{"id":"https://openalex.org/W2544765807","doi":"https://doi.org/10.1109/devlrn.2012.6400862","title":"Optimal rewards in multiagent teams","display_name":"Optimal rewards in multiagent teams","publication_year":2012,"publication_date":"2012-11-01","ids":{"openalex":"https://openalex.org/W2544765807","doi":"https://doi.org/10.1109/devlrn.2012.6400862","mag":"2544765807"},"language":"en","primary_location":{"id":"doi:10.1109/devlrn.2012.6400862","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2012.6400862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5003698008","display_name":"Bingyao Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingyao Liu","raw_affiliation_strings":["Automation Science & Engin. Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Automation Science & Engin. Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065366930","display_name":"Satinder Singh","orcid":"https://orcid.org/0000-0002-2736-7641"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Satinder Singh","raw_affiliation_strings":["Computer Science & Engin. University of Michigan, Ann Arbor, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science & Engin. University of Michigan, Ann Arbor, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077109450","display_name":"Richard L. Lewis","orcid":"https://orcid.org/0000-0001-6403-489X"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard L. Lewis","raw_affiliation_strings":["Psychology University of Michigan, Ann Arbor, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Psychology University of Michigan, Ann Arbor, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058280770","display_name":"Shiyin Qin","orcid":"https://orcid.org/0000-0002-2663-3813"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyin Qin","raw_affiliation_strings":["Automation Science & Engin. Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Automation Science & Engin. Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9962000250816345,"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/T11031","display_name":"Game Theory and Applications","score":0.992900013923645,"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/computer-science","display_name":"Computer science","score":0.7225260734558105},{"id":"https://openalex.org/keywords/stochastic-game","display_name":"Stochastic game","score":0.6228122711181641},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.6201470494270325},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5724221467971802},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5405714511871338},{"id":"https://openalex.org/keywords/interdependence","display_name":"Interdependence","score":0.5115467309951782},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.48971202969551086},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4166443645954132},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.413252592086792},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3682541847229004},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11329090595245361},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10467806458473206}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7225260734558105},{"id":"https://openalex.org/C22171661","wikidata":"https://www.wikidata.org/wiki/Q1074380","display_name":"Stochastic game","level":2,"score":0.6228122711181641},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6201470494270325},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5724221467971802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5405714511871338},{"id":"https://openalex.org/C185874996","wikidata":"https://www.wikidata.org/wiki/Q269699","display_name":"Interdependence","level":2,"score":0.5115467309951782},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.48971202969551086},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4166443645954132},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.413252592086792},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3682541847229004},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11329090595245361},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10467806458473206},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/devlrn.2012.6400862","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2012.6400862","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.299.904","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.299.904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-personal.umich.edu/~rickl/pubs/liu-singh-lewis-qin-2012-icdl.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W807910218","https://openalex.org/W1540685400","https://openalex.org/W1625390266","https://openalex.org/W1777239053","https://openalex.org/W1819200667","https://openalex.org/W1863227302","https://openalex.org/W1982239148","https://openalex.org/W2000514530","https://openalex.org/W2058857176","https://openalex.org/W2061562262","https://openalex.org/W2071841410","https://openalex.org/W2099845938","https://openalex.org/W2101524054","https://openalex.org/W2105380246","https://openalex.org/W2109516767","https://openalex.org/W2127572219","https://openalex.org/W2127842795","https://openalex.org/W2135995480","https://openalex.org/W2154902490","https://openalex.org/W2155511972","https://openalex.org/W2164424353","https://openalex.org/W2168405694","https://openalex.org/W6622926695","https://openalex.org/W6632235069","https://openalex.org/W6636578284","https://openalex.org/W6638088447","https://openalex.org/W6675312893","https://openalex.org/W6675777089","https://openalex.org/W6676230659","https://openalex.org/W6679078561","https://openalex.org/W6680368475"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W2357857148","https://openalex.org/W4224009465","https://openalex.org/W1981558224","https://openalex.org/W4286629047","https://openalex.org/W2028024605","https://openalex.org/W4306321456","https://openalex.org/W2095876242","https://openalex.org/W4285260836"],"abstract_inverted_index":{"Following":[0],"work":[1],"on":[2,119,125],"designing":[3],"optimal":[4,13],"rewards":[5,14],"for":[6,26,151],"single":[7],"agents,":[8],"we":[9],"define":[10],"a":[11,57,71],"multiagent":[12,58],"problem":[15,24,114],"(ORP)":[16],"in":[17,42,60,74,86,137],"common-payoff":[18],"(or":[19],"team)":[20],"settings.":[21],"This":[22],"new":[23],"solves":[25],"individual":[27,171],"agent":[28,63],"reward":[29,66,98,157,172],"functions":[30,67,173],"that":[31,129,159,169],"guide":[32,46],"agents":[33,45,108,141],"to":[34,40,76,91,176],"better":[35,177],"overall":[36],"team":[37],"performance":[38],"relative":[39],"teams":[41],"which":[43,61,138],"all":[44,139],"their":[47],"behavior":[48],"with":[49,89,184],"the":[50,78,92,96,102,107,120,130,134,140,143,152,156,160,166],"same":[51,144],"given":[52,97,145],"team-reward":[53,146],"function.":[54],"We":[55,123],"present":[56],"architecture":[59,132],"each":[62,111],"learns":[64],"good":[65,83],"from":[68],"experience":[69],"using":[70],"gradient-based":[72],"algorithm":[73,162],"addition":[75],"performing":[77],"usual":[79],"task":[80],"of":[81,104,155,179],"planning":[82],"policies":[84],"(except":[85],"this":[87],"case":[88],"respect":[90],"learned":[93,188],"rather":[94],"than":[95,181],"function).":[99],"Multiagency":[100],"introduces":[101],"challenge":[103],"nonstationarity:":[105],"because":[106],"learn":[109],"simultaneously,":[110],"agent's":[112],"learning":[113,161,170],"is":[115,182],"nonstationary":[116],"and":[117,168],"interdependent":[118],"other":[121],"agents.":[122],"demonstrate":[124],"two":[126],"simple":[127],"domains":[128],"proposed":[131],"outperforms":[133],"conventional":[135],"approach":[136],"use":[142],"function":[147],"(even":[148],"when":[149],"accounting":[150],"resource":[153],"overhead":[154],"learning);":[158],"performs":[163],"stably":[164],"despite":[165],"nonstationarity;":[167],"can":[174],"lead":[175],"specialization":[178],"roles":[180],"possible":[183],"shared":[185],"reward,":[186],"whether":[187],"or":[189],"given.":[190]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}