{"id":"https://openalex.org/W2972128755","doi":"https://doi.org/10.1109/access.2019.2939384","title":"Discrete-Time Multi-Player Games Based on Off-Policy Q-Learning","display_name":"Discrete-Time Multi-Player Games Based on Off-Policy Q-Learning","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2972128755","doi":"https://doi.org/10.1109/access.2019.2939384","mag":"2972128755"},"language":"en","primary_location":{"id":"doi:10.1109/access.2019.2939384","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2939384","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08824067.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08824067.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070599005","display_name":"Jinna Li","orcid":"https://orcid.org/0000-0001-9985-6308"},"institutions":[{"id":"https://openalex.org/I166846921","display_name":"Liaoning Shihua University","ror":"https://ror.org/00k6c4h29","country_code":"CN","type":"education","lineage":["https://openalex.org/I166846921"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinna Li","raw_affiliation_strings":["School of Information and Control Engineering, Liaoning Shihua University, Fushun, China"],"raw_orcid":"https://orcid.org/0000-0001-9985-6308","affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, Liaoning Shihua University, Fushun, China","institution_ids":["https://openalex.org/I166846921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057045555","display_name":"Zhenfei Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I166846921","display_name":"Liaoning Shihua University","ror":"https://ror.org/00k6c4h29","country_code":"CN","type":"education","lineage":["https://openalex.org/I166846921"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenfei Xiao","raw_affiliation_strings":["School of Information and Control Engineering, Liaoning Shihua University, Fushun, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, Liaoning Shihua University, Fushun, China","institution_ids":["https://openalex.org/I166846921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100741313","display_name":"Ping Li","orcid":"https://orcid.org/0000-0002-3216-6246"},"institutions":[{"id":"https://openalex.org/I166846921","display_name":"Liaoning Shihua University","ror":"https://ror.org/00k6c4h29","country_code":"CN","type":"education","lineage":["https://openalex.org/I166846921"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Li","raw_affiliation_strings":["School of Information and Control Engineering, Liaoning Shihua University, Fushun, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, Liaoning Shihua University, Fushun, China","institution_ids":["https://openalex.org/I166846921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I166846921"],"apc_list":{"value":2075,"currency":"USD","value_usd":2075},"apc_paid":{"value":2075,"currency":"USD","value_usd":2075},"fwci":1.9778,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.87869078,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":"7","issue":null,"first_page":"134647","last_page":"134659"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9754999876022339,"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/T12047","display_name":"Viral Infections and Vectors","score":0.9485999941825867,"subfield":{"id":"https://openalex.org/subfields/2725","display_name":"Infectious Diseases"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.7963504791259766},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6422052383422852},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.6008813381195068},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5240305066108704},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5155153274536133},{"id":"https://openalex.org/keywords/best-response","display_name":"Best response","score":0.504062294960022},{"id":"https://openalex.org/keywords/zero-sum-game","display_name":"Zero-sum game","score":0.49974822998046875},{"id":"https://openalex.org/keywords/epsilon-equilibrium","display_name":"Epsilon-equilibrium","score":0.48408615589141846},{"id":"https://openalex.org/keywords/sequential-game","display_name":"Sequential game","score":0.4746147692203522},{"id":"https://openalex.org/keywords/potential-game","display_name":"Potential game","score":0.4660763740539551},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4629249572753906},{"id":"https://openalex.org/keywords/equilibrium-selection","display_name":"Equilibrium selection","score":0.42172300815582275},{"id":"https://openalex.org/keywords/correlated-equilibrium","display_name":"Correlated equilibrium","score":0.41163370013237},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.4105414152145386},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.3868435323238373},{"id":"https://openalex.org/keywords/repeated-game","display_name":"Repeated game","score":0.366239070892334},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.3610815405845642},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2866021394729614},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22823932766914368}],"concepts":[{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.7963504791259766},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6422052383422852},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.6008813381195068},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5240305066108704},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5155153274536133},{"id":"https://openalex.org/C32407928","wikidata":"https://www.wikidata.org/wiki/Q2733833","display_name":"Best response","level":3,"score":0.504062294960022},{"id":"https://openalex.org/C136356330","wikidata":"https://www.wikidata.org/wiki/Q156612","display_name":"Zero-sum game","level":3,"score":0.49974822998046875},{"id":"https://openalex.org/C141824439","wikidata":"https://www.wikidata.org/wiki/Q307521","display_name":"Epsilon-equilibrium","level":4,"score":0.48408615589141846},{"id":"https://openalex.org/C73795354","wikidata":"https://www.wikidata.org/wiki/Q287618","display_name":"Sequential game","level":3,"score":0.4746147692203522},{"id":"https://openalex.org/C2778079155","wikidata":"https://www.wikidata.org/wiki/Q288500","display_name":"Potential game","level":3,"score":0.4660763740539551},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4629249572753906},{"id":"https://openalex.org/C164407509","wikidata":"https://www.wikidata.org/wiki/Q5384490","display_name":"Equilibrium selection","level":4,"score":0.42172300815582275},{"id":"https://openalex.org/C163630976","wikidata":"https://www.wikidata.org/wiki/Q964667","display_name":"Correlated equilibrium","level":5,"score":0.41163370013237},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.4105414152145386},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.3868435323238373},{"id":"https://openalex.org/C202556891","wikidata":"https://www.wikidata.org/wiki/Q1584646","display_name":"Repeated game","level":3,"score":0.366239070892334},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.3610815405845642},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2866021394729614},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22823932766914368},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2019.2939384","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2939384","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08824067.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:04a4651583b44564b9332af947374acc","is_oa":true,"landing_page_url":"https://doaj.org/article/04a4651583b44564b9332af947374acc","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 7, Pp 134647-134659 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2019.2939384","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2939384","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08824067.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1483111355","display_name":null,"funder_award_id":"61673100","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2303554934","display_name":null,"funder_award_id":"2018XJJ-005","funder_id":"https://openalex.org/F4320329351","funder_display_name":"Liaoning Shihua University"},{"id":"https://openalex.org/G2763882931","display_name":null,"funder_award_id":"2019-KF-03-06","funder_id":"https://openalex.org/F4320323086","funder_display_name":"Natural Science Foundation of Liaoning Province"},{"id":"https://openalex.org/G5156944241","display_name":null,"funder_award_id":"61525302","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7272473876","display_name":null,"funder_award_id":"61590922","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G74425646","display_name":null,"funder_award_id":"61673280","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7510781838","display_name":null,"funder_award_id":"(61673199)","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8743717570","display_name":null,"funder_award_id":"61503257","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/F4320323086","display_name":"Natural Science Foundation of Liaoning Province","ror":null},{"id":"https://openalex.org/F4320329351","display_name":"Liaoning Shihua University","ror":"https://ror.org/00k6c4h29"},{"id":"https://openalex.org/F4320335661","display_name":"State Key Laboratory of Synthetical Automation for Process Industries","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2972128755.pdf","grobid_xml":"https://content.openalex.org/works/W2972128755.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W166862392","https://openalex.org/W560518094","https://openalex.org/W1488674906","https://openalex.org/W1614417283","https://openalex.org/W1968908471","https://openalex.org/W1976956127","https://openalex.org/W1991119064","https://openalex.org/W1999213690","https://openalex.org/W2005437559","https://openalex.org/W2012451615","https://openalex.org/W2013895638","https://openalex.org/W2019338681","https://openalex.org/W2020047580","https://openalex.org/W2087063454","https://openalex.org/W2098035803","https://openalex.org/W2105004188","https://openalex.org/W2108383324","https://openalex.org/W2112103082","https://openalex.org/W2132468772","https://openalex.org/W2165726932","https://openalex.org/W2329769476","https://openalex.org/W2462102501","https://openalex.org/W2550394442","https://openalex.org/W2560131027","https://openalex.org/W2564717627","https://openalex.org/W2579592432","https://openalex.org/W2580629550","https://openalex.org/W2606378794","https://openalex.org/W2761756876","https://openalex.org/W2767696060","https://openalex.org/W2767784613","https://openalex.org/W2771641782","https://openalex.org/W2887344203","https://openalex.org/W2963674921","https://openalex.org/W6715102896"],"related_works":["https://openalex.org/W4301347782","https://openalex.org/W1667857601","https://openalex.org/W1553185561","https://openalex.org/W3004964213","https://openalex.org/W4287871712","https://openalex.org/W3011680666","https://openalex.org/W3006995042","https://openalex.org/W2128266000","https://openalex.org/W4233209381","https://openalex.org/W3123744589"],"abstract_inverted_index":{"In":[0],"this":[1,52,123,207],"paper,":[2],"an":[3,36,93],"off-policy":[4,37,94,167],"game":[5,17,38,58,95,168,198],"Q-learning":[6,22,39,91,96,169,199],"algorithm":[7,97,130,170],"is":[8,41,60,98,113,156,200,203],"proposed":[9,129,166],"for":[10,24,33,43,105,180],"solving":[11,25],"linear":[12,81],"discrete-time":[13],"non-zero":[14,56],"sum":[15,57],"multi-player":[16,34,106],"problems.":[18],"Unlike":[19],"the":[20,26,45,63,67,87,102,110,116,128,134,150,165,182,189],"existing":[21],"methods":[23],"Riccati":[27],"equation":[28],"by":[29],"on-policy":[30,197],"learning":[31],"approaches":[32],"games,":[35,107],"method":[40],"developed":[42,99],"achieving":[44],"Nash":[46,111,151,160,190],"equilibrium":[47,112,152,161,191],"of":[48,122,159,188,206],"multiple":[49],"players.":[50],"To":[51],"end,":[53],"first,":[54],"a":[55,141],"problem":[59],"formulated,":[61],"and":[62,66,90,143],"value":[64],"function":[65],"Q-function":[68],"defined":[69],"according":[70],"to":[71,79,100,138,148,177],"each-player":[72],"individual":[73],"performance":[74],"index":[75],"are":[76,175],"rigorously":[77],"proved":[78],"be":[80,139,194],"quadratic":[82],"forms.":[83],"Then,":[84],"based":[85],"on":[86],"dynamic":[88],"programming":[89],"methods,":[92],"find":[101],"control":[103,118,178],"policies":[104,179],"such":[108],"that":[109,127],"reached":[114],"under":[115],"learned":[117],"policies.":[119],"The":[120],"merit":[121],"paper":[124],"lies":[125],"in":[126],"does":[131],"not":[132],"require":[133],"system":[135],"model":[136],"parameters":[137],"known":[140],"priori":[142],"fully":[144],"utilizes":[145],"measurable":[146],"data":[147],"learn":[149],"solution.":[153],"Moreover,":[154],"there":[155],"no":[157],"bias":[158,187],"solution":[162,192],"when":[163],"implementing":[164],"even":[171],"though":[172],"probing":[173],"noises":[174],"added":[176],"maintaining":[181],"persistent":[183],"excitation":[184],"condition.":[185],"While":[186],"could":[193],"produced":[195],"if":[196],"employed.":[201],"This":[202],"another":[204],"contribution":[205],"paper.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2026-08-22T07:34:49.880490","created_date":"2025-10-10T00:00:00"}