{"id":"https://openalex.org/W4385482710","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191652","title":"Advantage Constrained Proximal Policy Optimization in Multi-Agent Reinforcement Learning","display_name":"Advantage Constrained Proximal Policy Optimization in Multi-Agent Reinforcement Learning","publication_year":2023,"publication_date":"2023-06-18","ids":{"openalex":"https://openalex.org/W4385482710","doi":"https://doi.org/10.1109/ijcnn54540.2023.10191652"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn54540.2023.10191652","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191652","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5006442353","display_name":"Weifan Li","orcid":"https://orcid.org/0000-0003-1871-8355"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weifan Li","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems,Beijing,China,100190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems,Beijing,China,100190","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080193690","display_name":"Yuanheng Zhu","orcid":"https://orcid.org/0000-0001-5384-423X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanheng Zhu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems,Beijing,China,100190","School of artificial intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems,Beijing,China,100190","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of artificial intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100624298","display_name":"Dongbin Zhao","orcid":"https://orcid.org/0000-0001-8218-9633"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbin Zhao","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems,Beijing,China,100190","School of artificial intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems,Beijing,China,100190","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of artificial intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"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":0.9939000010490417,"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":0.9939000010490417,"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/T11674","display_name":"Sports Analytics and Performance","score":0.9332000017166138,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9212999939918518,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7708182334899902},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6219761967658997},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.594205915927887},{"id":"https://openalex.org/keywords/lemma","display_name":"Lemma (botany)","score":0.5742543935775757},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5598999261856079},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.42024916410446167},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.4104142487049103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27425989508628845},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26630735397338867},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25336045026779175}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7708182334899902},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6219761967658997},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.594205915927887},{"id":"https://openalex.org/C2777759810","wikidata":"https://www.wikidata.org/wiki/Q149316","display_name":"Lemma (botany)","level":3,"score":0.5742543935775757},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5598999261856079},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.42024916410446167},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.4104142487049103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27425989508628845},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26630735397338867},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25336045026779175},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C46757340","wikidata":"https://www.wikidata.org/wiki/Q43238","display_name":"Poaceae","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn54540.2023.10191652","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn54540.2023.10191652","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.44999998807907104,"display_name":"Partnerships for the goals"}],"awards":[{"id":"https://openalex.org/G1195804794","display_name":null,"funder_award_id":"62136008","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/G1594336315","display_name":null,"funder_award_id":"2018AAA0102404","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"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/F4320322847","display_name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","ror":"https://ror.org/031141b54"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W2130801532","https://openalex.org/W2572587835","https://openalex.org/W2617547828","https://openalex.org/W2736601468","https://openalex.org/W2785556016","https://openalex.org/W2807741983","https://openalex.org/W2891076394","https://openalex.org/W2963890729","https://openalex.org/W2996726407","https://openalex.org/W3007689182","https://openalex.org/W3011672202","https://openalex.org/W3046288222","https://openalex.org/W3099689767","https://openalex.org/W3113301408","https://openalex.org/W3163926178","https://openalex.org/W3170533301","https://openalex.org/W3196692929","https://openalex.org/W3196869853","https://openalex.org/W3200561352","https://openalex.org/W3207544809","https://openalex.org/W3210169707","https://openalex.org/W4286748781","https://openalex.org/W4288594419","https://openalex.org/W4295598622","https://openalex.org/W6638018090","https://openalex.org/W6679257226","https://openalex.org/W6741002519","https://openalex.org/W6749304979","https://openalex.org/W6752380930","https://openalex.org/W6758846586","https://openalex.org/W6771787661","https://openalex.org/W6781750019","https://openalex.org/W6795908048","https://openalex.org/W6800682094","https://openalex.org/W6801058317","https://openalex.org/W6802002411","https://openalex.org/W6840380725"],"related_works":["https://openalex.org/W3006682748","https://openalex.org/W1097487277","https://openalex.org/W2768610039","https://openalex.org/W4308265086","https://openalex.org/W2949964783","https://openalex.org/W2801357573","https://openalex.org/W2106889256","https://openalex.org/W2982363256","https://openalex.org/W2974000959","https://openalex.org/W2358024260"],"abstract_inverted_index":{"We":[0],"investigate":[1],"the":[2,87,99,102,109,115,148,152,157,172],"integration":[3],"of":[4,101,111],"value-based":[5,24],"and":[6,32,50,85,106,156,168],"policy":[7,43,62,121],"gradient":[8,44,52,63,122],"methods":[9,45],"in":[10,23,41],"multi-agent":[11,42,61,93],"reinforcement":[12],"learning":[13],"(MARL).":[14],"The":[15,142],"Individual-Global-Max":[16],"(IGM)":[17],"principle":[18],"plays":[19],"an":[20,128],"important":[21],"role":[22],"MARL,":[25],"as":[26,165],"it":[27],"ensures":[28],"consistency":[29,100],"between":[30],"joint":[31,88],"local":[33,77,107],"action":[34],"values.":[35],"IGM":[36],"is":[37,145],"difficult":[38],"to":[39,47,98,132,139,171],"guarantee":[40],"due":[46],"stochastic":[48],"exploration":[49],"conflicting":[51],"directions.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57],"propose":[58],"a":[59,136],"novel":[60],"algorithm":[64],"called":[65],"Advantage":[66],"Constrained":[67],"Proximal":[68],"Policy":[69],"Optimization":[70],"(ACPPO).":[71],"ACPPO":[72,161],"calculates":[73],"each":[74,112],"agent's":[75],"current":[76],"state-action":[78,89],"advantage":[79,83,90,94,105],"based":[80,91],"on":[81,92],"their":[82],"network":[84],"estimates":[86],"decomposition":[95],"lemma.":[96],"According":[97],"estimated":[103],"joint-action":[104,116],"advantage,":[108],"coefficient":[110],"agent":[113],"constrains":[114],"advantage.":[117],"ACPPO,":[118],"unlike":[119],"previous":[120],"MARL":[123],"algorithms,":[124],"does":[125],"not":[126],"require":[127],"additional":[129],"sampled":[130],"baseline":[131],"reduce":[133],"variance":[134],"or":[135],"sequential":[137],"scheme":[138],"improve":[140],"accuracy.":[141],"proposed":[143],"method":[144],"evaluated":[146],"using":[147],"continuous":[149],"matrix":[150],"game,":[151],"Starcraft":[153],"Multi-Agent":[154,158],"Challenge,":[155],"MuJoCo":[159],"task.":[160],"outperforms":[162],"baselines":[163],"such":[164],"MAPPO,":[166],"MADDPG,":[167],"HATRPO,":[169],"according":[170],"results.":[173]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}