{"id":"https://openalex.org/W4206132861","doi":"https://doi.org/10.3390/fi14010017","title":"The Important Role of Global State for Multi-Agent Reinforcement Learning","display_name":"The Important Role of Global State for Multi-Agent Reinforcement Learning","publication_year":2021,"publication_date":"2021-12-30","ids":{"openalex":"https://openalex.org/W4206132861","doi":"https://doi.org/10.3390/fi14010017"},"language":"en","primary_location":{"id":"doi:10.3390/fi14010017","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi14010017","pdf_url":"https://www.mdpi.com/1999-5903/14/1/17/pdf?version=1640919331","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-5903/14/1/17/pdf?version=1640919331","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002589174","display_name":"Shuailong Li","orcid":"https://orcid.org/0000-0001-6784-0563"},"institutions":[{"id":"https://openalex.org/I142078773","display_name":"Shenyang Institute of Automation","ror":"https://ror.org/00ft6nj33","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"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/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":"Shuailong Li","raw_affiliation_strings":["Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China","State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China","University of Chinese Academy of Sciences, Beijing 100049, China"],"raw_orcid":"https://orcid.org/0000-0001-6784-0563","affiliations":[{"raw_affiliation_string":"Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"raw_affiliation_string":"State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101669643","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0002-6771-6789"},"institutions":[{"id":"https://openalex.org/I142078773","display_name":"Shenyang Institute of Automation","ror":"https://ror.org/00ft6nj33","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"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/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":true,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China","University of Chinese Academy of Sciences, Beijing 100049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023270824","display_name":"Yuquan Leng","orcid":"https://orcid.org/0000-0003-4063-4545"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuquan Leng","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities, Southern University of Science and Technology, Shenzhen 518055, China","Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems, Department of Mechanical and Energy Engineering, Southern University of Science and Technology, Shenzhen 518055, China"],"raw_orcid":"https://orcid.org/0000-0003-4063-4545","affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities, Southern University of Science and Technology, Shenzhen 518055, China","institution_ids":["https://openalex.org/I3045169105"]},{"raw_affiliation_string":"Shenzhen Key Laboratory of Biomimetic Robotics and Intelligent Systems, Department of Mechanical and Energy Engineering, Southern University of Science and Technology, Shenzhen 518055, China","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100618787","display_name":"Xiaohui Wang","orcid":"https://orcid.org/0000-0002-3415-5612"},"institutions":[{"id":"https://openalex.org/I142078773","display_name":"Shenyang Institute of Automation","ror":"https://ror.org/00ft6nj33","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"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/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":"Xiaohui Wang","raw_affiliation_strings":["Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China","State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China","University of Chinese Academy of Sciences, Beijing 100049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"raw_affiliation_string":"State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China","institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5023270824","https://openalex.org/A5101669643"],"corresponding_institution_ids":["https://openalex.org/I142078773","https://openalex.org/I19820366","https://openalex.org/I3045169105","https://openalex.org/I4210165038"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1512},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1512},"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.19980359,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":"14","issue":"1","first_page":"17","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980000257492065,"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":0.9980000257492065,"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/T11975","display_name":"Evolutionary Algorithms and Applications","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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9926999807357788,"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":0.9064083099365234},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8098188638687134},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.6035809516906738},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5731026530265808},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5303576588630676},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.471680223941803},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.45621457695961},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4088316857814789},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3244391679763794}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9064083099365234},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8098188638687134},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6035809516906738},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5731026530265808},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5303576588630676},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.471680223941803},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.45621457695961},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4088316857814789},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3244391679763794},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/fi14010017","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi14010017","pdf_url":"https://www.mdpi.com/1999-5903/14/1/17/pdf?version=1640919331","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:gam:jftint:v:14:y:2021:i:1:p:17-:d:714777","is_oa":false,"landing_page_url":"https://www.mdpi.com/1999-5903/14/1/17/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:doaj.org/article:a1203083dba241aaaf763e3f12abc034","is_oa":true,"landing_page_url":"https://doaj.org/article/a1203083dba241aaaf763e3f12abc034","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":"Future Internet, Vol 14, Iss 1, p 17 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/fi14010017","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi14010017","pdf_url":"https://www.mdpi.com/1999-5903/14/1/17/pdf?version=1640919331","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","score":0.4699999988079071,"display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4206132861.pdf","grobid_xml":"https://content.openalex.org/works/W4206132861.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W103885025","https://openalex.org/W1518858799","https://openalex.org/W1641379095","https://openalex.org/W2099618002","https://openalex.org/W2121092017","https://openalex.org/W2136202932","https://openalex.org/W2145339207","https://openalex.org/W2146482048","https://openalex.org/W2147492008","https://openalex.org/W2156194062","https://openalex.org/W2257979135","https://openalex.org/W2280163991","https://openalex.org/W2617547828","https://openalex.org/W2618530766","https://openalex.org/W2760948241","https://openalex.org/W2766447205","https://openalex.org/W2794643322","https://openalex.org/W2962847657","https://openalex.org/W2981038142","https://openalex.org/W2989838630","https://openalex.org/W2997475283","https://openalex.org/W2997649476","https://openalex.org/W2997769754","https://openalex.org/W2997874851","https://openalex.org/W2997933098","https://openalex.org/W2998723654","https://openalex.org/W6630897036","https://openalex.org/W6695011786"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2089013912","https://openalex.org/W2076061571","https://openalex.org/W1987513656","https://openalex.org/W2145821588"],"abstract_inverted_index":{"Environmental":[0],"information":[1,36,47,60],"plays":[2],"an":[3],"important":[4],"role":[5],"in":[6,40],"deep":[7],"reinforcement":[8,24],"learning":[9,25],"(DRL).":[10],"However,":[11],"many":[12,66],"algorithms":[13,67],"do":[14],"not":[15],"pay":[16],"much":[17],"attention":[18],"to":[19,30,61],"environmental":[20,46,55,59],"information.":[21],"In":[22],"multi-agent":[23,133],"decision-making,":[26],"because":[27],"agents":[28,39],"need":[29],"make":[31],"decisions":[32],"combined":[33],"with":[34,78],"the":[35,41,45,52,62,79,82,87,95,117],"of":[37,54,72,94,109,116],"other":[38],"environment,":[42],"this":[43],"makes":[44],"more":[48],"important.":[49],"To":[50],"prove":[51],"importance":[53],"information,":[56],"we":[57],"added":[58],"algorithm.":[63],"We":[64],"evaluated":[65],"on":[68],"a":[69],"challenging":[70],"set":[71],"StarCraft":[73],"II":[74],"micromanagement":[75],"tasks.":[76],"Compared":[77],"original":[80,96,118],"algorithm,":[81,97],"standard":[83],"deviation":[84],"(except":[85,120],"for":[86,121],"VDN":[88,122],"algorithm)":[89],"was":[90,112],"smaller":[91],"than":[92,114],"that":[93,100,115,127],"which":[98,125],"shows":[99,126],"our":[101,110,128],"algorithm":[102,111,119],"has":[103],"better":[104],"stability.":[105],"The":[106],"average":[107],"score":[108],"higher":[113],"and":[123],"COMA),":[124],"work":[129],"significantly":[130],"outperforms":[131],"existing":[132],"RL":[134],"methods.":[135]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}
