{"id":"https://openalex.org/W3198965389","doi":"https://doi.org/10.1109/access.2021.3113350","title":"QSOD: Hybrid Policy Gradient for Deep Multi-agent Reinforcement Learning","display_name":"QSOD: Hybrid Policy Gradient for Deep Multi-agent Reinforcement Learning","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3198965389","doi":"https://doi.org/10.1109/access.2021.3113350","mag":"3198965389"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3113350","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3113350","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09540595.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/ielx7/6287639/6514899/09540595.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053810241","display_name":"Hafiz Muhammad Raza Ur Rehman","orcid":"https://orcid.org/0000-0003-2230-6927"},"institutions":[{"id":"https://openalex.org/I55240360","display_name":"Yeungnam University","ror":"https://ror.org/05yc6p159","country_code":"KR","type":"education","lineage":["https://openalex.org/I55240360"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hafiz Muhammad Raza Ur Rehman","raw_affiliation_strings":["Department of Information and Communication Engineering, Yeungnam University, Gyeongsan, South Korea","Department of Information and Communication Engineering Yeungnam University Gyeongsan, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-2230-6927","affiliations":[{"raw_affiliation_string":"Department of Information and Communication Engineering, Yeungnam University, Gyeongsan, South Korea","institution_ids":["https://openalex.org/I55240360"]},{"raw_affiliation_string":"Department of Information and Communication Engineering Yeungnam University Gyeongsan, South Korea","institution_ids":["https://openalex.org/I55240360"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084878720","display_name":"Byung-Won On","orcid":"https://orcid.org/0000-0001-6929-3188"},"institutions":[{"id":"https://openalex.org/I120158604","display_name":"Kunsan National University","ror":"https://ror.org/02yj55q56","country_code":"KR","type":"education","lineage":["https://openalex.org/I120158604"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byung-Won On","raw_affiliation_strings":["Department of Software Convergence Engineering, Kunsan National University, Gunsan, South Korea","Department of Software Convergence Engineering, Kunsan National University, Gunsan 54150, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-6929-3188","affiliations":[{"raw_affiliation_string":"Department of Software Convergence Engineering, Kunsan National University, Gunsan, South Korea","institution_ids":["https://openalex.org/I120158604"]},{"raw_affiliation_string":"Department of Software Convergence Engineering, Kunsan National University, Gunsan 54150, South Korea","institution_ids":["https://openalex.org/I120158604"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080626085","display_name":"Devarani Devi Ningombam","orcid":"https://orcid.org/0000-0002-6946-6584"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Devarani Devi Ningombam","raw_affiliation_strings":["Planning Division, Electronics and Telecommunications Research Institute, Daejeon, South Korea","Planning Division, Electronics and Telecommunications Research Institute Daejeon, 34129, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Planning Division, Electronics and Telecommunications Research Institute, Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]},{"raw_affiliation_string":"Planning Division, Electronics and Telecommunications Research Institute Daejeon, 34129, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085539609","display_name":"Sungwon Yi","orcid":"https://orcid.org/0000-0002-4986-9546"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungwon Yi","raw_affiliation_strings":["Planning Division, Electronics and Telecommunications Research Institute, Daejeon, South Korea","Planning Division, Electronics and Telecommunications Research Institute Daejeon, 34129, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Planning Division, Electronics and Telecommunications Research Institute, Daejeon, South Korea","institution_ids":["https://openalex.org/I142401562"]},{"raw_affiliation_string":"Planning Division, Electronics and Telecommunications Research Institute Daejeon, 34129, South Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044080887","display_name":"Gyu Sang Choi","orcid":"https://orcid.org/0000-0002-0854-768X"},"institutions":[{"id":"https://openalex.org/I55240360","display_name":"Yeungnam University","ror":"https://ror.org/05yc6p159","country_code":"KR","type":"education","lineage":["https://openalex.org/I55240360"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gyu Sang Choi","raw_affiliation_strings":["Department of Information and Communication Engineering, Yeungnam University, Gyeongsan, South Korea","Department of Information and Communication Engineering Yeungnam University Gyeongsan, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-0854-768X","affiliations":[{"raw_affiliation_string":"Department of Information and Communication Engineering, Yeungnam University, Gyeongsan, South Korea","institution_ids":["https://openalex.org/I55240360"]},{"raw_affiliation_string":"Department of Information and Communication Engineering Yeungnam University Gyeongsan, South Korea","institution_ids":["https://openalex.org/I55240360"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.1195,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.82521166,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"9","issue":null,"first_page":"129728","last_page":"129741"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9876999855041504,"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":0.8534901142120361},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6451897621154785},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4280426502227783}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8534901142120361},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6451897621154785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4280426502227783}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2021.3113350","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3113350","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09540595.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:68f0b78038fa4f6abfdf228735c49cfa","is_oa":true,"landing_page_url":"https://doaj.org/article/68f0b78038fa4f6abfdf228735c49cfa","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 9, Pp 129728-129741 (2021)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3113350","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3113350","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09540595.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":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G3591598716","display_name":null,"funder_award_id":"FA2386","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G5407164105","display_name":null,"funder_award_id":"19YE1410","funder_id":"https://openalex.org/F4320322093","funder_display_name":"Electronics and Telecommunications Research Institute"},{"id":"https://openalex.org/G6753616810","display_name":null,"funder_award_id":"FA2386-19-1-4020","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320322093","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3198965389.pdf","grobid_xml":"https://content.openalex.org/works/W3198965389.grobid-xml"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W56117469","https://openalex.org/W98006832","https://openalex.org/W1641379095","https://openalex.org/W1999561548","https://openalex.org/W2002302337","https://openalex.org/W2012812921","https://openalex.org/W2061438946","https://openalex.org/W2099618002","https://openalex.org/W2101934420","https://openalex.org/W2110906765","https://openalex.org/W2134779831","https://openalex.org/W2145339207","https://openalex.org/W2345827752","https://openalex.org/W2518713116","https://openalex.org/W2559793483","https://openalex.org/W2562637642","https://openalex.org/W2588790649","https://openalex.org/W2592798481","https://openalex.org/W2594794854","https://openalex.org/W2617547828","https://openalex.org/W2749807327","https://openalex.org/W2756196406","https://openalex.org/W2768629321","https://openalex.org/W2807741983","https://openalex.org/W2898567809","https://openalex.org/W2949963774","https://openalex.org/W2963658727","https://openalex.org/W2964338167","https://openalex.org/W2966896140","https://openalex.org/W2970129473","https://openalex.org/W2973184394","https://openalex.org/W3011120880","https://openalex.org/W3046288222","https://openalex.org/W3093287223","https://openalex.org/W3114105834","https://openalex.org/W4288091739","https://openalex.org/W4293862243","https://openalex.org/W4295402504","https://openalex.org/W4295598622","https://openalex.org/W4297665038","https://openalex.org/W4299802797","https://openalex.org/W6602332174","https://openalex.org/W6604066176","https://openalex.org/W6676769901","https://openalex.org/W6680096503","https://openalex.org/W6713411898","https://openalex.org/W6726754200","https://openalex.org/W6730690867","https://openalex.org/W6734678876","https://openalex.org/W6735011893","https://openalex.org/W6737849119","https://openalex.org/W6738796088","https://openalex.org/W6743756900","https://openalex.org/W6744537943","https://openalex.org/W6749304979","https://openalex.org/W6752380930","https://openalex.org/W6762491519","https://openalex.org/W6766854325","https://openalex.org/W6767327128","https://openalex.org/W6775686901","https://openalex.org/W6781750019","https://openalex.org/W6787444798","https://openalex.org/W6864424756"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109"],"abstract_inverted_index":{"When":[0],"individuals":[1],"interact":[2],"with":[3,179,194],"one":[4,180],"another":[5],"to":[6,15,68,157,189],"accomplish":[7],"specific":[8],"goals,":[9],"they":[10],"learn":[11],"from":[12],"others\u2019":[13],"experiences":[14],"achieve":[16],"the":[17,70,74,134,159,172,176,184,195],"tasks":[18],"at":[19],"hand.":[20],"The":[21,112],"same":[22],"holds":[23],"for":[24,56,133],"learning":[25,36],"in":[26,40,165,211],"virtual":[27],"environments,":[28],"such":[29,96],"as":[30,97,142],"video":[31],"games.":[32],"Deep":[33],"multiagent":[34],"reinforcement":[35],"shows":[37],"promising":[38],"results":[39,202],"terms":[41],"of":[42,73,118,137,161],"completing":[43],"many":[44],"challenging":[45],"tasks.":[46],"To":[47,59],"demonstrate":[48,203],"its":[49],"viability,":[50],"most":[51],"algorithms":[52,95,197],"use":[53],"value":[54,64,93],"decomposition":[55,65,94],"multiple":[57],"agents.":[58],"guide":[60],"each":[61],"agent,":[62],"behavior":[63],"is":[66,155,168],"utilized":[67],"decompose":[69],"combined":[71],"Q-value":[72,143],"agents":[75,173],"into":[76],"individual":[77,105,139],"agent":[78,106,140],"Q-values.":[79],"A":[80,150],"different":[81],"mixing":[82],"method":[83,103],"can":[84],"be":[85],"utilized,":[86],"using":[87,145],"a":[88,109,129],"monotonicity":[89],"assumption":[90],"based":[91],"on":[92],"QMIX":[98,198,208],"and":[99,147,199,209,214],"QVMix.":[100,200],"However,":[101],"this":[102,125],"selects":[104],"actions":[107],"through":[108,175],"greedy":[110],"policy.":[111],"agents,":[113],"which":[114],"require":[115],"large":[116],"numbers":[117],"training":[119,217],"trials,":[120],"are":[121],"not":[122],"addressed.":[123],"In":[124],"paper,":[126],"we":[127],"propose":[128],"novel":[130],"hybrid":[131],"policy":[132],"action":[135],"selection":[136],"an":[138],"known":[141],"Selection":[144],"Optimization":[146],"DRL":[148],"(QSOD).":[149],"grey":[151],"wolf":[152],"optimizer":[153],"(GWO)":[154],"used":[156,183],"determine":[158],"choice":[160],"individuals\u2019":[162],"actions.":[163],"As":[164],"GWO,":[166],"there":[167],"proper":[169],"attention":[170],"among":[171],"facilitated":[174],"agents\u2019":[177],"coordination":[178],"another.":[181],"We":[182],"StarCraft":[185],"2":[186],"Learning":[187],"Environment":[188],"compare":[190],"our":[191,205],"proposed":[192],"algorithm":[193,206],"state-of-the-art":[196],"Experimental":[201],"that":[204],"outperforms":[207],"QVMix":[210],"all":[212],"scenarios":[213],"requires":[215],"fewer":[216],"trials.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}