{"id":"https://openalex.org/W2779774899","doi":"https://doi.org/10.1109/tcyb.2017.2781130","title":"MOO-MDP: An Object-Oriented Representation for Cooperative Multiagent Reinforcement Learning","display_name":"MOO-MDP: An Object-Oriented Representation for Cooperative Multiagent Reinforcement Learning","publication_year":2017,"publication_date":"2017-12-28","ids":{"openalex":"https://openalex.org/W2779774899","doi":"https://doi.org/10.1109/tcyb.2017.2781130","mag":"2779774899","pmid":"https://pubmed.ncbi.nlm.nih.gov/29990289"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2017.2781130","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2017.2781130","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cybernetics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.1109/TCYB.2017.2781130","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053630715","display_name":"Felipe Leno da Silva","orcid":"https://orcid.org/0000-0003-4703-2061"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Felipe Leno Da Silva","raw_affiliation_strings":["Intelligent Techniques Laboratory, University of S\u00e3o Paulo, S\u00e3o Paulo, Brazil"],"affiliations":[{"raw_affiliation_string":"Intelligent Techniques Laboratory, University of S\u00e3o Paulo, S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021316298","display_name":"Ruben Glatt","orcid":"https://orcid.org/0000-0002-4401-3810"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Ruben Glatt","raw_affiliation_strings":["Intelligent Techniques Laboratory, University of S\u00e3o Paulo, S\u00e3o Paulo, Brazil"],"affiliations":[{"raw_affiliation_string":"Intelligent Techniques Laboratory, University of S\u00e3o Paulo, S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069264027","display_name":"Anna Helena Reali Costa","orcid":"https://orcid.org/0000-0001-7309-4528"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Anna Helena Reali Costa","raw_affiliation_strings":["Intelligent Techniques Laboratory, University of S\u00e3o Paulo, S\u00e3o Paulo, Brazil"],"affiliations":[{"raw_affiliation_string":"Intelligent Techniques Laboratory, University of S\u00e3o Paulo, S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I17974374"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053630715"],"corresponding_institution_ids":["https://openalex.org/I17974374"],"apc_list":null,"apc_paid":null,"fwci":4.3617,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.95554301,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"49","issue":"2","first_page":"567","last_page":"579"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9842000007629395,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9775999784469604,"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":0.8310374021530151},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8082972764968872},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7724303007125854},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6441916823387146},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6151919364929199},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.486431360244751},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45867854356765747},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4399203062057495},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.42840713262557983},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35469019412994385},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3541363775730133},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3492673933506012},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3183574676513672},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09029990434646606}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8310374021530151},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8082972764968872},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7724303007125854},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6441916823387146},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6151919364929199},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.486431360244751},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45867854356765747},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4399203062057495},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.42840713262557983},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35469019412994385},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3541363775730133},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3492673933506012},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3183574676513672},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09029990434646606},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tcyb.2017.2781130","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2017.2781130","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cybernetics","raw_type":"journal-article"},{"id":"pmid:29990289","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29990289","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on cybernetics","raw_type":null},{"id":"pmh:002994939","is_oa":true,"landing_page_url":"https://doi.org/10.1109/TCYB.2017.2781130","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"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":"reponame:Reposit\u00f3rio Institucional da USP (Biblioteca Digital da Produ\u00e7\u00e3o Intelectual)","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:002994939","is_oa":true,"landing_page_url":"https://doi.org/10.1109/TCYB.2017.2781130","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"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":"reponame:Reposit\u00f3rio Institucional da USP (Biblioteca Digital da Produ\u00e7\u00e3o Intelectual)","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6100000143051147,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2214311588","display_name":null,"funder_award_id":"425860/2016-7","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"},{"id":"https://openalex.org/G3274686731","display_name":null,"funder_award_id":"2016/21047-3","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G4850177541","display_name":null,"funder_award_id":"2015/16310-4","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G817560822","display_name":null,"funder_award_id":"311608/2014-0","funder_id":"https://openalex.org/F4320322025","funder_display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico"}],"funders":[{"id":"https://openalex.org/F4320320997","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","ror":"https://ror.org/02ddkpn78"},{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W180119731","https://openalex.org/W1518858799","https://openalex.org/W1542941925","https://openalex.org/W1560074431","https://openalex.org/W1599772204","https://openalex.org/W1641379095","https://openalex.org/W1835254890","https://openalex.org/W1999912147","https://openalex.org/W2013413939","https://openalex.org/W2020573190","https://openalex.org/W2055921164","https://openalex.org/W2070963703","https://openalex.org/W2097186697","https://openalex.org/W2097381042","https://openalex.org/W2099618002","https://openalex.org/W2101355568","https://openalex.org/W2104144149","https://openalex.org/W2107544712","https://openalex.org/W2119567691","https://openalex.org/W2120846115","https://openalex.org/W2121863487","https://openalex.org/W2127186087","https://openalex.org/W2128814508","https://openalex.org/W2131600418","https://openalex.org/W2145339207","https://openalex.org/W2145790759","https://openalex.org/W2191395120","https://openalex.org/W2282350268","https://openalex.org/W2522413982","https://openalex.org/W2583279473","https://openalex.org/W2604402446","https://openalex.org/W2620645529","https://openalex.org/W2787259794","https://openalex.org/W3020831056","https://openalex.org/W4214717370","https://openalex.org/W4298023569","https://openalex.org/W6633472260","https://openalex.org/W6635891584","https://openalex.org/W6638624986","https://openalex.org/W6674600207","https://openalex.org/W6675130473","https://openalex.org/W6678168664","https://openalex.org/W6678873164","https://openalex.org/W6687364284","https://openalex.org/W6695303531","https://openalex.org/W6727060998"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W2315999538"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,36,51,67,144],"(RL)":[2],"is":[3,37],"a":[4,27,42,93],"widely":[5],"known":[6],"technique":[7],"to":[8,31,38,128],"enable":[9],"autonomous":[10],"learning.":[11],"Even":[12],"though":[13],"RL":[14],"methods":[15],"achieved":[16],"successes":[17],"in":[18,41,158,168],"increasingly":[19],"large":[20],"and":[21,47,98,112,124,161,171],"complex":[22],"problems,":[23],"scaling":[24],"solutions":[25],"remains":[26],"challenge.":[28],"One":[29],"way":[30],"simplify":[32],"(and":[33],"consequently":[34],"accelerate)":[35],"exploit":[39],"regularities":[40],"domain,":[43],"which":[44],"allows":[45],"generalization":[46,61],"reduction":[48],"of":[49,77,96,109,165],"the":[50,66,75,107,120,143,163],"space.":[52],"While":[53],"object-oriented":[54],"Markov":[55],"decision":[56],"processes":[57],"(OO-MDPs)":[58],"provide":[59],"such":[60],"opportunities,":[62],"we":[63,91],"argue":[64],"that":[65,135],"process":[68],"may":[69],"be":[70],"further":[71],"simplified":[72],"by":[73,146],"dividing":[74],"workload":[76],"tasks":[78],"amongst":[79],"multiple":[80],"agents,":[81],"solving":[82],"problems":[83],"as":[84],"multiagent":[85,101],"systems":[86],"(MAS).":[87],"In":[88],"this":[89],"paper,":[90],"propose":[92],"novel":[94],"combination":[95],"OO-MDP":[97,102,111],"MAS,":[99,113],"called":[100],"(MOO-MDP).":[103],"Our":[104],"proposal":[105],"accrues":[106],"benefits":[108],"both":[110],"better":[114],"addressing":[115],"scalability":[116],"issues.":[117],"We":[118,133,150],"formalize":[119],"general":[121],"model":[122],"MOO-MDP":[123],"present":[125],"an":[126],"algorithm":[127,137],"solve":[129],"deterministic":[130],"cooperative":[131],"MOO-MDPs.":[132],"show":[134],"our":[136,153,166],"learns":[138],"optimal":[139],"policies":[140],"while":[141],"reducing":[142],"space":[145],"exploiting":[147],"state":[148],"abstractions.":[149],"experimentally":[151],"compare":[152],"results":[154],"with":[155],"earlier":[156],"approaches":[157],"three":[159],"domains":[160],"evaluate":[162],"advantages":[164],"approach":[167],"sample":[169],"efficiency":[170],"memory":[172],"requirements.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}