{"id":"https://openalex.org/W3039502116","doi":"https://doi.org/10.1109/access.2020.3007219","title":"Cooperative Multi-Agent Reinforcement Learning With Approximate Model Learning","display_name":"Cooperative Multi-Agent Reinforcement Learning With Approximate Model Learning","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3039502116","doi":"https://doi.org/10.1109/access.2020.3007219","mag":"3039502116"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.3007219","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3007219","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09133381.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09133381.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100716896","display_name":"Young Joon Park","orcid":"https://orcid.org/0000-0002-3950-3065"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Young Joon Park","raw_affiliation_strings":["School of Industrial Management Engineering, Korea University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-3950-3065","affiliations":[{"raw_affiliation_string":"School of Industrial Management Engineering, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100360631","display_name":"Young Jae Lee","orcid":"https://orcid.org/0000-0002-1309-0602"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Young Jae Lee","raw_affiliation_strings":["School of Industrial Management Engineering, Korea University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Industrial Management Engineering, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058258354","display_name":"Seoung Bum Kim","orcid":"https://orcid.org/0000-0002-2205-8516"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seoung Bum Kim","raw_affiliation_strings":["School of Industrial Management Engineering, Korea University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-2205-8516","affiliations":[{"raw_affiliation_string":"School of Industrial Management Engineering, Korea University, Seoul, South Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.3038,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.84782145,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"8","issue":null,"first_page":"125389","last_page":"125400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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":0.994700014591217,"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"}},{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9243999719619751,"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":0.883345901966095},{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.8242767453193665},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8052817583084106},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5659053921699524},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5645298957824707},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.46457159519195557},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3649665117263794},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.32807791233062744},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08448901772499084}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.883345901966095},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.8242767453193665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8052817583084106},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5659053921699524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5645298957824707},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.46457159519195557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3649665117263794},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.32807791233062744},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08448901772499084},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2020.3007219","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3007219","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09133381.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:bdfbf5c114e74e639e433cd1bc262c55","is_oa":true,"landing_page_url":"https://doaj.org/article/bdfbf5c114e74e639e433cd1bc262c55","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":"IEEE Access, Vol 8, Pp 125389-125400 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.3007219","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3007219","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09133381.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3281661566","display_name":null,"funder_award_id":"NRF-2019R1A4A1024732","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G6221987393","display_name":null,"funder_award_id":"NRF-2019R1A4A1024732","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G6557190913","display_name":null,"funder_award_id":"2019R1A4A1024732","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322006","display_name":"Ministry of Culture, Sports and Tourism","ror":"https://ror.org/02fkk6k65"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320323890","display_name":"Korea Creative Content Agency","ror":"https://ror.org/036vyg793"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3039502116.pdf","grobid_xml":"https://content.openalex.org/works/W3039502116.grobid-xml"},"referenced_works_count":79,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1192553058","https://openalex.org/W1507591516","https://openalex.org/W1513468570","https://openalex.org/W1641379095","https://openalex.org/W2012812921","https://openalex.org/W2026662445","https://openalex.org/W2101934420","https://openalex.org/W2122763142","https://openalex.org/W2134779831","https://openalex.org/W2142505627","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2165150801","https://openalex.org/W2166533447","https://openalex.org/W2173248099","https://openalex.org/W2257979135","https://openalex.org/W2292533394","https://openalex.org/W2395575420","https://openalex.org/W2602275733","https://openalex.org/W2604283518","https://openalex.org/W2604726708","https://openalex.org/W2617547828","https://openalex.org/W2756196406","https://openalex.org/W2768629321","https://openalex.org/W2786969620","https://openalex.org/W2810602713","https://openalex.org/W2894976951","https://openalex.org/W2902591104","https://openalex.org/W2920362155","https://openalex.org/W2924816077","https://openalex.org/W2945703303","https://openalex.org/W2949238434","https://openalex.org/W2950151997","https://openalex.org/W2950471160","https://openalex.org/W2951948137","https://openalex.org/W2953444180","https://openalex.org/W2954559956","https://openalex.org/W2962872206","https://openalex.org/W2962938168","https://openalex.org/W2963658727","https://openalex.org/W2963661429","https://openalex.org/W2963864421","https://openalex.org/W2963881016","https://openalex.org/W2964229770","https://openalex.org/W2979814938","https://openalex.org/W3004640943","https://openalex.org/W3004732081","https://openalex.org/W3034236692","https://openalex.org/W3099518626","https://openalex.org/W3104860527","https://openalex.org/W4295598622","https://openalex.org/W4299802797","https://openalex.org/W4302570325","https://openalex.org/W4385245566","https://openalex.org/W6627932998","https://openalex.org/W6630520071","https://openalex.org/W6678214046","https://openalex.org/W6680096503","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6696324988","https://openalex.org/W6712181171","https://openalex.org/W6729448088","https://openalex.org/W6735650757","https://openalex.org/W6736742618","https://openalex.org/W6737849119","https://openalex.org/W6738796088","https://openalex.org/W6739901393","https://openalex.org/W6744537943","https://openalex.org/W6749304979","https://openalex.org/W6755069753","https://openalex.org/W6760405395","https://openalex.org/W6762946645","https://openalex.org/W6764943343","https://openalex.org/W6765166828","https://openalex.org/W6773620346","https://openalex.org/W6773690109"],"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":{"In":[0],"multi-agent":[1,78,172,189],"reinforcement":[2,190],"learning,":[3,155],"it":[4,49,186],"is":[5,50],"essential":[6],"for":[7,73],"agents":[8,67,110],"to":[9,13,18,53,100,111,119,127,136,140,143,162,174],"learn":[10],"communication":[11,31],"protocol":[12],"optimize":[14],"collaboration":[15],"policies":[16,47,64,76],"and":[17,44,57,96,115,118,153,166,178,199],"solve":[19,29],"unstable":[20,154],"learning":[21,45,74,191,197],"problems.":[22],"Existing":[23],"methods":[24,37],"based":[25],"on":[26],"actor-critic":[27,94],"networks":[28,95,107,131,161],"the":[30,55,60,63,82,109,129,137,144,167,176,181,203,210],"problem":[32],"among":[33,84],"agents.":[34,85],"However,":[35],"these":[36],"have":[38],"difficulty":[39],"in":[40,77,193,202],"improving":[41],"sample":[42],"efficiency":[43,198],"robust":[46],"because":[48],"not":[51],"easy":[52],"understand":[54],"dynamics":[56],"nonstationary":[58],"of":[59,65,90,180,195],"environment":[61],"as":[62],"other":[66,214],"change.":[68],"We":[69,170],"propose":[70,157],"a":[71],"method":[72,88,183,212],"cooperative":[75],"environments":[79,173],"by":[80,132,184],"considering":[81],"communications":[83],"The":[86,105,123,206],"proposed":[87,182,211],"consists":[89],"recurrent":[91],"neural":[92],"network-based":[93],"deterministic":[97],"policy":[98],"gradients":[99],"centrally":[101],"train":[102,128],"decentralized":[103],"policies.":[104],"actor":[106,130],"cause":[108],"communicate":[112],"using":[113,158],"forward":[114],"backward":[116],"paths":[117],"determine":[120],"subsequent":[121],"actions.":[122],"critic":[124],"network":[125],"helps":[126],"sending":[133],"gradient":[134],"signals":[135],"actors":[138],"according":[139],"their":[141],"contribution":[142],"global":[145],"reward.":[146],"To":[147],"address":[148],"issues":[149],"with":[150,187],"partial":[151],"observability":[152],"we":[156],"auxiliary":[159],"prediction":[160],"approximate":[163],"state":[164],"transitions":[165],"reward":[168],"function.":[169],"used":[171],"demonstrate":[175,208],"usefulness":[177],"superiority":[179],"comparing":[185],"existing":[188],"methods,":[192],"terms":[194],"both":[196],"goal":[200],"achievements":[201],"test":[204],"phase.":[205],"results":[207],"that":[209],"outperformed":[213],"alternatives.":[215]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}