{"id":"https://openalex.org/W1513468570","doi":null,"title":"Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm","display_name":"Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm","publication_year":1998,"publication_date":"1998-07-24","ids":{"openalex":"https://openalex.org/W1513468570","mag":"1513468570"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.138.2589","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.138.2589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ee.duke.edu/~lcarin/emag/seminar_presentations/Multiagent_Learning_Hu_ICML98.pdf","raw_type":"text"},"volume":null,"type":"article","indexed_in":[],"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/A5103937904","display_name":"Junling Hu","orcid":"https://orcid.org/0009-0004-9643-0300","observed_orcids":["https://orcid.org/0009-0004-9643-0300"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junling Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5002102744","display_name":"Michael P. Wellman","orcid":"https://orcid.org/0000-0002-1691-6844","observed_orcids":["https://orcid.org/0000-0002-1691-6844"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael P. Wellman","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-1691-6844","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.7426,"has_fulltext":false,"cited_by_count":776,"citation_normalized_percentile":{"value":0.992516,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"242","last_page":"250"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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/T11031","display_name":"Game Theory and Applications","score":0.0010999999940395355,"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"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.00019999999494757503,"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/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.9990000128746033},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.8669999837875366},{"id":"https://openalex.org/keywords/convergence-analysis","display_name":"convergence analysis","score":0.765999972820282},{"id":"https://openalex.org/keywords/zero-sum-stochastic-games","display_name":"zero-sum stochastic games","score":0.7919999957084656},{"id":"https://openalex.org/keywords/optimal-strategies","display_name":"optimal strategies","score":0.5709999799728394},{"id":"https://openalex.org/keywords/multiple-nash-equilibria","display_name":"multiple Nash equilibria","score":0.9430000185966492}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8113656044006348},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6614320278167725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4442984461784363},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4329512417316437},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3322363495826721}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.138.2589","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.138.2589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ee.duke.edu/~lcarin/emag/seminar_presentations/Multiagent_Learning_Hu_ICML98.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.31.4827","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.31.4827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.eecs.umich.edu/people/wellman/icml98.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.42.1313","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.42.1313","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ai.eecs.umich.edu/people/junling/papers/icml98.ps","raw_type":"text"},{"id":"mag:1513468570","doi":null,"is_oa":false,"landing_page_url":"http://dblp.uni-trier.de/db/conf/icml/icml1998.html#HuW98","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2403056771","https://openalex.org/W7124199144","https://openalex.org/W2358428922","https://openalex.org/W7096597637","https://openalex.org/W2099602914","https://openalex.org/W1515108343","https://openalex.org/W7095697378","https://openalex.org/W1966224968","https://openalex.org/W2901559512","https://openalex.org/W2145067550"],"abstract_inverted_index":{"In":[0],"this":[1,37,79],"paper,":[2],"we":[3],"adopt":[4],"general-sum":[5],"stochastic":[6,24],"games":[7,25],"as":[8],"a":[9,27,32,45,63,108,115],"framework":[10],"for":[11,55,129],"multiagent":[12,33,130],"reinforcement":[13,125,147],"learning.":[14,144],"Our":[15],"work":[16,19],"extends":[17],"previous":[18],"by":[20],"Littman":[21],"on":[22],"zero-sum":[23],"to":[26,44,88],"broader":[28],"framework.":[29],"We":[30],"design":[31],"Q-learning":[34],"method":[35,110],"under":[36,48],"framework,":[38],"and":[39,99,120,139],"prove":[40],"that":[41,111],"it":[42],"converges":[43],"Nash":[46,65,74],"equilibrium":[47,66],"specified":[49],"conditions.":[50],"This":[51],"algorithm":[52,80],"is":[53,127],"useful":[54],"finding":[56],"the":[57,68,77,140],"optimal":[58,90],"strategy":[59],"when":[60],"there":[61,71],"exists":[62],"unique":[64],"in":[67,76,102,149],"game.":[69],"When":[70],"exist":[72],"multiple":[73],"equilibria":[75],"game,":[78],"should":[81],"be":[82,122],"combined":[83],"with":[84],"other":[85,137],"learning":[86,95,109,126,148],"techniques":[87],"find":[89],"strategies.":[91],"1":[92],"Introduction":[93],"Reinforcement":[94],"has":[96],"gained":[97],"attention":[98],"extensive":[100],"study":[101],"recent":[103],"years":[104],"[5,":[105],"12].":[106],"As":[107],"does":[112],"not":[113],"need":[114],"model":[116],"of":[117,146],"its":[118],"environment":[119,141],"can":[121],"used":[123],"online,":[124],"wellsuited":[128],"systems,":[131],"where":[132],"agents":[133],"know":[134],"little":[135],"about":[136],"agents,":[138],"changes":[142],"during":[143],"Applications":[145],"multi...":[150]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":27},{"year":2021,"cited_by_count":46},{"year":2020,"cited_by_count":58},{"year":2019,"cited_by_count":52},{"year":2018,"cited_by_count":21},{"year":2017,"cited_by_count":18},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":17},{"year":2014,"cited_by_count":31},{"year":2013,"cited_by_count":35},{"year":2012,"cited_by_count":27}],"updated_date":"2026-10-27T15:51:10.671819","created_date":"2016-06-24T00:00:00"}