{"id":"https://openalex.org/W4390742939","doi":"https://doi.org/10.1007/s11633-023-1454-4","title":"Distributed Deep Reinforcement Learning: A Survey and a Multi-player Multi-agent Learning Toolbox","display_name":"Distributed Deep Reinforcement Learning: A Survey and a Multi-player Multi-agent Learning Toolbox","publication_year":2024,"publication_date":"2024-01-11","ids":{"openalex":"https://openalex.org/W4390742939","doi":"https://doi.org/10.1007/s11633-023-1454-4"},"language":"en","primary_location":{"id":"doi:10.1007/s11633-023-1454-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11633-023-1454-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11633-023-1454-4.pdf","source":{"id":"https://openalex.org/S28082686","display_name":"International Journal of Automation and Computing","issn_l":"1476-8186","issn":["1476-8186","1751-8520","2731-538X","2731-5398"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Intelligence Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11633-023-1454-4.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083652259","display_name":"Qiyue Yin","orcid":"https://orcid.org/0000-0002-3442-6275"},"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/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"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":"Qiyue Yin","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China"],"raw_orcid":"https://orcid.org/0000-0002-3442-6275","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100563040","display_name":"Tongtong Yu","orcid":"https://orcid.org/0009-0009-8600-9033"},"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/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tongtong Yu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004671129","display_name":"Shengqi Shen","orcid":"https://orcid.org/0000-0003-4422-2636"},"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/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengqi Shen","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101912623","display_name":"Jun Yang","orcid":"https://orcid.org/0000-0002-9386-5825"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yang","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101199074","display_name":"Meijing Zhao","orcid":null},"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/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meijing Zhao","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111924466","display_name":"Wancheng Ni","orcid":null},"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/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"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":"Wancheng Ni","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028693655","display_name":"Kaiqi Huang","orcid":"https://orcid.org/0000-0002-2677-9273"},"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/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"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":"Kaiqi Huang","raw_affiliation_strings":["Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Beijing, 100190, China","Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100644630","display_name":"Bin Liang","orcid":"https://orcid.org/0000-0002-8591-8843"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Liang","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115602506","display_name":"Liang Wang","orcid":"https://orcid.org/0000-0001-5224-8647"},"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/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210097554","display_name":"Center for Excellence in Brain Science and Intelligence Technology","ror":"https://ror.org/00vpwhm04","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"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":"Liang Wang","raw_affiliation_strings":["Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Beijing, 100190, China","Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210097554"]},{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5083652259"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879","https://openalex.org/I4210165038"],"apc_list":{"value":2890,"currency":"USD","value_usd":2890},"apc_paid":{"value":2890,"currency":"USD","value_usd":2890},"fwci":9.1518,"has_fulltext":true,"cited_by_count":38,"citation_normalized_percentile":{"value":0.98258598,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"21","issue":"3","first_page":"411","last_page":"430"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9643999934196472,"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/T11674","display_name":"Sports Analytics and Performance","score":0.9562000036239624,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9280548095703125},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7428981065750122},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6001467108726501},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5553012490272522},{"id":"https://openalex.org/keywords/toolbox","display_name":"Toolbox","score":0.531218409538269},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.4616576135158539},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.43050575256347656},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3633311688899994},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.27202776074409485}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9280548095703125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7428981065750122},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6001467108726501},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5553012490272522},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.531218409538269},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.4616576135158539},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.43050575256347656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3633311688899994},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27202776074409485},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11633-023-1454-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11633-023-1454-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11633-023-1454-4.pdf","source":{"id":"https://openalex.org/S28082686","display_name":"International Journal of Automation and Computing","issn_l":"1476-8186","issn":["1476-8186","1751-8520","2731-538X","2731-5398"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Intelligence Research","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11633-023-1454-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11633-023-1454-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11633-023-1454-4.pdf","source":{"id":"https://openalex.org/S28082686","display_name":"International Journal of Automation and Computing","issn_l":"1476-8186","issn":["1476-8186","1751-8520","2731-538X","2731-5398"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Intelligence Research","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320335639","display_name":"Institute of Automation, Chinese Academy of Sciences","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4390742939.pdf"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1584496882","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2260756217","https://openalex.org/W2574978968","https://openalex.org/W2601298905","https://openalex.org/W2617766261","https://openalex.org/W2623431351","https://openalex.org/W2766447205","https://openalex.org/W2773381986","https://openalex.org/W2780624097","https://openalex.org/W2786036274","https://openalex.org/W2787938642","https://openalex.org/W2794643322","https://openalex.org/W2810602713","https://openalex.org/W2811374584","https://openalex.org/W2877093712","https://openalex.org/W2902907165","https://openalex.org/W2908064123","https://openalex.org/W2972087877","https://openalex.org/W2975999915","https://openalex.org/W2976996772","https://openalex.org/W2981187905","https://openalex.org/W2982316857","https://openalex.org/W3011574394","https://openalex.org/W3026202797","https://openalex.org/W3037237150","https://openalex.org/W3088409176","https://openalex.org/W3099518626","https://openalex.org/W3100789280","https://openalex.org/W3101562231","https://openalex.org/W3114511015","https://openalex.org/W3119852584","https://openalex.org/W3129336662","https://openalex.org/W3156295478","https://openalex.org/W3169696988","https://openalex.org/W3183892796","https://openalex.org/W4246795719","https://openalex.org/W4313678669","https://openalex.org/W6681187623","https://openalex.org/W6684859321","https://openalex.org/W6718092244","https://openalex.org/W6748554570","https://openalex.org/W6756303580","https://openalex.org/W6758846586","https://openalex.org/W6767919266"],"related_works":["https://openalex.org/W4205140848","https://openalex.org/W2068663075","https://openalex.org/W2264067234","https://openalex.org/W2978678743","https://openalex.org/W2797837731","https://openalex.org/W3124243301","https://openalex.org/W4393677513","https://openalex.org/W1571502335","https://openalex.org/W1589409554","https://openalex.org/W4390832911"],"abstract_inverted_index":{"Abstract":[0],"With":[1],"the":[2,90,98,124,184,187],"breakthrough":[3],"of":[4,43,92,152,186],"AlphaGo,":[5],"deep":[6,33,53,68,101,120,132,146,166,197,232],"reinforcement":[7,34,54,69,102,121,133,147,167,198,233],"learning":[8,30,35,70,103,122,148,168,199],"has":[9,71],"become":[10],"a":[11,40,162,180,220,223],"recognized":[12],"technique":[13],"for":[14,50,190,225],"solving":[15],"sequential":[16],"decision-making":[17],"problems.":[18],"Despite":[19],"its":[20,26,73],"reputation,":[21],"data":[22],"inefficiency":[23],"caused":[24],"by":[25,96],"trial":[27],"and":[28,62,82,105,160,172,193,210],"error":[29],"mechanism":[31],"makes":[32],"difficult":[36],"to":[37,109,123,143,206],"apply":[38],"in":[39,75,230],"wide":[41],"range":[42],"areas.":[44],"Many":[45],"methods":[46,104],"have":[47],"been":[48],"developed":[49,171],"sample":[51],"efficient":[52,111],"learning,":[55,113],"such":[56,78],"as":[57,79],"environment":[58],"modelling,":[59],"experience":[60],"transfer,":[61],"distributed":[63,67,100,112,119,131,145,165,196,231],"modifications,":[64],"among":[65],"which":[66,174],"shown":[72],"potential":[74],"various":[76],"applications,":[77],"human-computer":[80],"gaming":[81],"intelligent":[83],"transportation.":[84],"In":[85],"this":[86,93,215],"paper,":[87],"we":[88,136,204],"conclude":[89],"state":[91],"exciting":[94],"field,":[95],"comparing":[97],"classical":[99],"studying":[106],"important":[107],"components":[108],"achieve":[110],"covering":[114],"single":[115,117],"player":[116],"agent":[118],"most":[125],"complex":[126,181,201],"multiple":[127,129,191,194],"players":[128,192],"agents":[130,195],"learning.":[134,234],"Furthermore,":[135],"review":[137,217],"recently":[138],"released":[139],"toolboxes":[140],"that":[141,214],"help":[142],"realize":[144],"without":[149],"many":[150],"modifications":[151],"their":[153,158],"non-distributed":[154],"versions.":[155],"By":[156],"analysing":[157],"strengths":[159],"weaknesses,":[161],"multi-player":[163],"multi-agent":[164],"toolbox":[169,189],"is":[170,175],"released,":[173],"further":[176],"validated":[177],"on":[178],"Wargame,":[179],"environment,":[182],"showing":[183],"usability":[185],"proposed":[188],"under":[200],"games.":[202],"Finally,":[203],"try":[205],"point":[207],"out":[208],"challenges":[209],"future":[211],"trends,":[212],"hoping":[213],"brief":[216],"can":[218],"provide":[219],"guide":[221],"or":[222],"spark":[224],"researchers":[226],"who":[227],"are":[228],"interested":[229]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":7}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2024-01-13T00:00:00"}
