{"id":"https://openalex.org/W4220947289","doi":"https://doi.org/10.1177/01423312221077755","title":"A Friend-or-Foe framework for multi-agent reinforcement learning policy generation in mixing cooperative\u2013competitive scenarios","display_name":"A Friend-or-Foe framework for multi-agent reinforcement learning policy generation in mixing cooperative\u2013competitive scenarios","publication_year":2022,"publication_date":"2022-03-29","ids":{"openalex":"https://openalex.org/W4220947289","doi":"https://doi.org/10.1177/01423312221077755"},"language":"en","primary_location":{"id":"doi:10.1177/01423312221077755","is_oa":false,"landing_page_url":"https://doi.org/10.1177/01423312221077755","pdf_url":null,"source":{"id":"https://openalex.org/S24148485","display_name":"Transactions of the Institute of Measurement and Control","issn_l":"0142-3312","issn":["0142-3312","1477-0369"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Institute of Measurement and Control","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/A5020448950","display_name":"Yu Sun","orcid":"https://orcid.org/0000-0002-8218-3909"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yu Sun","raw_affiliation_strings":["Naval Command College, China","The PLA Unit, China"],"raw_orcid":"https://orcid.org/0000-0002-8218-3909","affiliations":[{"raw_affiliation_string":"Naval Command College, China","institution_ids":[]},{"raw_affiliation_string":"The PLA Unit, China","institution_ids":[]}]},{"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/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":"Jun Lai","raw_affiliation_strings":["Command & Control Engineering College, Army Engineering University of PLA, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Command & Control Engineering College, Army Engineering University of PLA, 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/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":["Command & Control Engineering College, Army Engineering University of PLA, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Command & Control Engineering College, Army Engineering University of PLA, 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/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":"Xiliang Chen","raw_affiliation_strings":["Command & Control Engineering College, Army Engineering University of PLA, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Command & Control Engineering College, Army Engineering University of PLA, China","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072596372","display_name":"Zhixiong Xu","orcid":"https://orcid.org/0000-0003-0996-436X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhixiong Xu","raw_affiliation_strings":["Army Academy of Border and Coastal Defense, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Army Academy of Border and Coastal Defense, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001973434","display_name":"Zheng Lian","orcid":"https://orcid.org/0000-0001-9477-0599"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhen Lian","raw_affiliation_strings":["Naval Command College, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Naval Command College, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039780576","display_name":"Huijin Fan","orcid":"https://orcid.org/0000-0002-0370-173X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huijin Fan","raw_affiliation_strings":["Naval Command College, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Naval Command College, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5020448950","https://openalex.org/A5030992865","https://openalex.org/A5078602454","https://openalex.org/A5101900574"],"corresponding_institution_ids":["https://openalex.org/I4210163363"],"apc_list":null,"apc_paid":null,"fwci":0.4162,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66789983,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"44","issue":"12","first_page":"2378","last_page":"2395"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.988099992275238,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9664000272750854,"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":0.8184604644775391},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7902801036834717},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6894742846488953},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5811062455177307},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5560827255249023},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5164391994476318},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5056085586547852},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3175928294658661},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.25230270624160767},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20345023274421692}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8184604644775391},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7902801036834717},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6894742846488953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5811062455177307},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5560827255249023},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5164391994476318},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5056085586547852},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3175928294658661},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25230270624160767},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20345023274421692},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/01423312221077755","is_oa":false,"landing_page_url":"https://doi.org/10.1177/01423312221077755","pdf_url":null,"source":{"id":"https://openalex.org/S24148485","display_name":"Transactions of the Institute of Measurement and Control","issn_l":"0142-3312","issn":["0142-3312","1477-0369"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Transactions of the Institute of Measurement and Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7054816361","display_name":null,"funder_award_id":"61203192","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8972278584","display_name":null,"funder_award_id":"BK2011124","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W206679605","https://openalex.org/W1987864653","https://openalex.org/W2037036263","https://openalex.org/W2049916932","https://openalex.org/W2124141629","https://openalex.org/W2129018774","https://openalex.org/W2145339207","https://openalex.org/W2166533447","https://openalex.org/W2559655401","https://openalex.org/W2565516711","https://openalex.org/W2617547828","https://openalex.org/W2754517384","https://openalex.org/W2908261578","https://openalex.org/W2969195240","https://openalex.org/W2969525674","https://openalex.org/W2981038142","https://openalex.org/W4237637693"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435","https://openalex.org/W20361778"],"abstract_inverted_index":{"Although":[0],"multi-agent":[1,14,49,81,143],"deep":[2,9,50,82,144],"deterministic":[3,51,83,145],"policy":[4,28,52,84,146],"gradient":[5,53,85,147],"is":[6],"a":[7],"classic":[8],"reinforcement":[10],"learning":[11],"algorithm":[12,46,163],"in":[13,151,177],"systems.":[15],"It":[16],"also":[17],"has":[18],"critical":[19],"problems":[20],"such":[21],"as":[22,63],"poor":[23],"training":[24,90,104,126,168],"stability":[25,127,169],"and":[26,35,95,106,148,170],"low":[27],"robustness,":[29],"which":[30,99],"significantly":[31],"limit":[32],"the":[33,38,56,68,76,79,101,119,167,171],"capability":[34],"application":[36],"of":[37,70,78,103,122,128,137,173],"algorithm.":[39,131],"So":[40],"this":[41],"article":[42],"proposes":[43],"an":[44,110],"improved":[45],"called":[47],"friend-or-foe":[48,71,142],"for":[54],"solving":[55],"above":[57],"problems.":[58],"The":[59,157],"main":[60],"innovations":[61],"are":[62],"follows:":[64],"(1)":[65],"inspired":[66],"by":[67,86],"concept":[69],"game":[72],"theory,":[73],"we":[74,108,133],"modified":[75],"framework":[77],"original":[80,149],"using":[87],"two":[88],"identical":[89],"networks":[91],"with":[92],"agents\u2019":[93,174],"optimal":[94],"worst":[96],"actions":[97],"input,":[98],"improves":[100],"robustness":[102,172],"policies,":[105],"(2)":[107],"propose":[109],"action":[111],"perturbation":[112],"technique":[113],"based":[114],"on":[115],"gradient-descent":[116],"to":[117],"expand":[118],"selection":[120],"range":[121],"actions,":[123],"thereby":[124],"improving":[125,162],"our":[129,141,161],"proposing":[130],"Finally,":[132],"conducted":[134],"multiple":[135],"sets":[136],"comparative":[138],"experiments":[139],"between":[140],"one":[150],"four":[152],"authoritative":[153],"mixed":[154],"cooperative\u2013competitive":[155],"scenarios.":[156],"results":[158],"show":[159],"that":[160],"can":[164],"simultaneously":[165],"improve":[166],"generating":[175],"policies":[176],"different":[178],"complicated":[179],"environments.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}