{"id":"https://openalex.org/W4385767524","doi":"https://doi.org/10.24963/ijcai.2023/40","title":"Inducing Stackelberg Equilibrium through Spatio-Temporal Sequential Decision-Making in Multi-Agent Reinforcement Learning","display_name":"Inducing Stackelberg Equilibrium through Spatio-Temporal Sequential Decision-Making in Multi-Agent Reinforcement Learning","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385767524","doi":"https://doi.org/10.24963/ijcai.2023/40"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/40","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/40","pdf_url":"https://www.ijcai.org/proceedings/2023/0040.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0040.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100392920","display_name":"Bin Zhang","orcid":"https://orcid.org/0000-0003-3172-8056"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Zhang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences","School of Artificial Intelligence, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100419693","display_name":"Lijuan Li","orcid":"https://orcid.org/0000-0002-2758-7433"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijuan Li","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences","School of Artificial Intelligence, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100628168","display_name":"Zhiwei Xu","orcid":"https://orcid.org/0000-0002-0754-5295"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwei Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences","School of Artificial Intelligence, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100419597","display_name":"Dapeng Li","orcid":"https://orcid.org/0000-0002-8232-3094"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dapeng Li","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences","School of Artificial Intelligence, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016996180","display_name":"Guoliang Fan","orcid":"https://orcid.org/0000-0002-8584-9040"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoliang Fan","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences","School of Artificial Intelligence, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7948,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.87986371,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"353","last_page":"361"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9732000231742859,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.926800012588501,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/stackelberg-competition","display_name":"Stackelberg competition","score":0.8537746667861938},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7719073295593262},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7538055181503296},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6052983403205872},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.6025398969650269},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5427132248878479},{"id":"https://openalex.org/keywords/fictitious-play","display_name":"Fictitious play","score":0.5001027584075928},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.42965298891067505},{"id":"https://openalex.org/keywords/coordination-game","display_name":"Coordination game","score":0.42103147506713867},{"id":"https://openalex.org/keywords/stochastic-game","display_name":"Stochastic game","score":0.41820189356803894},{"id":"https://openalex.org/keywords/best-response","display_name":"Best response","score":0.4154953360557556},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.41311919689178467},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.345018208026886},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.321478933095932},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.2586978077888489},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1350250542163849}],"concepts":[{"id":"https://openalex.org/C199510392","wikidata":"https://www.wikidata.org/wiki/Q1184602","display_name":"Stackelberg competition","level":2,"score":0.8537746667861938},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7719073295593262},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7538055181503296},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6052983403205872},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.6025398969650269},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5427132248878479},{"id":"https://openalex.org/C145071142","wikidata":"https://www.wikidata.org/wiki/Q1411116","display_name":"Fictitious play","level":3,"score":0.5001027584075928},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.42965298891067505},{"id":"https://openalex.org/C107257861","wikidata":"https://www.wikidata.org/wiki/Q656316","display_name":"Coordination game","level":2,"score":0.42103147506713867},{"id":"https://openalex.org/C22171661","wikidata":"https://www.wikidata.org/wiki/Q1074380","display_name":"Stochastic game","level":2,"score":0.41820189356803894},{"id":"https://openalex.org/C32407928","wikidata":"https://www.wikidata.org/wiki/Q2733833","display_name":"Best response","level":3,"score":0.4154953360557556},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41311919689178467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.345018208026886},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.321478933095932},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.2586978077888489},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1350250542163849},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/40","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/40","pdf_url":"https://www.ijcai.org/proceedings/2023/0040.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/40","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/40","pdf_url":"https://www.ijcai.org/proceedings/2023/0040.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385767524.pdf"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W586722081","https://openalex.org/W1502765764","https://openalex.org/W1542941925","https://openalex.org/W2104602264","https://openalex.org/W2395575420","https://openalex.org/W2615790994","https://openalex.org/W2736601468","https://openalex.org/W2769883686","https://openalex.org/W2785315072","https://openalex.org/W2788115019","https://openalex.org/W2946045694","https://openalex.org/W2963864421","https://openalex.org/W2997072274","https://openalex.org/W3163926178","https://openalex.org/W3200561352","https://openalex.org/W4206560593","https://openalex.org/W4286748781","https://openalex.org/W4288336812","https://openalex.org/W4295598622","https://openalex.org/W4298857966","https://openalex.org/W4299802797","https://openalex.org/W4306802380","https://openalex.org/W4365395843","https://openalex.org/W4365420812","https://openalex.org/W4381733136"],"related_works":["https://openalex.org/W4287644830","https://openalex.org/W2082505783","https://openalex.org/W1935632502","https://openalex.org/W3092557414","https://openalex.org/W2955291419","https://openalex.org/W2117671832","https://openalex.org/W2363607131","https://openalex.org/W2080682057","https://openalex.org/W1984394557","https://openalex.org/W3125633875"],"abstract_inverted_index":{"In":[0,51],"multi-agent":[1],"reinforcement":[2],"learning":[3,128],"(MARL),":[4],"self-interested":[5],"agents":[6,31,138],"attempt":[7],"to":[8,124,147],"establish":[9],"equilibrium":[10,45,58],"and":[11,38,74,129,131,156,166],"achieve":[12],"coordination":[13],"depending":[14],"on":[15,81,104],"game":[16,35,154],"structure.":[17],"However,":[18],"existing":[19],"MARL":[20],"approaches":[21],"are":[22],"mostly":[23],"bound":[24],"by":[25,86,108],"the":[26,33,42,54,72,105,135,148],"simultaneous":[27],"actions":[28],"of":[29,44,53,56,137],"all":[30,87],"in":[32,151,159],"Markov":[34],"(MG)":[36],"framework,":[37],"few":[39],"works":[40],"consider":[41],"formation":[43],"strategies":[46],"via":[47],"asynchronous":[48],"action":[49],"coordination.":[50],"view":[52],"advantages":[55],"Stackelberg":[57],"(SE)":[59],"over":[60],"Nash":[61],"equilibrium,":[62],"we":[63],"construct":[64],"a":[65,82],"spatio-temporal":[66],"sequential":[67],"decision-making":[68],"structure":[69],"derived":[70],"from":[71],"MG":[73],"propose":[75],"an":[76],"N-level":[77],"policy":[78],"model":[79],"based":[80],"conditional":[83],"hypernetwork":[84],"shared":[85],"agents.":[88,110],"This":[89],"approach":[90],"allows":[91],"for":[92,127],"asymmetric":[93],"training":[94],"with":[95,98],"symmetric":[96],"execution,":[97],"each":[99],"agent":[100],"responding":[101],"optimally":[102],"conditioned":[103],"decisions":[106],"made":[107],"superior":[109],"Agents":[111],"can":[112],"learn":[113],"heterogeneous":[114],"SE":[115,149],"policies":[116,150],"while":[117],"still":[118],"maintaining":[119],"parameter":[120],"sharing,":[121],"which":[122],"leads":[123],"reduced":[125],"cost":[126],"storage":[130],"enhanced":[132],"scalability":[133],"as":[134],"number":[136],"increases.":[139],"Experiments":[140],"demonstrate":[141],"that":[142],"our":[143],"method":[144],"effectively":[145],"converges":[146],"repeated":[152],"matrix":[153],"scenarios,":[155],"performs":[157],"admirably":[158],"immensely":[160],"complex":[161],"settings":[162],"including":[163],"cooperative":[164],"tasks":[165],"mixed":[167],"tasks.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}