{"id":"https://openalex.org/W58712762","doi":null,"title":"Learning in dynamic noncooperative multiagent systems.","display_name":"Learning in dynamic noncooperative multiagent systems.","publication_year":1999,"publication_date":"1999-01-01","ids":{"openalex":"https://openalex.org/W58712762","mag":"58712762"},"language":"en","primary_location":{"id":"pmh:oai:deepblue.lib.umich.edu:2027.42/131906","doi":null,"is_oa":false,"landing_page_url":"https://deepblue.lib.umich.edu/bitstreams/dcd1c163-1811-4fb8-9613-1845f3f48691/download","pdf_url":null,"source":{"id":"https://openalex.org/S4306400393","display_name":"Deep Blue (University of Michigan)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I27837315","host_organization_name":"University of Michigan","host_organization_lineage":["https://openalex.org/I27837315"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"volume":null,"type":"dissertation","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":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6913999915122986,"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":0.6913999915122986,"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":0.29170000553131104,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.005799999926239252,"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-learning","display_name":"multi-agent learning","score":0.9049999713897705},{"id":"https://openalex.org/keywords/noncooperative-games","display_name":"non-cooperative game","score":0.9300000071525574},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.7850000262260437},{"id":"https://openalex.org/keywords/stochastic-games","display_name":"stochastic games","score":0.5979999899864197},{"id":"https://openalex.org/keywords/incomplete-information","display_name":"incomplete information","score":0.8870000243186951},{"id":"https://openalex.org/keywords/nash-equilibrium-convergence","display_name":"Nash equilibrium convergence","score":0.843999981880188},{"id":"https://openalex.org/keywords/model-based-learning","display_name":"model-based learning","score":0.6779999732971191},{"id":"https://openalex.org/keywords/recursive-models","display_name":"recursive models","score":0.9430000185966492},{"id":"https://openalex.org/keywords/double-auction-markets","display_name":"double auction markets","score":0.8059999942779541},{"id":"https://openalex.org/keywords/selfish-agents","display_name":"self-interested agents","score":0.7139999866485596},{"id":"https://openalex.org/keywords/decision-making","display_name":"decision-making","score":0.45500001311302185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5101661682128906}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:deepblue.lib.umich.edu:2027.42/131906","doi":null,"is_oa":false,"landing_page_url":"https://deepblue.lib.umich.edu/bitstreams/dcd1c163-1811-4fb8-9613-1845f3f48691/download","pdf_url":null,"source":{"id":"https://openalex.org/S4306400393","display_name":"Deep Blue (University of Michigan)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I27837315","host_organization_name":"University of Michigan","host_organization_lineage":["https://openalex.org/I27837315"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},{"id":"mag:58712762","doi":null,"is_oa":false,"landing_page_url":"https://hdl.handle.net/2027.42/131906","pdf_url":null,"source":{"id":"https://openalex.org/S4306400393","display_name":"Deep Blue (University of Michigan)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I27837315","host_organization_name":"University of Michigan","host_organization_lineage":["https://openalex.org/I27837315"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Deep Blue (University of Michigan)","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2358428922","https://openalex.org/W4412353378","https://openalex.org/W7099078619","https://openalex.org/W1972349721","https://openalex.org/W7095697378","https://openalex.org/W7098366223","https://openalex.org/W2100427262","https://openalex.org/W1971173632","https://openalex.org/W341120173","https://openalex.org/W7099656984"],"abstract_inverted_index":{"Dynamic":[0],"noncooperative":[1],"multiagent":[2,48,106,232],"systems":[3,5,34],"are":[4,84,137,191],"where":[6,157,184],"self-interested":[7],"agents":[8,158,209],"interact":[9],"with":[10,42],"each":[11,194],"other":[12,293,307],"and":[13,25,51,95,139,163,193,295],"their":[14,165],"interactions":[15],"change":[16],"over":[17],"time.":[18],"We":[19,31,45,108,172,234,261],"investigate":[20],"the":[21,33,36,56,90,99,123,135,170,185,189,221,237,290,302,310,316],"problem":[22,238],"of":[23,38,58,92,131,161,169,188,223,239,265,279,292,304,306,312],"learning":[24,67,112,141,156,177],"decision":[26,81],"making":[27],"in":[28,35,55,242,256,268],"such":[29],"systems.":[30,74,107],"model":[32,267],"framework":[37,57,91],"general-sum":[39],"stochastic":[40,59],"games":[41],"incomplete":[43],"information.":[44],"design":[46],"a":[47,65,116,132,181,229,243,269],"Q-learning":[49,63],"method,":[50,64,68],"prove":[52,109],"its":[53,199,287],"convergence":[54,76],"games.":[60,260],"The":[61,208],"standard":[62],"reinforcement":[66,93,149],"was":[69,77],"originally":[70],"designed":[71],"for":[72,79,102,231],"single-agent":[73,85],"Its":[75],"proved":[78],"Markov":[80],"processes,":[82],"which":[83,252],"problems.":[86],"Our":[87,274],"extension":[88],"broadens":[89],"learning,":[94,150],"helps":[96],"to":[97,105,115,147,180,219,286],"establish":[98],"theoretical":[100],"foundation":[101],"applying":[103],"it":[104],"that":[110,174,277],"our":[111,129,140],"algorithm":[113],"converges":[114],"Nash":[117],"equilibrium":[118,203],"under":[119],"certain":[120],"restrictions":[121,136],"on":[122],"game":[124,245],"structure":[125],"during":[126],"learning.":[127,233],"In":[128,145],"simulations":[130],"grid-world":[133],"game,":[134],"relaxed":[138],"method":[142],"still":[143],"converges.":[144],"addition":[146],"model-free":[148],"we":[151],"have":[152],"also":[153,235],"studied":[154,253],"model-based":[155],"form":[159],"models":[160,166,187,222],"others":[162,190,224],"update":[164],"through":[167],"observations":[168],"environment.":[171],"find":[173],"agents'":[175,186],"mutual":[176],"can":[178,282],"lead":[179],"conjectural":[182],"equilibrium,":[183],"fulfilled,":[192],"agent":[195,281],"behaves":[196],"optimally":[197],"given":[198],"expectation.":[200],"Such":[201],"an":[202,280],"state":[204],"may":[205,210],"be":[206,211,283,315],"suboptimal.":[207],"worse":[212],"off":[213],"than":[214],"had":[215],"they":[216],"not":[217],"attempted":[218],"learn":[220],"at":[225],"all.":[226],"This":[227,247],"poses":[228],"pitfall":[230],"analyzed":[236],"recursive":[240,254,266],"modeling":[241,255],"dynamic":[244],"framework.":[246],"differs":[248],"from":[249],"previous":[250],"work":[251],"static":[257],"or":[258],"repeated":[259],"implement":[262],"various":[263],"levels":[264],"simulated":[270],"double":[271],"auction":[272],"market.":[273],"experiments":[275],"show":[276],"performance":[278],"quite":[284],"sensitive":[285],"assumptions":[288],"about":[289,301],"policies":[291],"agents,":[294,308],"when":[296],"there":[297],"is":[298],"substantial":[299],"uncertainty":[300],"level":[303,311],"sophistication":[305],"reducing":[309],"recursion":[313],"might":[314],"best":[317],"policy.":[318]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2016-06-24T00:00:00"}