{"id":"https://openalex.org/W3196861772","doi":"https://doi.org/10.3389/frobt.2024.1394209","title":"MACRPO: Multi-agent cooperative recurrent policy optimization","display_name":"MACRPO: Multi-agent cooperative recurrent policy optimization","publication_year":2024,"publication_date":"2024-12-20","ids":{"openalex":"https://openalex.org/W3196861772","doi":"https://doi.org/10.3389/frobt.2024.1394209","mag":"3196861772","pmid":"https://pubmed.ncbi.nlm.nih.gov/39760046"},"language":"en","primary_location":{"id":"doi:10.3389/frobt.2024.1394209","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frobt.2024.1394209","pdf_url":null,"source":{"id":"https://openalex.org/S2595095599","display_name":"Frontiers in Robotics and AI","issn_l":"2296-9144","issn":["2296-9144"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Robotics and AI","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3389/frobt.2024.1394209","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035651536","display_name":"Eshagh Kargar","orcid":"https://orcid.org/0000-0001-5899-3592"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Eshagh Kargar","raw_affiliation_strings":["Intelligent Robotics Group, Electrical Engineering and Automation Department, Aalto University, Helsinki, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Robotics Group, Electrical Engineering and Automation Department, Aalto University, Helsinki, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080940147","display_name":"Ville Kyrki","orcid":"https://orcid.org/0000-0002-5230-5549"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ville Kyrki","raw_affiliation_strings":["Intelligent Robotics Group, Electrical Engineering and Automation Department, Aalto University, Helsinki, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Robotics Group, Electrical Engineering and Automation Department, Aalto University, Helsinki, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5035651536"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":{"value":1900,"currency":"USD","value_usd":1900},"apc_paid":{"value":1592,"currency":"EUR","value_usd":1716},"fwci":0.3254,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59752836,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"11","issue":null,"first_page":"1394209","last_page":"1394209"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.982200026512146,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9666000008583069,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/computer-science","display_name":"Computer science","score":0.8504921197891235},{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.6521124839782715},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5020642280578613},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4606281816959381},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3748718500137329},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3565160036087036}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8504921197891235},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.6521124839782715},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5020642280578613},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4606281816959381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3748718500137329},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3565160036087036},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied 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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3389/frobt.2024.1394209","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frobt.2024.1394209","pdf_url":null,"source":{"id":"https://openalex.org/S2595095599","display_name":"Frontiers in Robotics and AI","issn_l":"2296-9144","issn":["2296-9144"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Robotics and AI","raw_type":"journal-article"},{"id":"pmid:39760046","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39760046","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":"Frontiers in robotics and AI","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11695781","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11695781","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Robot AI","raw_type":"Text"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/132830","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/fb8c8967-00a7-4282-83ba-8f2297ea1777","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"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":null,"raw_type":"publishedVersion"},{"id":"pmh:oai:doaj.org/article:cc08fb81741b44a0b15fca5c3a08264a","is_oa":true,"landing_page_url":"https://doaj.org/article/cc08fb81741b44a0b15fca5c3a08264a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Robotics and AI, Vol 11 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/frobt.2024.1394209","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frobt.2024.1394209","pdf_url":null,"source":{"id":"https://openalex.org/S2595095599","display_name":"Frontiers in Robotics and AI","issn_l":"2296-9144","issn":["2296-9144"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Robotics and AI","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W1641379095","https://openalex.org/W2096145798","https://openalex.org/W2101934420","https://openalex.org/W2104459548","https://openalex.org/W2107726111","https://openalex.org/W2137514195","https://openalex.org/W2149551746","https://openalex.org/W2292533394","https://openalex.org/W2559655401","https://openalex.org/W2602275733","https://openalex.org/W2612690371","https://openalex.org/W2612817080","https://openalex.org/W2617547828","https://openalex.org/W2736601468","https://openalex.org/W2747329762","https://openalex.org/W2762117857","https://openalex.org/W2768629321","https://openalex.org/W2794643322","https://openalex.org/W2807741983","https://openalex.org/W2908261578","https://openalex.org/W2921955147","https://openalex.org/W2954559956","https://openalex.org/W2963000099","https://openalex.org/W2963407617","https://openalex.org/W2981038142","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W2998367975","https://openalex.org/W3013664888","https://openalex.org/W3021358026","https://openalex.org/W3031015890","https://openalex.org/W3034278799","https://openalex.org/W3048703323","https://openalex.org/W3091006519","https://openalex.org/W3117423974","https://openalex.org/W3173215816","https://openalex.org/W3205875899","https://openalex.org/W4286748781","https://openalex.org/W4295598622","https://openalex.org/W4295719664","https://openalex.org/W4297810554","https://openalex.org/W4301501993","https://openalex.org/W6637033378","https://openalex.org/W6640044251","https://openalex.org/W6712181171","https://openalex.org/W6713411898","https://openalex.org/W6738796088","https://openalex.org/W6745935785","https://openalex.org/W6746015766","https://openalex.org/W6752380930","https://openalex.org/W6757784512","https://openalex.org/W6770126465","https://openalex.org/W6796861069","https://openalex.org/W6840380725"],"related_works":["https://openalex.org/W2046459260","https://openalex.org/W2967463586","https://openalex.org/W2074679142","https://openalex.org/W2765830098","https://openalex.org/W1971989957","https://openalex.org/W2517338020","https://openalex.org/W3157641275","https://openalex.org/W4312300846","https://openalex.org/W2104042711","https://openalex.org/W4206221578"],"abstract_inverted_index":{"(MACRPO).":[0],"We":[1,108,128],"propose":[2,27,62],"two":[3],"novel":[4],"ways":[5],"of":[6,51,79,88],"integrating":[7],"information":[8],"across":[9],"agents":[10,82,99,157],"and":[11,26,49,55,72,119,125,135,147,149,161],"time":[12],"in":[13,21,96],"MACRPO:":[14],"First,":[15],"we":[16,61],"use":[17,32,87],"a":[18,28,63,84],"recurrent":[19,39],"layer":[20],"the":[22,33,38,43,47,77,98,130],"critic's":[23],"network":[24,44],"architecture":[25],"new":[29,64],"framework":[30],"to":[31,36,45,102],"proposed":[34],"meta-trajectory":[35],"train":[37],"layer.":[40],"This":[41],"allows":[42],"learn":[46],"cooperation":[48,80],"dynamics":[50],"interactions":[52],"between":[53,81,156],"agents,":[54],"also":[56,150],"handle":[57],"partial":[58],"observability.":[59],"Second,":[60],"advantage":[65],"function":[66],"that":[67],"incorporates":[68],"other":[69,169],"agents'":[70],"rewards":[71],"value":[73],"functions":[74],"by":[75],"controlling":[76],"level":[78],"using":[83],"parameter.":[85],"The":[86,163,171],"this":[89],"control":[90],"parameter":[91],"is":[92,173],"suitable":[93],"for":[94],"environments":[95,116],"which":[97],"are":[100],"unable":[101],"fully":[103],"cooperate":[104],"with":[105,117,132,153],"each":[106],"other.":[107],"evaluate":[109],"our":[110],"algorithm":[111],"on":[112],"three":[113],"challenging":[114],"multi-agent":[115,137],"continuous":[118],"discrete":[120],"action":[121],"spaces,":[122],"Deepdrive-Zero,":[123],"Multi-Walker,":[124],"Particle":[126],"environment.":[127],"compare":[129],"results":[131,164],"several":[133],"ablations":[134],"state-of-the-art":[136],"algorithms":[138],"such":[139,158],"as":[140,159],"MAGIC,":[141],"IC3Net,":[142],"CommNet,":[143],"GA-Comm,":[144],"QMIX,":[145],"MADDPG,":[146],"RMAPPO,":[148],"single-agent":[151],"methods":[152],"shared":[154],"parameters":[155],"IMPALA":[160],"APEX.":[162],"show":[165],"superior":[166],"performance":[167],"against":[168],"algorithms.":[170],"code":[172],"available":[174],"online":[175],"at":[176],"https://github.com/kargarisaac/macrpo.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}