{"id":"https://openalex.org/W3111629178","doi":"https://doi.org/10.1109/smc42975.2020.9283033","title":"Friend-or-Foe Deep Deterministic Policy Gradient","display_name":"Friend-or-Foe Deep Deterministic Policy Gradient","publication_year":2020,"publication_date":"2020-10-11","ids":{"openalex":"https://openalex.org/W3111629178","doi":"https://doi.org/10.1109/smc42975.2020.9283033","mag":"3111629178"},"language":"en","primary_location":{"id":"doi:10.1109/smc42975.2020.9283033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc42975.2020.9283033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-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/A5101763478","display_name":"Hao Jiang","orcid":"https://orcid.org/0000-0002-8304-3692"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hao Jiang","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019758816","display_name":"Dianxi Shi","orcid":"https://orcid.org/0000-0002-8112-371X"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dianxi Shi","raw_affiliation_strings":["Tianjin Artificial Intelligence Innovation Center, National Innovation Institute of Defense Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tianjin Artificial Intelligence Innovation Center, National Innovation Institute of Defense Technology, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100884245","display_name":"Chao Xue","orcid":"https://orcid.org/0000-0002-9507-9991"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Xue","raw_affiliation_strings":["Artificial Intelligence Research Center, National Innovation Institute of Defense Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center, National Innovation Institute of Defense Technology, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100455413","display_name":"Yajie Wang","orcid":"https://orcid.org/0000-0002-0962-4464"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yajie Wang","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031404939","display_name":"Gongju Wang","orcid":"https://orcid.org/0000-0002-7162-3067"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gongju Wang","raw_affiliation_strings":["Artificial Intelligence Research Center, National Innovation Institute of Defense Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center, National Innovation Institute of Defense Technology, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108625236","display_name":"Yongjun Zhang","orcid":"https://orcid.org/0000-0001-9845-4251"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongjun Zhang","raw_affiliation_strings":["Artificial Intelligence Research Center, National Innovation Institute of Defense Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center, National Innovation Institute of Defense Technology, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101763478"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.1326,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.56779629,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3523","last_page":"3530"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9984999895095825,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9700999855995178,"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/computer-science","display_name":"Computer science","score":0.7559958696365356},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7418245077133179},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7079207897186279},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.582308292388916},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5654496550559998},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5432937145233154},{"id":"https://openalex.org/keywords/minimax","display_name":"Minimax","score":0.4917152225971222},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.43974971771240234},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13542324304580688},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.10029900074005127}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7559958696365356},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7418245077133179},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7079207897186279},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.582308292388916},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5654496550559998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5432937145233154},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.4917152225971222},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.43974971771240234},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13542324304580688},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.10029900074005127},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc42975.2020.9283033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc42975.2020.9283033","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.5}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1519783625","https://openalex.org/W1542941925","https://openalex.org/W1945616565","https://openalex.org/W2118688707","https://openalex.org/W2121615981","https://openalex.org/W2145339207","https://openalex.org/W2165150801","https://openalex.org/W2395575420","https://openalex.org/W2475089067","https://openalex.org/W2594103415","https://openalex.org/W2604283518","https://openalex.org/W2604763608","https://openalex.org/W2606411279","https://openalex.org/W2617547828","https://openalex.org/W2736601468","https://openalex.org/W2766413382","https://openalex.org/W2768629321","https://openalex.org/W2786478526","https://openalex.org/W2787938642","https://openalex.org/W2904455790","https://openalex.org/W2911825241","https://openalex.org/W2962841471","https://openalex.org/W2962938168","https://openalex.org/W2963000099","https://openalex.org/W2963039558","https://openalex.org/W2963207607","https://openalex.org/W2963390138","https://openalex.org/W2963407617","https://openalex.org/W2963937357","https://openalex.org/W2964095117","https://openalex.org/W2964345382","https://openalex.org/W2969419629","https://openalex.org/W4297789683","https://openalex.org/W4299802797","https://openalex.org/W4302570325","https://openalex.org/W6631168379","https://openalex.org/W6640425456","https://openalex.org/W6677477928","https://openalex.org/W6678317597","https://openalex.org/W6684205842","https://openalex.org/W6712181171","https://openalex.org/W6721101288","https://openalex.org/W6734517396","https://openalex.org/W6735011893","https://openalex.org/W6736057607","https://openalex.org/W6736622323","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6743367460","https://openalex.org/W6745594345","https://openalex.org/W6748689423","https://openalex.org/W6748839928","https://openalex.org/W6750393176"],"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/W4200062060"],"abstract_inverted_index":{"One":[0],"of":[1,44,120,175,200],"the":[2,6,15,20,29,41,45,54,76,110,118,122,126,129,167,173,197],"toughest":[3],"challenges":[4],"in":[5,74,89],"multi-agent":[7,135],"deep":[8,136],"reinforcement":[9],"learning":[10],"(MADRL)":[11],"is":[12],"that":[13],"when":[14],"opponents'":[16,30,55,105],"policies":[17,31,106],"change":[18],"rapidly,":[19],"collaborative":[21,46,94,144],"agents":[22,47,78,95],"can't":[23],"learn":[24],"well":[25],"to":[26,28,36,53,142,158,195],"respond":[27,100],"effectively.":[32],"This":[33],"may":[34,48],"lead":[35],"a":[37,64,152],"local":[38],"optimum":[39],"w.r.t.":[40],"learned":[42],"policy":[43,138],"be":[49,80],"only":[50],"locally":[51],"optimal":[52],"current":[56],"policies.":[57],"To":[58],"address":[59],"this":[60],"problem,":[61],"we":[62,116,150],"propose":[63],"novel":[65],"algorithm":[66,114,140],"termed":[67],"Friend-or-Foe":[68,112],"Deep":[69],"Deterministic":[70],"Policy":[71],"Gradient":[72],"(FD2PG),":[73],"which":[75,170],"cooperative":[77],"can":[79,96,171],"trained":[81],"more":[82],"robust":[83],"and":[84,99,124,147,166,177,188],"have":[85],"stronger":[86],"cooperation":[87],"ability":[88],"continuous":[90],"action":[91],"space.":[92],"These":[93],"generalize":[97],"easily":[98],"correctly,":[101],"even":[102],"if":[103],"their":[104],"alter.":[107],"Inspired":[108],"by":[109],"classic":[111],"Q-learning":[113],"(FFQ),":[115],"introduce":[117,151],"idea":[119],"minimizing":[121],"foes":[123],"maximizing":[125],"friends":[127],"into":[128],"centralized":[130],"training":[131],"distributed":[132],"execution":[133],"framework,":[134],"deterministic":[137],"gradient":[139],"(MADDPG),":[141],"enhance":[143],"agents'":[145],"robustness":[146],"cooperativity.":[148],"Besides,":[149],"Minimax":[153],"Multi-Agent":[154],"Learning":[155],"(MMAL)":[156],"method":[157],"explore":[159],"two":[160,189],"special":[161],"equilibriums":[162],"(the":[163],"adversarial":[164],"equilibrium":[165],"coordination":[168],"equilibrium),":[169],"guarantee":[172],"convergence":[174],"FD2PG":[176,201],"improve":[178],"optimization.":[179],"Extensive":[180],"fine-grained":[181],"experiments,":[182,192],"including":[183],"four":[184],"representative":[185],"scenario":[186],"experiments":[187],"scale-performance":[190],"correlation":[191],"were":[193],"conducted":[194],"demonstrate":[196],"superior":[198],"performance":[199],"comparing":[202],"with":[203],"existing":[204],"baselines.":[205]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}