{"id":"https://openalex.org/W4225547330","doi":"https://doi.org/10.1093/comjnl/bxac027","title":"Improvement of MADRL Equilibrium Based on Pareto Optimization","display_name":"Improvement of MADRL Equilibrium Based on Pareto Optimization","publication_year":2022,"publication_date":"2022-04-14","ids":{"openalex":"https://openalex.org/W4225547330","doi":"https://doi.org/10.1093/comjnl/bxac027"},"language":"en","primary_location":{"id":"doi:10.1093/comjnl/bxac027","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxac027","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","raw_type":"journal-article"},"type":"article","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/A5008606161","display_name":"Zhiruo Zhao","orcid":"https://orcid.org/0000-0002-6952-5337"},"institutions":[{"id":"https://openalex.org/I2799773085","display_name":"Nanjing General Hospital of Nanjing Military Command","ror":"https://ror.org/04kmpyd03","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I2799773085"]},{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiruo Zhao","raw_affiliation_strings":["Army Engineering University of PLA , , Nanjing, CO 210000 China","Command & Control Engineering College , , Nanjing, CO 210000 China","Command & Control Engineering College, Army Engineering University of PLA, Nanjing, CO 210000 China"],"raw_orcid":"https://orcid.org/0000-0002-6952-5337","affiliations":[{"raw_affiliation_string":"Army Engineering University of PLA , , Nanjing, CO 210000 China","institution_ids":["https://openalex.org/I4210163363"]},{"raw_affiliation_string":"Command & Control Engineering College , , Nanjing, CO 210000 China","institution_ids":["https://openalex.org/I2799773085"]},{"raw_affiliation_string":"Command & Control Engineering College, Army Engineering University of PLA, Nanjing, CO 210000 China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078602454","display_name":"Lei Cao","orcid":"https://orcid.org/0000-0002-6997-8504"},"institutions":[{"id":"https://openalex.org/I2799773085","display_name":"Nanjing General Hospital of Nanjing Military Command","ror":"https://ror.org/04kmpyd03","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I2799773085"]},{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lei Cao","raw_affiliation_strings":["Army Engineering University of PLA , , Nanjing, CO 210000 China","Command & Control Engineering College , , Nanjing, CO 210000 China","Command & Control Engineering College, Army Engineering University of PLA, Nanjing, CO 210000 China"],"raw_orcid":"https://orcid.org/0000-0002-6997-8504","affiliations":[{"raw_affiliation_string":"Army Engineering University of PLA , , Nanjing, CO 210000 China","institution_ids":["https://openalex.org/I4210163363"]},{"raw_affiliation_string":"Command & Control Engineering College , , Nanjing, CO 210000 China","institution_ids":["https://openalex.org/I2799773085"]},{"raw_affiliation_string":"Command & Control Engineering College, Army Engineering University of PLA, Nanjing, CO 210000 China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030992865","display_name":"Xiliang Chen","orcid":"https://orcid.org/0000-0001-5198-0932"},"institutions":[{"id":"https://openalex.org/I2799773085","display_name":"Nanjing General Hospital of Nanjing Military Command","ror":"https://ror.org/04kmpyd03","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I2799773085"]},{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiliang Chen","raw_affiliation_strings":["Army Engineering University of PLA , , Nanjing, CO 210000 China","Command & Control Engineering College , , Nanjing, CO 210000 China","Command & Control Engineering College, Army Engineering University of PLA, Nanjing, CO 210000 China"],"raw_orcid":"https://orcid.org/0000-0001-5198-0932","affiliations":[{"raw_affiliation_string":"Army Engineering University of PLA , , Nanjing, CO 210000 China","institution_ids":["https://openalex.org/I4210163363"]},{"raw_affiliation_string":"Command & Control Engineering College , , Nanjing, CO 210000 China","institution_ids":["https://openalex.org/I2799773085"]},{"raw_affiliation_string":"Command & Control Engineering College, Army Engineering University of PLA, Nanjing, CO 210000 China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101900574","display_name":"Jun Lai","orcid":"https://orcid.org/0000-0002-3608-4985"},"institutions":[{"id":"https://openalex.org/I2799773085","display_name":"Nanjing General Hospital of Nanjing Military Command","ror":"https://ror.org/04kmpyd03","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I2799773085"]},{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Lai","raw_affiliation_strings":["Army Engineering University of PLA , , Nanjing, CO 210000 China","Command & Control Engineering College , , Nanjing, CO 210000 China","Command & Control Engineering College, Army Engineering University of PLA, Nanjing, CO 210000 China"],"raw_orcid":"https://orcid.org/0000-0002-3608-4985","affiliations":[{"raw_affiliation_string":"Army Engineering University of PLA , , Nanjing, CO 210000 China","institution_ids":["https://openalex.org/I4210163363"]},{"raw_affiliation_string":"Command & Control Engineering College , , Nanjing, CO 210000 China","institution_ids":["https://openalex.org/I2799773085"]},{"raw_affiliation_string":"Command & Control Engineering College, Army Engineering University of PLA, Nanjing, CO 210000 China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002294263","display_name":"Legui Zhang","orcid":"https://orcid.org/0000-0003-2768-7044"},"institutions":[{"id":"https://openalex.org/I2799773085","display_name":"Nanjing General Hospital of Nanjing Military Command","ror":"https://ror.org/04kmpyd03","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I2799773085"]},{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Legui Zhang","raw_affiliation_strings":["Army Engineering University of PLA , , Nanjing, CO 210000 China","Command & Control Engineering College , , Nanjing, CO 210000 China","Command & Control Engineering College, Army Engineering University of PLA, Nanjing, CO 210000 China"],"raw_orcid":"https://orcid.org/0000-0003-2768-7044","affiliations":[{"raw_affiliation_string":"Army Engineering University of PLA , , Nanjing, CO 210000 China","institution_ids":["https://openalex.org/I4210163363"]},{"raw_affiliation_string":"Command & Control Engineering College , , Nanjing, CO 210000 China","institution_ids":["https://openalex.org/I2799773085"]},{"raw_affiliation_string":"Command & Control Engineering College, Army Engineering University of PLA, Nanjing, CO 210000 China","institution_ids":["https://openalex.org/I4210163363"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5078602454"],"corresponding_institution_ids":["https://openalex.org/I2799773085","https://openalex.org/I4210163363"],"apc_list":{"value":2635,"currency":"GBP","value_usd":3232},"apc_paid":null,"fwci":0.1387,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52283389,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"66","issue":"7","first_page":"1573","last_page":"1585"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9649999737739563,"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/T11942","display_name":"Transportation and Mobility Innovations","score":0.9556999802589417,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8464894890785217},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.7056085467338562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6906018853187561},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6670686602592468},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6611413359642029},{"id":"https://openalex.org/keywords/pareto-principle","display_name":"Pareto principle","score":0.6198380589485168},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5116246342658997},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.47819972038269043},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"Multi-objective optimization","score":0.46183088421821594},{"id":"https://openalex.org/keywords/pareto-optimal","display_name":"Pareto optimal","score":0.4308995306491852},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.40638983249664307},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2926979660987854},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2224290370941162},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19963055849075317},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.07793718576431274}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8464894890785217},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.7056085467338562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6906018853187561},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6670686602592468},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6611413359642029},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.6198380589485168},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5116246342658997},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.47819972038269043},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.46183088421821594},{"id":"https://openalex.org/C2986314615","wikidata":"https://www.wikidata.org/wiki/Q36829","display_name":"Pareto optimal","level":3,"score":0.4308995306491852},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.40638983249664307},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2926979660987854},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2224290370941162},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19963055849075317},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.07793718576431274},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1093/comjnl/bxac027","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxac027","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3371825432","display_name":null,"funder_award_id":"61806221","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W80106572","https://openalex.org/W1542941925","https://openalex.org/W1605074941","https://openalex.org/W1907356258","https://openalex.org/W1972645710","https://openalex.org/W2008061812","https://openalex.org/W2034471979","https://openalex.org/W2120846115","https://openalex.org/W2124191651","https://openalex.org/W2145339207","https://openalex.org/W2535351973","https://openalex.org/W3020942682","https://openalex.org/W6639734652","https://openalex.org/W6640998109","https://openalex.org/W6678168664","https://openalex.org/W6678570727"],"related_works":["https://openalex.org/W2073298047","https://openalex.org/W1963790170","https://openalex.org/W2090178682","https://openalex.org/W2586328217","https://openalex.org/W2033790662","https://openalex.org/W2049264236","https://openalex.org/W4241467429","https://openalex.org/W2073147994","https://openalex.org/W2001591765","https://openalex.org/W317165722"],"abstract_inverted_index":{"Abstract":[0],"In":[1,84],"order":[2,85],"to":[3,36,51,74,86,123],"solve":[4],"the":[5,9,20,53,69,88,131,138,155],"incalculability":[6],"caused":[7,93,99],"by":[8,94,100],"issue":[10,62],"of":[11,22,68,90,109,126,157],"inconsistent":[12],"objective":[13],"functions":[14],"in":[15,63,107],"multi-agent":[16],"deep":[17],"reinforcement":[18,64],"learning,":[19],"concept":[21],"Nash":[23,75],"equilibrium":[24],"is":[25,44,59],"introduced.":[26],"However,":[27],"a":[28,39],"Marko":[29],"game":[30],"may":[31],"have":[32],"multiple":[33],"equilibriums,":[34],"how":[35,50],"filter":[37],"out":[38,134],"stable":[40],"and":[41,57,97],"optimal":[42],"one":[43],"worth":[45],"studying.":[46],"Besides":[47],"solution":[48],"concept,":[49],"keep":[52],"balance":[54],"between":[55],"exploration":[56],"exploitation":[58],"another":[60],"key":[61],"learning.":[65],"On":[66],"basis":[67],"methods,":[70,148],"which":[71],"can":[72],"converge":[73],"equilibrium,":[76],"this":[77],"paper":[78],"makes":[79],"improvement":[80],"through":[81,120],"Pareto":[82,95],"optimization.":[83],"alleviate":[87],"problem":[89],"over":[91],"fitting":[92],"optimization":[96],"non-convergence":[98],"strategy":[101],"change,":[102],"we":[103],"use":[104],"stratified":[105],"sampling":[106,111],"place":[108],"random":[110],"as":[112],"assistance.":[113],"What\u2019s":[114],"more,":[115],"our":[116],"methods":[117,140],"are":[118,141],"trained":[119],"fictitious":[121],"self-play":[122],"make":[124],"full":[125],"self-learning":[127],"experiences.":[128],"By":[129],"analyzing":[130],"experiment":[132],"carried":[133],"on":[135],"MAgent":[136],"platform,":[137],"proposed":[139],"not":[142],"only":[143],"far":[144],"better":[145],"than":[146],"traditional":[147],"but":[149],"also":[150],"reaching":[151],"or":[152],"even":[153],"surpassing":[154],"state":[156],"art":[158],"MADRL":[159],"methods.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}