{"id":"https://openalex.org/W2164851236","doi":"https://doi.org/10.1142/s0219525909002301","title":"LEARNING FROM ACTIONS NOT TAKEN IN MULTIAGENT SYSTEMS","display_name":"LEARNING FROM ACTIONS NOT TAKEN IN MULTIAGENT SYSTEMS","publication_year":2009,"publication_date":"2009-08-01","ids":{"openalex":"https://openalex.org/W2164851236","doi":"https://doi.org/10.1142/s0219525909002301","mag":"2164851236"},"language":"en","primary_location":{"id":"doi:10.1142/s0219525909002301","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219525909002301","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/A5108507903","display_name":"Kagan Tumer","orcid":null},"institutions":[{"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"]},{"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"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"KAGAN TUMER","raw_affiliation_strings":["Oregon State University, 204 Rogers Hall, Corvallis, Oregon 97331, USA"],"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/A5015724504","display_name":"Newsha Khani","orcid":null},"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":"NEWSHA KHANI","raw_affiliation_strings":["Oregon State University, 204 Rogers Hall, Corvallis, Oregon 97331, USA"],"affiliations":[{"raw_affiliation_string":"Oregon State University, 204 Rogers Hall, Corvallis, Oregon 97331, USA","institution_ids":["https://openalex.org/I131249849","https://openalex.org/I75717288"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5108507903"],"corresponding_institution_ids":["https://openalex.org/I131249849","https://openalex.org/I75717288"],"apc_list":null,"apc_paid":null,"fwci":0.8724,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.8156444,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"12","issue":"04n05","first_page":"455","last_page":"473"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9947999715805054,"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":0.978600025177002,"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/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.7291048169136047},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.707618236541748},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6835139393806458},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6248823404312134},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5902194976806641},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5895199775695801},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5260962247848511},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4795803129673004},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4729868173599243},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.0896310806274414},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0694781243801117}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.7291048169136047},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.707618236541748},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6835139393806458},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6248823404312134},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5902194976806641},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5895199775695801},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5260962247848511},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4795803129673004},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4729868173599243},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0896310806274414},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0694781243801117},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1142/s0219525909002301","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219525909002301","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:s0219525909002301","is_oa":false,"landing_page_url":"http://www.worldscientific.com/doi/abs/10.1142/S0219525909002301","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":99,"referenced_works":["https://openalex.org/W13526124","https://openalex.org/W102626069","https://openalex.org/W606039600","https://openalex.org/W820940628","https://openalex.org/W830002905","https://openalex.org/W1513468570","https://openalex.org/W1521003796","https://openalex.org/W1536258751","https://openalex.org/W1538558539","https://openalex.org/W1542941925","https://openalex.org/W1557517019","https://openalex.org/W1560074431","https://openalex.org/W1564534945","https://openalex.org/W1575989700","https://openalex.org/W1576452626","https://openalex.org/W1589901344","https://openalex.org/W1595172192","https://openalex.org/W1597309614","https://openalex.org/W1626977535","https://openalex.org/W1657704689","https://openalex.org/W1760981091","https://openalex.org/W1861528341","https://openalex.org/W1931280659","https://openalex.org/W1963576113","https://openalex.org/W1969302761","https://openalex.org/W1973039793","https://openalex.org/W1979377690","https://openalex.org/W1980358463","https://openalex.org/W2004224914","https://openalex.org/W2006303459","https://openalex.org/W2015071010","https://openalex.org/W2020294948","https://openalex.org/W2021198656","https://openalex.org/W2024060531","https://openalex.org/W2034587361","https://openalex.org/W2053194968","https://openalex.org/W2061504687","https://openalex.org/W2083535091","https://openalex.org/W2088956500","https://openalex.org/W2089415692","https://openalex.org/W2094304980","https://openalex.org/W2095611126","https://openalex.org/W2097568888","https://openalex.org/W2098262393","https://openalex.org/W2098432798","https://openalex.org/W2098877483","https://openalex.org/W2099815249","https://openalex.org/W2103047651","https://openalex.org/W2103551861","https://openalex.org/W2103626435","https://openalex.org/W2104394958","https://openalex.org/W2104459548","https://openalex.org/W2104602264","https://openalex.org/W2104641222","https://openalex.org/W2107726111","https://openalex.org/W2108734173","https://openalex.org/W2110116921","https://openalex.org/W2110158409","https://openalex.org/W2113998737","https://openalex.org/W2116043092","https://openalex.org/W2116384962","https://openalex.org/W2116399160","https://openalex.org/W2117341272","https://openalex.org/W2118318536","https://openalex.org/W2118899043","https://openalex.org/W2119567691","https://openalex.org/W2121517924","https://openalex.org/W2121863487","https://openalex.org/W2128643385","https://openalex.org/W2128672031","https://openalex.org/W2129512980","https://openalex.org/W2132022084","https://openalex.org/W2132522159","https://openalex.org/W2134281179","https://openalex.org/W2138076440","https://openalex.org/W2140711439","https://openalex.org/W2142505627","https://openalex.org/W2146890818","https://openalex.org/W2150414301","https://openalex.org/W2150690636","https://openalex.org/W2151035451","https://openalex.org/W2153905331","https://openalex.org/W2154964352","https://openalex.org/W2156666755","https://openalex.org/W2161061197","https://openalex.org/W2165260235","https://openalex.org/W2168003214","https://openalex.org/W2169462890","https://openalex.org/W2171863654","https://openalex.org/W2172264025","https://openalex.org/W2615688110","https://openalex.org/W2787259794","https://openalex.org/W3011120880","https://openalex.org/W3098542421","https://openalex.org/W3103882218","https://openalex.org/W3105424838","https://openalex.org/W3124750989","https://openalex.org/W4205093675","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W3201448254","https://openalex.org/W4286970243","https://openalex.org/W2066431708","https://openalex.org/W3025615835","https://openalex.org/W4384133558","https://openalex.org/W173210993","https://openalex.org/W2390660599","https://openalex.org/W3003410553","https://openalex.org/W3028847759","https://openalex.org/W2393688264"],"abstract_inverted_index":{"In":[0,87],"large":[1],"cooperative":[2],"multiagent":[3,53,93,103],"systems,":[4],"coordinating":[5],"the":[6,9,14,23,30,48,56,81,99,114,129,142,159,196,212],"actions":[7,32,82,176],"of":[8,47,83,113],"agents":[10,24],"is":[11,55,136,200,208],"critical":[12,201,209],"to":[13,26,34,66,69,78,109,188,210],"overall":[15],"system":[16,36],"achieving":[17],"its":[18,111,124],"intended":[19],"goal.":[20],"Even":[21],"when":[22,172],"aim":[25],"cooperate,":[27],"ensuring":[28],"that":[29,96,131,158,195],"agent":[31,62,108,140,184],"lead":[33],"good":[35],"level":[37],"behavior":[38],"becomes":[39],"increasingly":[40],"difficult":[41],"as":[42],"systems":[43,54,104],"become":[44],"larger.":[45],"One":[46],"fundamental":[49],"difficulties":[50],"in":[51,71,102,119,169,202],"such":[52,162],"slow":[57],"learning":[58,85,94,100,198,207],"process":[59],"where":[60,183,205],"an":[61,107,139],"not":[63,127,164],"only":[64,173],"needs":[65,77],"learn":[67],"how":[68],"behave":[70],"a":[72,92,152],"complex":[73],"environment,":[74],"but":[75],"also":[76],"account":[79],"for":[80,122],"other":[84],"agents.":[86],"this":[88],"paper,":[89],"we":[90,193],"present":[91,181],"approach":[95,135],"significantly":[97],"improves":[98],"speed":[101,199],"by":[105],"allowing":[106],"update":[110],"estimate":[112,189],"rewards":[115,160],"(e.g.":[116],"value":[117],"function":[118],"reinforcement":[120],"learning)":[121],"all":[123],"available":[125],"actions,":[126],"just":[128],"action":[130],"was":[132],"taken.":[133],"This":[134],"based":[137],"on":[138,161],"estimating":[141],"counterfactual":[143],"reward":[144],"it":[145,150],"would":[146],"have":[147],"received":[148],"had":[149],"taken":[151],"particular":[153,174],"action.":[154],"Our":[155],"results":[156,182],"show":[157,194],"\"actions":[163],"taken\"":[165],"are":[166,177,186],"beneficial":[167],"early":[168],"training,":[170],"particularly":[171],"\"key\"":[175],"used.":[178],"We":[179],"then":[180],"teams":[185],"leveraged":[187],"those":[190],"rewards.":[191],"Finally,":[192],"improved":[197],"dynamic":[203],"environments":[204],"fast":[206],"tracking":[211],"underlying":[213],"processes.":[214]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}