/W4383200262","https://openalex.org/W4386212337","https://openalex.org/W4387431645","https://openalex.org/W4387442993","https://openalex.org/W4388225464","https://openalex.org/W4390144572","https://openalex.org/W4391166826","https://openalex.org/W4391175216","https://openalex.org/W4391407074","https://openalex.org/W4391854298","https://openalex.org/W4391879685","https://openalex.org/W4391919254","https://openalex.org/W4392693998","https://openalex.org/W4392796637","https://openalex.org/W4392867798","https://openalex.org/W4395056437","https://openalex.org/W4399361416","https://openalex.org/W4399666533","https://openalex.org/W4399994426","https://openalex.org/W4400526177","https://openalex.org/W4400904839","https://openalex.org/W4401247004","https://openalex.org/W4401534871","https://openalex.org/W4401683893","https://openalex.org/W4402444449","https://openalex.org/W4403722221","https://openalex.org/W4405284445","https://openalex.org/W4406102533","https://openalex.org/W4406158127","https://openalex.org/W4406788351","https://openalex.org/W4406857054","https://openalex.org/W4406858234","https://openalex.org/W4406900765","https://openalex.org/W4407014066","https://openalex.org/W4407102704","https://openalex.org/W4407196485","https://openalex.org/W4408790649","https://openalex.org/W4410227715","https://openalex.org/W4410808427","https://openalex.org/W6949425989"],"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],"Multi-Agent":[1],"Reinforcement":[2],"Learning":[3],"(MARL)":[4],"has":[5],"become":[6],"a":[7,50,60],"powerful":[8],"framework":[9],"for":[10,67],"numerous":[11],"real-world":[12],"applications,":[13],"modeling":[14],"distributed":[15],"decision-making":[16],"and":[17,36,75,83,87,96],"learning":[18],"from":[19,30],"interactions":[20],"with":[21],"complex":[22],"environments.":[23],"Resource":[24],"Allocation":[25],"Optimization":[26],"(RAO)":[27],"benefits":[28],"significantly":[29],"MARL\u2019s":[31,100],"ability":[32],"to":[33,44,93,102],"tackle":[34],"dynamic":[35],"decentralized":[37],"contexts.":[38],"MARL-based":[39],"approaches":[40],"are":[41],"increasingly":[42],"applied":[43],"RAO":[45],"challenges":[46,86],"across":[47],"sectors":[48],"playing":[49],"pivotal":[51],"role":[52],"in":[53,98],"industry":[54],"4.0":[55],"developments.":[56],"This":[57],"survey":[58,91],"provides":[59],"comprehensive":[61],"review":[62],"of":[63],"recent":[64],"MARL":[65],"algorithms":[66],"RAO,":[68],"encompassing":[69],"core":[70],"concepts,":[71],"classifications,":[72],"design":[73],"steps":[74],"benchmarks.":[76],"By":[77],"outlining":[78],"the":[79],"current":[80],"research":[81],"landscape":[82],"identifying":[84],"primary":[85],"future":[88],"directions,":[89],"this":[90],"aims":[92],"support":[94],"researchers":[95],"practitioners":[97],"leveraging":[99],"potential":[101],"advance":[103],"resource":[104],"allocation":[105],"solutions.":[106]},"counts_by_year":[{"year":2026,"cited_by_count":16},{"year":2025,"cited_by_count":15}],"updated_date":"2026-05-08T15:41:06.802602","created_date":"2025-10-10T00:00:00"}