{"id":"https://openalex.org/W3095442437","doi":"https://doi.org/10.1080/09540091.2020.1832961","title":"Learning adversarial policy in multiple scenes environment via multi-agent reinforcement learning","display_name":"Learning adversarial policy in multiple scenes environment via multi-agent reinforcement learning","publication_year":2020,"publication_date":"2020-11-03","ids":{"openalex":"https://openalex.org/W3095442437","doi":"https://doi.org/10.1080/09540091.2020.1832961","mag":"3095442437"},"language":"en","primary_location":{"id":"doi:10.1080/09540091.2020.1832961","is_oa":false,"landing_page_url":"https://doi.org/10.1080/09540091.2020.1832961","pdf_url":null,"source":{"id":"https://openalex.org/S4210188800","display_name":"Connection Science","issn_l":"0954-0091","issn":["0954-0091","1360-0494"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Connection Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"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/A5100421849","display_name":"Yang Li","orcid":"https://orcid.org/0009-0006-4018-5582"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Li","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai, People's Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai, People's Republic of China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100674034","display_name":"Xinzhi Wang","orcid":"https://orcid.org/0000-0002-4552-3978"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinzhi Wang","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai, People's Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai, People's Republic of China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100777576","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-5974-1589"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai, People's Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai, People's Republic of China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101902939","display_name":"Zhenyu Zhang","orcid":"https://orcid.org/0000-0002-9470-7132"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Zhang","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai, People's Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai, People's Republic of China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048419868","display_name":"Jianshu Wang","orcid":"https://orcid.org/0000-0002-6870-5061"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianshu Wang","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai, People's Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai, People's Republic of China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100426947","display_name":"Xiangfeng Luo","orcid":"https://orcid.org/0000-0003-4577-9241"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiangfeng Luo","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai, People's Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai, People's Republic of China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086702173","display_name":"Shaorong Xie","orcid":"https://orcid.org/0000-0002-8016-9310"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shaorong Xie","raw_affiliation_strings":["School of Computer Engineering and Science, Shanghai University, Shanghai, People's Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Engineering and Science, Shanghai University, Shanghai, People's Republic of China","institution_ids":["https://openalex.org/I141962983"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5086702173","https://openalex.org/A5100426947"],"corresponding_institution_ids":["https://openalex.org/I141962983"],"apc_list":{"value":1270,"currency":"USD","value_usd":1270},"apc_paid":null,"fwci":0.536,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.74927551,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"33","issue":"3","first_page":"407","last_page":"426"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9783999919891357,"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"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.9767000079154968,"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":0.8646002411842346},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.810310959815979},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.736348032951355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5798170566558838},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5761118531227112},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5652345418930054},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4987063407897949},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.474278062582016},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42664116621017456},{"id":"https://openalex.org/keywords/trust-region","display_name":"Trust region","score":0.42456087470054626},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4125230014324188},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.149542897939682}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8646002411842346},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.810310959815979},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.736348032951355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5798170566558838},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5761118531227112},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5652345418930054},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4987063407897949},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.474278062582016},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42664116621017456},{"id":"https://openalex.org/C89109886","wikidata":"https://www.wikidata.org/wiki/Q1535924","display_name":"Trust region","level":3,"score":0.42456087470054626},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4125230014324188},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.149542897939682},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C178635117","wikidata":"https://www.wikidata.org/wiki/Q747499","display_name":"RADIUS","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1080/09540091.2020.1832961","is_oa":false,"landing_page_url":"https://doi.org/10.1080/09540091.2020.1832961","pdf_url":null,"source":{"id":"https://openalex.org/S4210188800","display_name":"Connection Science","issn_l":"0954-0091","issn":["0954-0091","1360-0494"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Connection Science","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:8dab34d98b81435092afdd51d22d2c8b","is_oa":false,"landing_page_url":"https://doaj.org/article/8dab34d98b81435092afdd51d22d2c8b","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Connection Science, Vol 33, Iss 3, Pp 407-426 (2021)","raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.800000011920929,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G3109497526","display_name":null,"funder_award_id":"MC-201920-X01","funder_id":"https://openalex.org/F4320323970","funder_display_name":"Ministry of Industry and Information Technology of the People's Republic of China"},{"id":"https://openalex.org/G3411408586","display_name":null,"funder_award_id":"61991415.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323970","display_name":"Ministry of Industry and Information Technology of the People's Republic of China","ror":"https://ror.org/0385nmy68"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W41554520","https://openalex.org/W1513468570","https://openalex.org/W1540725368","https://openalex.org/W1542941925","https://openalex.org/W1560074431","https://openalex.org/W1607392272","https://openalex.org/W1702462424","https://openalex.org/W1967398213","https://openalex.org/W1993194158","https://openalex.org/W2044097402","https://openalex.org/W2064774485","https://openalex.org/W2067050450","https://openalex.org/W2092215165","https://openalex.org/W2096145798","https://openalex.org/W2097498347","https://openalex.org/W2108892923","https://openalex.org/W2119717200","https://openalex.org/W2146628995","https://openalex.org/W2396783599","https://openalex.org/W2567289819","https://openalex.org/W2592798481","https://openalex.org/W2604283518","https://openalex.org/W2604873668","https://openalex.org/W2617547828","https://openalex.org/W2623431351","https://openalex.org/W2768629321","https://openalex.org/W2769375497","https://openalex.org/W2792726216","https://openalex.org/W2810602713","https://openalex.org/W2901886291","https://openalex.org/W2912971983","https://openalex.org/W2918949733","https://openalex.org/W2939653603","https://openalex.org/W2944740309","https://openalex.org/W2945095794","https://openalex.org/W2949201811","https://openalex.org/W2951896791","https://openalex.org/W2962938168","https://openalex.org/W2963562809","https://openalex.org/W2963821308","https://openalex.org/W2997940961","https://openalex.org/W2998367975","https://openalex.org/W3005672216","https://openalex.org/W3006868075","https://openalex.org/W3008967682","https://openalex.org/W3099518626","https://openalex.org/W3103532359","https://openalex.org/W6681809998","https://openalex.org/W6763002283"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W4246396837","https://openalex.org/W2482350142","https://openalex.org/W3176240006","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4288019534","https://openalex.org/W4385488867"],"abstract_inverted_index":{"Learning":[0],"adversarial":[1,226],"policy":[2,110,123,227],"aims":[3],"to":[4,38,66,174],"learn":[5,39],"behavioural":[6,40],"strategies":[7,41],"for":[8,146,156],"agents":[9,103,115],"with":[10,44,126,164,229],"different":[11,102],"goals,":[12],"is":[13,62,191,200],"one":[14,188],"of":[15,134,189],"the":[16,53,96,105,132,150,176,198],"most":[17],"significant":[18],"tasks":[19],"in":[20,52,84,95,104,136,183,220],"multi-agent":[21,79,137],"systems.":[22],"Multi-agent":[23],"reinforcement":[24],"learning":[25,177],"(MARL),":[26],"as":[27],"a":[28,72],"state-of-the-art":[29],"learning-based":[30],"model,":[31],"employs":[32],"centralised":[33],"or":[34,60],"decentralised":[35],"control":[36,101],"methods":[37,219],"by":[42,206],"interacting":[43],"environments.":[45],"It":[46],"suffers":[47],"from":[48,116,167],"instability":[49],"and":[50,108,149,197,215,223],"slowness":[51],"training":[54,68,97,135,160],"process.":[55,178],"Considering":[56],"that":[57,210],"parallel":[58,93,169],"simulation":[59],"computation":[61],"an":[63,127],"effective":[64,159],"way":[65],"improve":[67],"performance,":[69],"we":[70,89,120],"propose":[71],"novel":[73],"MARL":[74],"method":[75],"called":[76],"Multiple":[77,99],"scenes":[78,94,170],"proximal":[80,122],"Policy":[81],"Optimisation":[82],"(MPO)":[83],"this":[85],"paper.":[86],"In":[87],"MPO,":[88],"first":[90],"simulate":[91],"multiple":[92,117,168],"environment.":[98],"policies":[100],"same":[106],"scene,":[107],"each":[109],"also":[111],"controls":[112],"several":[113],"identical":[114],"scenes.":[118],"Then,":[119],"expand":[121],"optimisation":[124],"(PPO)":[125],"improved":[128],"actor-critic":[129],"network,":[130],"ensuring":[131],"stability":[133],"tasks.":[138],"The":[139],"actor":[140],"network":[141,152],"only":[142],"uses":[143,153],"local":[144],"information":[145,155],"decision":[147],"making,":[148],"critic":[151],"global":[154],"training.":[157],"Finally,":[158],"trajectories":[161],"are":[162],"computed":[163],"two":[165,184],"criteria":[166],"rather":[171],"than":[172,217],"single":[173],"accelerate":[175],"We":[179],"evaluate":[180],"our":[181],"approach":[182],"simulated":[185],"3D":[186],"environments,":[187],"which":[190],"Unity's":[192],"official":[193],"open-source":[194],"soccer":[195],"game,":[196],"other":[199],"unmanned":[201],"surface":[202],"vehicles":[203],"(USVs)":[204],"built":[205],"Unity.":[207],"Experiments":[208],"demonstrate":[209],"MPO":[211],"converges":[212],"more":[213],"stable":[214],"faster":[216],"benchmark":[218,230],"model":[221],"training,":[222],"demonstrates":[224],"excellent":[225],"compared":[228],"models.":[231]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}