{"id":"https://openalex.org/W2014394432","doi":"https://doi.org/10.1109/tamd.2014.2362682","title":"Optimal Rewards for Cooperative Agents","display_name":"Optimal Rewards for Cooperative Agents","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2014394432","doi":"https://doi.org/10.1109/tamd.2014.2362682","mag":"2014394432"},"language":"en","primary_location":{"id":"doi:10.1109/tamd.2014.2362682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tamd.2014.2362682","pdf_url":null,"source":{"id":"https://openalex.org/S108448409","display_name":"IEEE Transactions on Autonomous Mental Development","issn_l":"1943-0604","issn":["1943-0604","1943-0612"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Autonomous Mental Development","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/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":["School of Automation Science & Engineering, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation Science & Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103117754","display_name":"Satinder Singh","orcid":"https://orcid.org/0000-0002-8215-8295"},"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":["Division of Computer Science & Engineering, University of Michigan, Ann Arbor, USA","Division of Computer Science and Engineering, University of Michigan, Ann Arbor, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Computer Science & Engineering, University of Michigan, Ann Arbor, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Division of Computer Science and Engineering, 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":["Department of Psychology, University of Michigan, Ann Arbor, USA","Dept. of Psychology, Univ. of Michigan, Ann Arbor, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Psychology, University of Michigan, Ann Arbor, USA","institution_ids":["https://openalex.org/I27837315"]},{"raw_affiliation_string":"Dept. of Psychology, Univ. 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":["School of Automation Science & Engineering, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation Science & Engineering, 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":0.8284,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.8047342,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"6","issue":"4","first_page":"286","last_page":"297"},"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9854999780654907,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9825999736785889,"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":0.707808792591095},{"id":"https://openalex.org/keywords/stochastic-game","display_name":"Stochastic game","score":0.6256351470947266},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5902739763259888},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.538314163684845},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5248967409133911},{"id":"https://openalex.org/keywords/interdependence","display_name":"Interdependence","score":0.48376035690307617},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3834933936595917},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11777454614639282},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1050260066986084}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.707808792591095},{"id":"https://openalex.org/C22171661","wikidata":"https://www.wikidata.org/wiki/Q1074380","display_name":"Stochastic game","level":2,"score":0.6256351470947266},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5902739763259888},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.538314163684845},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5248967409133911},{"id":"https://openalex.org/C185874996","wikidata":"https://www.wikidata.org/wiki/Q269699","display_name":"Interdependence","level":2,"score":0.48376035690307617},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3834933936595917},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11777454614639282},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1050260066986084},{"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},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tamd.2014.2362682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tamd.2014.2362682","pdf_url":null,"source":{"id":"https://openalex.org/S108448409","display_name":"IEEE Transactions on Autonomous Mental Development","issn_l":"1943-0604","issn":["1943-0604","1943-0612"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Autonomous Mental Development","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"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/W1975744985","https://openalex.org/W1996847178","https://openalex.org/W2000514530","https://openalex.org/W2061562262","https://openalex.org/W2071841410","https://openalex.org/W2099845938","https://openalex.org/W2101524054","https://openalex.org/W2105380246","https://openalex.org/W2105546430","https://openalex.org/W2109516767","https://openalex.org/W2122480991","https://openalex.org/W2123327671","https://openalex.org/W2123408238","https://openalex.org/W2127572219","https://openalex.org/W2127842795","https://openalex.org/W2135995480","https://openalex.org/W2154902490","https://openalex.org/W2155511972","https://openalex.org/W2163602945","https://openalex.org/W2164424353","https://openalex.org/W2168405694","https://openalex.org/W2896027395","https://openalex.org/W4243467076","https://openalex.org/W6632235069","https://openalex.org/W6638088447","https://openalex.org/W6675312893","https://openalex.org/W6675777089","https://openalex.org/W6676230659","https://openalex.org/W6678479682","https://openalex.org/W6679078561","https://openalex.org/W6680368475","https://openalex.org/W6683991275"],"related_works":["https://openalex.org/W2139079562","https://openalex.org/W2749324135","https://openalex.org/W2908433117","https://openalex.org/W2969604939","https://openalex.org/W2378306841","https://openalex.org/W114687057","https://openalex.org/W3122988618","https://openalex.org/W1994631104","https://openalex.org/W3146908316","https://openalex.org/W1981558224"],"abstract_inverted_index":{"Following":[0],"work":[1],"on":[2,121,130],"designing":[3],"optimal":[4,13],"rewards":[5,14],"for":[6,28,156],"single":[7],"agents,":[8],"we":[9],"define":[10],"a":[11,59,73],"multiagent":[12,60],"problem":[15,26,116],"(ORP)":[16],"in":[17,44,62,76,88,142],"cooperative":[18],"(specifically,":[19],"common-payoff":[20],"or":[21,194],"team)":[22],"settings.":[23],"This":[24],"new":[25],"solves":[27],"individual":[29,176],"agent":[30,65],"reward":[31,68,100,126,162,177],"functions":[32,69,178],"that":[33,134,164,174],"guide":[34,48],"agents":[35,47,110,124,146],"to":[36,42,78,93,181],"better":[37,182],"overall":[38],"team":[39],"performance":[40],"relative":[41],"teams":[43],"which":[45,63,143],"all":[46,144],"their":[49],"behavior":[50],"with":[51,91,189],"the":[52,80,94,98,104,109,122,135,139,145,148,157,161,165,171],"same":[53,149],"given":[54,99,150],"team-reward":[55,151],"function.":[56],"We":[57,128],"present":[58],"architecture":[61,137],"each":[64,113],"learns":[66],"good":[67,85],"from":[70],"experience":[71],"using":[72],"gradient-based":[74],"algorithm":[75,167],"addition":[77],"performing":[79],"usual":[81],"task":[82],"of":[83,106,160,184],"planning":[84],"policies":[86],"(except":[87],"this":[89],"case":[90],"respect":[92],"learned":[95,193],"rather":[96],"than":[97,186],"function).":[101],"Multiagency":[102],"introduces":[103],"challenge":[105],"nonstationarity:":[107],"because":[108],"learn":[111],"simultaneously,":[112],"agent's":[114],"reward-learning":[115],"is":[117,187],"nonstationary":[118],"and":[119,173],"interdependent":[120],"other":[123],"evolving":[125],"functions.":[127],"demonstrate":[129],"two":[131],"simple":[132],"domains":[133],"proposed":[136],"outperforms":[138],"conventional":[140],"approach":[141],"use":[147],"function":[152],"(even":[153],"when":[154],"accounting":[155],"resource":[158],"overhead":[159],"learning);":[163],"learning":[166,175],"performs":[168],"stably":[169],"despite":[170],"nonstationarity;":[172],"can":[179],"lead":[180],"specialization":[183],"roles":[185],"possible":[188],"shared":[190],"reward,":[191],"whether":[192],"given.":[195]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}