{"id":"https://openalex.org/W4312804952","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892004","title":"Meta Proximal Policy Optimization for Cooperative Multi-Agent Continuous Control","display_name":"Meta Proximal Policy Optimization for Cooperative Multi-Agent Continuous Control","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312804952","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892004"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892004","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892004","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073310872","display_name":"Boli Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Boli Fang","raw_affiliation_strings":["Indiana University,Department of Computer Science,Bloomington,IN,USA","Department of Computer Science, Indiana University, Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"Indiana University,Department of Computer Science,Bloomington,IN,USA","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"Department of Computer Science, Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109521346","display_name":"Zhenghao Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenghao Peng","raw_affiliation_strings":["Chinese University of Hong Kong,Department of Information Engineering,Hong Kong,China","Department of Information Engineering, Chinese University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong,Department of Information Engineering,Hong Kong,China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Information Engineering, Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101409444","display_name":"Hao Sun","orcid":"https://orcid.org/0000-0002-1314-4957"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hao Sun","raw_affiliation_strings":["University of Cambridge,Department of Applied Mathematics and Theoretical Physics,UK","Department of Applied Mathematics and Theoretical Physics, University of Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"University of Cambridge,Department of Applied Mathematics and Theoretical Physics,UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Department of Applied Mathematics and Theoretical Physics, University of Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100418224","display_name":"Qin Zhang","orcid":"https://orcid.org/0000-0002-6851-3115"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qin Zhang","raw_affiliation_strings":["Indiana University,Department of Computer Science,Bloomington,IN,USA","Department of Computer Science, Indiana University, Bloomington, IN, USA"],"affiliations":[{"raw_affiliation_string":"Indiana University,Department of Computer Science,Bloomington,IN,USA","institution_ids":["https://openalex.org/I4210119109"]},{"raw_affiliation_string":"Department of Computer Science, Indiana University, Bloomington, IN, USA","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5073310872"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":0.1041,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.32877229,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"abs 2009 10897","issue":null,"first_page":"1","last_page":"8"},"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.98089998960495,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9753999710083008,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.8844119906425476},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7240703701972961},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7233453392982483},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6010802984237671},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.5021486282348633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46499907970428467},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.46127769351005554},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.38289469480514526},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3149564266204834},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11123606562614441}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8844119906425476},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7240703701972961},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7233453392982483},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6010802984237671},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.5021486282348633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46499907970428467},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.46127769351005554},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38289469480514526},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3149564266204834},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11123606562614441},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892004","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892004","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4805677947","display_name":null,"funder_award_id":"CCF-2006591","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1771410628","https://openalex.org/W2026662445","https://openalex.org/W2158782408","https://openalex.org/W2163302320","https://openalex.org/W2594794854","https://openalex.org/W2617547828","https://openalex.org/W2626637010","https://openalex.org/W2736601468","https://openalex.org/W2747213132","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2803767077","https://openalex.org/W2811374584","https://openalex.org/W2883532348","https://openalex.org/W2894976951","https://openalex.org/W2949963774","https://openalex.org/W2963262099","https://openalex.org/W2963864421","https://openalex.org/W2963871073","https://openalex.org/W2964043796","https://openalex.org/W2964096423","https://openalex.org/W2970272688","https://openalex.org/W2972122474","https://openalex.org/W3011672202","https://openalex.org/W3035802247","https://openalex.org/W3042933240","https://openalex.org/W3084269620","https://openalex.org/W3094349299","https://openalex.org/W3102824929","https://openalex.org/W3104860527","https://openalex.org/W3127561923","https://openalex.org/W3134226813","https://openalex.org/W3135457936","https://openalex.org/W3209101326","https://openalex.org/W4214717370","https://openalex.org/W4287662662","https://openalex.org/W4295598622","https://openalex.org/W4299802797","https://openalex.org/W4302570325","https://openalex.org/W6627932998","https://openalex.org/W6638018090","https://openalex.org/W6684126333","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6703271639","https://openalex.org/W6735011893","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6749304979","https://openalex.org/W6749859622","https://openalex.org/W6751869817","https://openalex.org/W6752963931","https://openalex.org/W6755069753","https://openalex.org/W6762491519","https://openalex.org/W6767151588","https://openalex.org/W6773319185","https://openalex.org/W6779438722","https://openalex.org/W6780815668","https://openalex.org/W6784046417","https://openalex.org/W6791533262"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2121910908","https://openalex.org/W2768698792"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,73,117],"propose":[4],"Multi-Agent":[5],"Proxy":[6],"Proximal":[7,80],"Policy":[8,81],"Optimization":[9,82],"(MA3PO),":[10],"a":[11],"novel":[12],"multi-agent":[13,25,37,112,157],"deep":[14],"reinforcement":[15,38,158],"learning":[16,39,159],"algorithm":[17,83,146,169],"that":[18,34,84,144,167],"tackles":[19],"the":[20,32,62,77,93,105,123,131,149,175],"challenge":[21],"of":[22,64,76,87,95,107,125],"cooperative":[23,111],"continuous":[24,57,88,163],"control.":[26],"Our":[27],"method":[28],"is":[29,170],"driven":[30],"by":[31],"observation":[33],"most":[35],"existing":[36,176],"algorithms":[40],"mainly":[41],"focus":[42],"on":[43,155],"discrete":[44],"state/action":[45,58],"spaces":[46,165],"and":[47,67,91,134],"are":[48],"thus":[49],"computationally":[50],"infeasible":[51],"when":[52],"extended":[53],"to":[54,68,103,121,138],"environments":[55,161],"with":[56,162,174],"spaces.":[59],"To":[60],"address":[61],"issue":[63],"computational":[65],"complexity":[66],"better":[69],"model":[70],"intra-agent":[71],"collaboration,":[72],"make":[74],"use":[75],"recently":[78],"successful":[79],"effectively":[85],"explores":[86],"action":[89,164],"spaces,":[90],"incorporate":[92],"notion":[94],"intrinsic":[96,128],"motivation":[97,129],"via":[98],"meta-gradient":[99,136],"methods":[100,137],"so":[101,143],"as":[102],"stimulate":[104],"behavior":[106],"individual":[108,126],"agents":[109],"in":[110],"settings.":[113],"Towards":[114],"these":[115],"ends,":[116],"design":[118],"proxy":[119],"rewards":[120],"quantify":[122],"effect":[124],"agent-level":[127],"onto":[130],"team-level":[132,150],"reward,":[133],"apply":[135],"leverage":[139],"such":[140],"an":[141],"addition":[142],"our":[145,168],"can":[147],"learn":[148],"cumulative":[151],"reward":[152],"effectively.":[153],"Experiments":[154],"various":[156],"benchmark":[160],"demonstrate":[166],"not":[171],"only":[172],"comparable":[173],"state-of-the-art":[177],"benchmarks,":[178],"but":[179],"also":[180],"significantly":[181],"reduces":[182],"training":[183],"time":[184],"complexity.":[185]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}