{"id":"https://openalex.org/W4386699358","doi":"https://doi.org/10.1109/tmc.2023.3315120","title":"Teamwork Reinforcement Learning With Concave Utilities","display_name":"Teamwork Reinforcement Learning With Concave Utilities","publication_year":2023,"publication_date":"2023-09-13","ids":{"openalex":"https://openalex.org/W4386699358","doi":"https://doi.org/10.1109/tmc.2023.3315120"},"language":"en","primary_location":{"id":"doi:10.1109/tmc.2023.3315120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2023.3315120","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Mobile Computing","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/A5101660454","display_name":"Zheng Yu","orcid":"https://orcid.org/0000-0002-2525-2912"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zheng Yu","raw_affiliation_strings":["Princeton University, Pirnceton, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0002-2525-2912","affiliations":[{"raw_affiliation_string":"Princeton University, Pirnceton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101898224","display_name":"Junyu Zhang","orcid":"https://orcid.org/0000-0003-2194-9664"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Junyu Zhang","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-2194-9664","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067555437","display_name":"Zheng Wen","orcid":"https://orcid.org/0000-0001-6987-6463"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zheng Wen","raw_affiliation_strings":["DeepMind, London, U.K"],"raw_orcid":"https://orcid.org/0000-0001-6987-6463","affiliations":[{"raw_affiliation_string":"DeepMind, London, U.K","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071433151","display_name":"Andrea Tacchetti","orcid":"https://orcid.org/0000-0001-9311-9171"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrea Tacchetti","raw_affiliation_strings":["DeepMind, London, U.K"],"raw_orcid":"https://orcid.org/0000-0001-9311-9171","affiliations":[{"raw_affiliation_string":"DeepMind, London, U.K","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100707460","display_name":"Mengdi Wang","orcid":"https://orcid.org/0000-0002-2101-9507"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mengdi Wang","raw_affiliation_strings":["Princeton University, Pirnceton, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0002-2101-9507","affiliations":[{"raw_affiliation_string":"Princeton University, Pirnceton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112947561","display_name":"Ian Gemp","orcid":"https://orcid.org/0000-0002-7774-3246"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ian Gemp","raw_affiliation_strings":["DeepMind, London, U.K"],"raw_orcid":"https://orcid.org/0000-0002-7774-3246","affiliations":[{"raw_affiliation_string":"DeepMind, London, U.K","institution_ids":["https://openalex.org/I4210090411"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101660454"],"corresponding_institution_ids":["https://openalex.org/I20089843"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11493717,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":"5","first_page":"5709","last_page":"5721"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9975000023841858,"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":0.9975000023841858,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.9715999960899353,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9616000056266785,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7459991574287415},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7222580909729004},{"id":"https://openalex.org/keywords/teamwork","display_name":"Teamwork","score":0.6916139125823975},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48619383573532104},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.47181451320648193},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.47099679708480835},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.4392779767513275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3580649793148041},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17399320006370544},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11079150438308716}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7459991574287415},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7222580909729004},{"id":"https://openalex.org/C111226992","wikidata":"https://www.wikidata.org/wiki/Q626225","display_name":"Teamwork","level":2,"score":0.6916139125823975},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48619383573532104},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.47181451320648193},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.47099679708480835},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.4392779767513275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3580649793148041},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17399320006370544},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11079150438308716},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmc.2023.3315120","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2023.3315120","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Mobile Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1941773203","display_name":null,"funder_award_id":"IIS-2107304","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G3039347803","display_name":null,"funder_award_id":"CMMI-1653435","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"},{"id":"https://openalex.org/G5429545050","display_name":null,"funder_award_id":"1006977","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8913687060","display_name":null,"funder_award_id":"DMS-1953686","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"}],"funders":[{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W205960364","https://openalex.org/W1542941925","https://openalex.org/W1669104078","https://openalex.org/W2057510529","https://openalex.org/W2098441552","https://openalex.org/W2120846115","https://openalex.org/W2132688592","https://openalex.org/W2164278908","https://openalex.org/W2170400507","https://openalex.org/W2948127421","https://openalex.org/W2951590735","https://openalex.org/W2963073480","https://openalex.org/W2963419911","https://openalex.org/W2964723139","https://openalex.org/W2969771825","https://openalex.org/W2991046523","https://openalex.org/W3027095131","https://openalex.org/W3038915804","https://openalex.org/W3081631809","https://openalex.org/W4234992901","https://openalex.org/W4242766606","https://openalex.org/W4252284432","https://openalex.org/W4300448178","https://openalex.org/W4301501993","https://openalex.org/W4381616632","https://openalex.org/W6631137000","https://openalex.org/W6678168664","https://openalex.org/W6680096503","https://openalex.org/W6681235875","https://openalex.org/W6682855959","https://openalex.org/W6683204974","https://openalex.org/W6683841269","https://openalex.org/W6728155968","https://openalex.org/W6738546315","https://openalex.org/W6757058172","https://openalex.org/W6762879277","https://openalex.org/W6780264914","https://openalex.org/W6780386840","https://openalex.org/W6796348162","https://openalex.org/W6796718340"],"related_works":["https://openalex.org/W2346864368","https://openalex.org/W2161212821","https://openalex.org/W2357960062","https://openalex.org/W1502903923","https://openalex.org/W2375154938","https://openalex.org/W3004147454","https://openalex.org/W3097094777","https://openalex.org/W4318969523","https://openalex.org/W2195500058","https://openalex.org/W2624966253"],"abstract_inverted_index":{"Complex":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"tasks":[4],"often":[5],"require":[6],"a":[7,11,28,58,77,85,105,122,127],"divide-and-conquer":[8],"approach,":[9],"where":[10,32,126],"large":[12],"task":[13,142],"is":[14,74,82],"divided":[15],"into":[16,116],"pieces":[17],"and":[18,45,64,136,160],"solved":[19],"by":[20],"individual":[21,33,117,131],"agents.":[22],"In":[23],"this":[24,155],"paper,":[25],"we":[26,103],"study":[27],"teamwork":[29,124,156],"RL":[30],"setting":[31],"agents":[34,132],"make":[35],"decisions":[36],"on":[37,145],"disjoint":[38],"subsets":[39],"(blocks)":[40],"of":[41,80,88,100,154],"the":[42,52,89,97,113,152,168,180],"state":[43,148],"space":[44],"have":[46],"private":[47],"interests":[48],"(reward":[49],"functions),":[50],"while":[51,185],"entire":[53],"team":[54,61,71,128,175],"aims":[55],"to":[56,68,111,167,177],"maximize":[57],"general":[59],"long-term":[60],"utility":[62],"function":[63,87],"may":[65],"be":[66],"subject":[67],"constraints.":[69],"This":[70,120,172],"utility,":[72],"which":[73],"not":[75],"necessarily":[76],"cumulative":[78],"sum":[79],"rewards,":[81],"modeled":[83],"as":[84],"nonlinear":[86],"team's":[90,169],"joint":[91,170],"state-action":[92],"occupancy":[93],"distribution.":[94],"By":[95],"leveraging":[96],"inherent":[98],"duality":[99],"policy":[101,108,157,184],"optimization,":[102],"propose":[104],"min-max":[106],"multi-block":[107],"optimization":[109,158],"framework":[110],"decompose":[112],"overall":[114],"problem":[115],"local":[118,141,147,188],"tasks.":[119],"enables":[121],"federated":[123],"mechanism":[125,159,173],"lead":[129],"coordinates":[130],"via":[133],"reward":[134],"shaping,":[135],"each":[137],"agent":[138],"solves":[139],"its":[140,146],"defined":[143],"only":[144],"subset.":[149],"We":[150],"analyze":[151],"convergence":[153,165],"establish":[161],"an":[162],"<inline-formula><tex-math":[163],"notation=\"LaTeX\">$O(1/T)$</tex-math></inline-formula>":[164],"rate":[166],"optimum.":[171],"allows":[174],"members":[176],"jointly":[178],"find":[179],"global":[181],"socially":[182],"optimal":[183],"keeping":[186],"their":[187],"privacy.":[189]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}