{"id":"https://openalex.org/W2169560253","doi":"https://doi.org/10.1142/s0219525909002295","title":"MULTIAGENT LEARNING FOR BLACK BOX SYSTEM REWARD FUNCTIONS","display_name":"MULTIAGENT LEARNING FOR BLACK BOX SYSTEM REWARD FUNCTIONS","publication_year":2009,"publication_date":"2009-08-01","ids":{"openalex":"https://openalex.org/W2169560253","doi":"https://doi.org/10.1142/s0219525909002295","mag":"2169560253"},"language":"en","primary_location":{"id":"doi:10.1142/s0219525909002295","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219525909002295","pdf_url":null,"source":{"id":"https://openalex.org/S107361000","display_name":"Advances in Complex Systems","issn_l":"0219-5259","issn":["0219-5259","1793-6802","1793-9615","1793-9623"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Complex Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5084748531","display_name":"Kagan Tumer","orcid":"https://orcid.org/0009-0007-3809-7257"},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]},{"id":"https://openalex.org/I75717288","display_name":"Rogers (United States)","ror":"https://ror.org/05m9vrv91","country_code":"US","type":"company","lineage":["https://openalex.org/I75717288"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"KAGAN TUMER","raw_affiliation_strings":["Oregon State University, 204 Rogers Hall, Corvallis, Oregon 97331, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon State University, 204 Rogers Hall, Corvallis, Oregon 97331, USA","institution_ids":["https://openalex.org/I131249849","https://openalex.org/I75717288"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047563625","display_name":"Adrian Agogino","orcid":"https://orcid.org/0000-0002-6802-4477"},"institutions":[{"id":"https://openalex.org/I1280536761","display_name":"Ames Research Center","ror":"https://ror.org/02acart68","country_code":"US","type":"facility","lineage":["https://openalex.org/I1280536761","https://openalex.org/I4210124779"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"ADRIAN AGOGINO","raw_affiliation_strings":["UCSC, NASA Ames Research Center, Mailstop 269-3, Moffett Field, California 94035, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCSC, NASA Ames Research Center, Mailstop 269-3, Moffett Field, California 94035, USA","institution_ids":["https://openalex.org/I1280536761"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.1574907,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"12","issue":"04n05","first_page":"475","last_page":"492"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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/T11182","display_name":"Auction Theory and Applications","score":0.9987999796867371,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.993399977684021,"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/computer-science","display_name":"Computer science","score":0.7513325214385986},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6055423617362976},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5593715906143188},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5488477945327759},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5118550658226013},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.5107479095458984},{"id":"https://openalex.org/keywords/blame","display_name":"Blame","score":0.46249982714653015},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.4349682033061981},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.4139483571052551},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.39624887704849243},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37044644355773926},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13235530257225037},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08883336186408997}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7513325214385986},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6055423617362976},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5593715906143188},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5488477945327759},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5118550658226013},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.5107479095458984},{"id":"https://openalex.org/C2781466463","wikidata":"https://www.wikidata.org/wiki/Q621695","display_name":"Blame","level":2,"score":0.46249982714653015},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.4349682033061981},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.4139483571052551},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.39624887704849243},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37044644355773926},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13235530257225037},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08883336186408997},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1142/s0219525909002295","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219525909002295","pdf_url":null,"source":{"id":"https://openalex.org/S107361000","display_name":"Advances in Complex Systems","issn_l":"0219-5259","issn":["0219-5259","1793-6802","1793-9615","1793-9623"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Complex Systems","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:wsi:acsxxx:v:12:y:2009:i:04n05:n:s0219525909002295","is_oa":false,"landing_page_url":"http://www.worldscientific.com/doi/abs/10.1142/S0219525909002295","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"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":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"No poverty","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W13526124","https://openalex.org/W156814138","https://openalex.org/W1491024819","https://openalex.org/W1525481342","https://openalex.org/W1980358463","https://openalex.org/W2015071010","https://openalex.org/W2021198656","https://openalex.org/W2036280551","https://openalex.org/W2053194968","https://openalex.org/W2058207083","https://openalex.org/W2082892656","https://openalex.org/W2083535091","https://openalex.org/W2095633276","https://openalex.org/W2098877483","https://openalex.org/W2103551861","https://openalex.org/W2104641222","https://openalex.org/W2107726111","https://openalex.org/W2109516767","https://openalex.org/W2116043092","https://openalex.org/W2117341272","https://openalex.org/W2118318536","https://openalex.org/W2118899043","https://openalex.org/W2119053738","https://openalex.org/W2121517924","https://openalex.org/W2126007133","https://openalex.org/W2129512980","https://openalex.org/W2130519480","https://openalex.org/W2132022084","https://openalex.org/W2132522159","https://openalex.org/W2155272711","https://openalex.org/W2161061197","https://openalex.org/W2164197363","https://openalex.org/W2166731466","https://openalex.org/W2171863654","https://openalex.org/W2172264025","https://openalex.org/W3098542421","https://openalex.org/W3101690729"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W2013643406","https://openalex.org/W2157978810","https://openalex.org/W2597809628","https://openalex.org/W3046370962"],"abstract_inverted_index":{"In":[0,60],"large,":[1],"distributed":[2,173],"systems":[3,36],"composed":[4],"of":[5,39,56,77,96,115,139,159,162,195],"adaptive":[6],"and":[7,176,183,192],"interactive":[8],"components":[9],"(agents),":[10],"ensuring":[11],"the":[12,15,19,54,57,93,142,145,163],"coordination":[13],"among":[14],"agents":[16],"so":[17],"that":[18],"system":[20,149],"achieves":[21],"certain":[22],"performance":[23,55,170,187],"objectives":[24],"is":[25,37],"a":[26,49,74,137,156,172,185,193],"challenging":[27],"proposition.":[28],"The":[29],"key":[30],"difficulty":[31],"to":[32,43,48,148],"overcome":[33],"in":[34,71,110],"such":[35],"one":[38],"credit":[40,45],"assignment:":[41],"How":[42],"apportion":[44],"(or":[46],"blame)":[47],"particular":[50],"agent":[51,146,204],"based":[52],"on":[53,171],"entire":[58],"system.":[59],"this":[61,66],"paper,":[62],"we":[63],"show":[64,184],"how":[65],"problem":[67,175,182],"can":[68,125,152],"be":[69,84,126,153],"solved":[70],"general":[72],"for":[73,133,136,198],"large":[75,111],"class":[76,138],"reward":[78,150],"functions":[79,151,161],"whose":[80],"analytical":[81],"form":[82],"may":[83],"unknown":[85],"(hence":[86],"\"black":[87],"box\"":[88],"reward).":[89],"This":[90],"method":[91],"combines":[92],"salient":[94],"features":[95],"global":[97],"solutions":[98,109,117],"(e.g.":[99,118],"\"team":[100],"games\")":[101],"which":[102,121],"are":[103],"broadly":[104],"applicable":[105],"but":[106,124],"provide":[107],"poor":[108],"problems":[112,140],"with":[113],"those":[114],"local":[116,134],"\"difference":[119],"rewards\")":[120],"learn":[122],"quickly,":[123],"computationally":[127],"burdensome.":[128],"We":[129,166],"introduce":[130],"two":[131],"estimates":[132],"rewards":[135,200],"where":[141],"mapping":[143],"from":[144],"actions":[147],"decomposed":[154],"into":[155],"linear":[157],"combination":[158],"nonlinear":[160],"agents'":[164],"actions.":[165],"test":[167],"our":[168],"method's":[169],"marketing":[174],"an":[177,202],"air":[178],"traffic":[179],"flow":[180],"management":[181],"44%":[186],"improvement":[188],"over":[189],"team":[190],"games":[191],"speedup":[194],"order":[196],"n":[197,203],"difference":[199],"(for":[201],"system).":[205]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}