{"id":"https://openalex.org/W2036103676","doi":"https://doi.org/10.1109/tcyb.2014.2349152","title":"Accelerating Multiagent Reinforcement Learning by Equilibrium Transfer","display_name":"Accelerating Multiagent Reinforcement Learning by Equilibrium Transfer","publication_year":2014,"publication_date":"2014-08-29","ids":{"openalex":"https://openalex.org/W2036103676","doi":"https://doi.org/10.1109/tcyb.2014.2349152","mag":"2036103676","pmid":"https://pubmed.ncbi.nlm.nih.gov/25181517"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2014.2349152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2014.2349152","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cybernetics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5104264364","display_name":"Yujing Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yujing Hu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","Department of Computer ScienceState Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"Department of Computer ScienceState Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074250521","display_name":"Yang Gao","orcid":"https://orcid.org/0000-0002-2488-1813"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Gao","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","Department of Computer ScienceState Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"Department of Computer ScienceState Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017743551","display_name":"Bo An","orcid":"https://orcid.org/0000-0002-7064-7438"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bo An","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University, Singapore","School of Computer Engineering, Nanyang Technological University,,Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University,,Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5104264364"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":4.0901,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.94188841,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"45","issue":"7","first_page":"1289","last_page":"1302"},"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":0.9969000220298767,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9894999861717224,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.7457050085067749},{"id":"https://openalex.org/keywords/equilibrium-selection","display_name":"Equilibrium selection","score":0.661062479019165},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6469456553459167},{"id":"https://openalex.org/keywords/thermodynamic-equilibrium","display_name":"Thermodynamic equilibrium","score":0.5989840030670166},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5585132241249084},{"id":"https://openalex.org/keywords/marl","display_name":"Marl","score":0.5405368804931641},{"id":"https://openalex.org/keywords/sequential-equilibrium","display_name":"Sequential equilibrium","score":0.5175599455833435},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.47626611590385437},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4714335501194},{"id":"https://openalex.org/keywords/equilibrium-point","display_name":"Equilibrium point","score":0.4668498635292053},{"id":"https://openalex.org/keywords/correlated-equilibrium","display_name":"Correlated equilibrium","score":0.4532242715358734},{"id":"https://openalex.org/keywords/game-theory","display_name":"Game theory","score":0.359317421913147},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3287356495857239},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2708631753921509},{"id":"https://openalex.org/keywords/repeated-game","display_name":"Repeated game","score":0.22083497047424316},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1767265498638153},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.12740370631217957},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11130908131599426},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.07685711979866028}],"concepts":[{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.7457050085067749},{"id":"https://openalex.org/C164407509","wikidata":"https://www.wikidata.org/wiki/Q5384490","display_name":"Equilibrium selection","level":4,"score":0.661062479019165},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6469456553459167},{"id":"https://openalex.org/C131157278","wikidata":"https://www.wikidata.org/wiki/Q51363","display_name":"Thermodynamic equilibrium","level":2,"score":0.5989840030670166},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5585132241249084},{"id":"https://openalex.org/C92927620","wikidata":"https://www.wikidata.org/wiki/Q184053","display_name":"Marl","level":3,"score":0.5405368804931641},{"id":"https://openalex.org/C201364048","wikidata":"https://www.wikidata.org/wiki/Q2897085","display_name":"Sequential equilibrium","level":5,"score":0.5175599455833435},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.47626611590385437},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4714335501194},{"id":"https://openalex.org/C94766913","wikidata":"https://www.wikidata.org/wiki/Q1530271","display_name":"Equilibrium point","level":3,"score":0.4668498635292053},{"id":"https://openalex.org/C163630976","wikidata":"https://www.wikidata.org/wiki/Q964667","display_name":"Correlated equilibrium","level":5,"score":0.4532242715358734},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.359317421913147},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3287356495857239},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2708631753921509},{"id":"https://openalex.org/C202556891","wikidata":"https://www.wikidata.org/wiki/Q1584646","display_name":"Repeated game","level":3,"score":0.22083497047424316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1767265498638153},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.12740370631217957},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11130908131599426},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.07685711979866028},{"id":"https://openalex.org/C78045399","wikidata":"https://www.wikidata.org/wiki/Q11214","display_name":"Differential equation","level":2,"score":0.0},{"id":"https://openalex.org/C109007969","wikidata":"https://www.wikidata.org/wiki/Q749565","display_name":"Structural basin","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2014.2349152","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2014.2349152","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cybernetics","raw_type":"journal-article"},{"id":"pmid:25181517","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25181517","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on cybernetics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2042088034","display_name":null,"funder_award_id":"61035003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2296064708","display_name":null,"funder_award_id":"NCET-10-0476","funder_id":"https://openalex.org/F4320334924","funder_display_name":"Program for New Century Excellent Talents in University"},{"id":"https://openalex.org/G5030852580","display_name":null,"funder_award_id":"61202212","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5616286496","display_name":null,"funder_award_id":"61175042","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6667581590","display_name":null,"funder_award_id":"61321491","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/F4320334924","display_name":"Program for New Century Excellent Talents in University","ror":"https://ror.org/01mv9t934"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W6043852","https://openalex.org/W11035765","https://openalex.org/W29099680","https://openalex.org/W1502765764","https://openalex.org/W1519783625","https://openalex.org/W1542941925","https://openalex.org/W1868540347","https://openalex.org/W1968902782","https://openalex.org/W1974740629","https://openalex.org/W1978375026","https://openalex.org/W1980737627","https://openalex.org/W1991799203","https://openalex.org/W2002373723","https://openalex.org/W2008393562","https://openalex.org/W2010526786","https://openalex.org/W2029250042","https://openalex.org/W2072256588","https://openalex.org/W2089415692","https://openalex.org/W2092710777","https://openalex.org/W2097381042","https://openalex.org/W2097780422","https://openalex.org/W2099618002","https://openalex.org/W2109100253","https://openalex.org/W2112632840","https://openalex.org/W2120846115","https://openalex.org/W2121863487","https://openalex.org/W2124152208","https://openalex.org/W2130463867","https://openalex.org/W2135017242","https://openalex.org/W2136934807","https://openalex.org/W2138965998","https://openalex.org/W2145067550","https://openalex.org/W2153427071","https://openalex.org/W2164637474","https://openalex.org/W2263562440","https://openalex.org/W2404646363","https://openalex.org/W2406194061","https://openalex.org/W4214717370","https://openalex.org/W6600255050","https://openalex.org/W6600453709","https://openalex.org/W6601161420","https://openalex.org/W6631168379","https://openalex.org/W6674600207","https://openalex.org/W6677068649","https://openalex.org/W6678168664","https://openalex.org/W6679792765","https://openalex.org/W6680209877","https://openalex.org/W6681342480","https://openalex.org/W6684470913","https://openalex.org/W6693140999","https://openalex.org/W6712951187","https://openalex.org/W6713690997"],"related_works":["https://openalex.org/W1553185561","https://openalex.org/W3124283980","https://openalex.org/W4299590005","https://openalex.org/W2953375265","https://openalex.org/W4245883071","https://openalex.org/W2114238237","https://openalex.org/W2893200946","https://openalex.org/W1979147872","https://openalex.org/W3035137804","https://openalex.org/W2097264194"],"abstract_inverted_index":{"An":[0],"important":[1],"approach":[2],"in":[3,16,177,206],"multiagent":[4],"reinforcement":[5],"learning":[6,65,207],"(MARL)":[7],"is":[8,51,122,151],"equilibrium-based":[9,32,68,114,162,200],"MARL,":[10,69],"which":[11],"adopts":[12],"equilibrium":[13,24,45,110,120,148,157,170,218,228],"solution":[14],"concepts":[15],"game":[17],"theory":[18],"and":[19,141,187,220,235],"requires":[20],"agents":[21,239],"to":[22,38,74,95,108,112,123,135,168,203],"play":[23],"strategies":[25],"at":[26],"each":[27,75,129],"state.":[28],"However,":[29],"most":[30],"existing":[31],"MARL":[33,150,163,201],"algorithms":[34,164,216,226],"cannot":[35],"scale":[36],"due":[37],"a":[39,132,144],"large":[40],"number":[41,237],"of":[42,67,92,119,238],"computationally":[43],"expensive":[44],"computations":[46],"(e.g.,":[47,181],"computing":[48],"Nash":[49],"equilibria":[50,85,127],"PPAD-hard)":[52],"during":[53,63],"learning.":[54],"For":[55],"the":[56,64,70,81,192,231,236],"first":[57],"time,":[58],"this":[59,103,105],"paper":[60,106],"finds":[61],"that":[62,155,191],"process":[66],"one-shot":[71],"games":[72,93],"corresponding":[73,94],"state's":[76],"successive":[77,96],"visits":[78,97],"often":[79],"have":[80,98],"same":[82],"or":[83],"similar":[84,99],"(for":[86],"some":[87],"states":[88],"more":[89],"than":[90,215,225],"90%":[91],"equilibria).":[100],"Inspired":[101],"by":[102],"observation,":[104],"proposes":[107],"use":[109],"transfer":[111,121,139,142,158,160,219,229],"accelerate":[113],"MARL.":[115],"The":[116],"key":[117],"idea":[118],"reuse":[124],"previously":[125],"computed":[126],"when":[128,230],"agent":[130],"has":[131],"small":[133],"incentive":[134],"deviate.":[136],"By":[137],"introducing":[138],"loss":[140],"condition,":[143],"novel":[145],"framework":[146],"called":[147],"transfer-based":[149],"proposed.":[152],"We":[153],"prove":[154],"although":[156],"brings":[159],"loss,":[161],"can":[165],"still":[166],"converge":[167],"an":[169],"policy":[171],"under":[172],"certain":[173],"assumptions.":[174],"Experimental":[175],"results":[176],"widely":[178],"used":[179],"benchmarks":[180],"grid":[182],"world":[183],"game,":[184,186],"soccer":[185],"wall":[188],"game)":[189],"show":[190],"proposed":[193],"framework:":[194],"1)":[195],"not":[196],"only":[197],"significantly":[198,223],"accelerates":[199],"(up":[202],"96.7%":[204],"reduction":[205],"time),":[208],"but":[209],"also":[210],"achieves":[211],"higher":[212],"average":[213],"rewards":[214],"without":[217,227],"2)":[221],"scales":[222],"better":[224],"state/action":[232],"space":[233],"grows":[234],"increases.":[240]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}