{"id":"https://openalex.org/W2807741983","doi":"https://doi.org/10.65109/jsrc7365","title":"Value-Decomposition Networks For Cooperative Multi-Agent Learning Based On Team Reward","display_name":"Value-Decomposition Networks For Cooperative Multi-Agent Learning Based On Team Reward","publication_year":2018,"publication_date":"2018-07-09","ids":{"openalex":"https://openalex.org/W2807741983","doi":"https://doi.org/10.65109/jsrc7365","mag":"2807741983"},"language":"en","primary_location":{"id":"doi:10.65109/jsrc7365","doi":"https://doi.org/10.65109/jsrc7365","is_oa":false,"landing_page_url":"https://doi.org/10.65109/jsrc7365","pdf_url":null,"source":{"id":"https://openalex.org/S4306417597","display_name":"Adaptive Agents and Multi-Agents Systems","issn_l":"1548-8403","issn":["1548-8403"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Joint Conference on Autonomous Agents and Multiagent Systems","raw_type":"proceedings-article"},"volume":null,"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/A5046100176","display_name":"Peter Sunehag","orcid":null,"observed_orcids":[]},"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":"Peter Sunehag","raw_affiliation_strings":["DeepMind Technologies, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind Technologies, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031943811","display_name":"Guy Lever","orcid":"https://orcid.org/0000-0001-9551-1839","observed_orcids":["https://orcid.org/0000-0001-9551-1839"]},"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":"Guy Lever","raw_affiliation_strings":["DeepMind Technologies, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind Technologies, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040179074","display_name":"Audr\u016bnas Gruslys","orcid":null,"observed_orcids":[]},"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":"Audrunas Gruslys","raw_affiliation_strings":["DeepMind Technologies, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind Technologies, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064372346","display_name":"Wojciech Marian Czarnecki","orcid":"https://orcid.org/0000-0002-2641-9542","observed_orcids":["https://orcid.org/0000-0002-2641-9542"]},"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":"Wojciech Marian Czarnecki","raw_affiliation_strings":["DeepMind Technologies, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind Technologies, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074826751","display_name":"Vin\u00edcius Zambaldi","orcid":null,"observed_orcids":[]},"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":"Vinicius Zambaldi","raw_affiliation_strings":["DeepMind Technologies, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind Technologies, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004153109","display_name":"Max Jaderberg","orcid":"https://orcid.org/0000-0002-9033-2695","observed_orcids":["https://orcid.org/0000-0002-9033-2695"]},"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":"Max Jaderberg","raw_affiliation_strings":["DeepMind Technologies, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind Technologies, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049659586","display_name":"Marc Lanctot","orcid":null,"observed_orcids":[]},"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":"Marc Lanctot","raw_affiliation_strings":["DeepMind Technologies, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind Technologies, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033070893","display_name":"Nicolas Sonnerat","orcid":null,"observed_orcids":[]},"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":"Nicolas Sonnerat","raw_affiliation_strings":["DeepMind Technologies, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind Technologies, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054808675","display_name":"Joel Z. Leibo","orcid":"https://orcid.org/0000-0002-3153-916X","observed_orcids":["https://orcid.org/0000-0002-3153-916X"]},"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":"Joel Z. Leibo","raw_affiliation_strings":["DeepMind Technologies, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind Technologies, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008547992","display_name":"Karl Tuyls","orcid":"https://orcid.org/0000-0001-7929-1944","observed_orcids":["https://orcid.org/0000-0001-7929-1944","https://orcid.org/0000-0001-6346-4564"]},"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":"Karl Tuyls","raw_affiliation_strings":["DeepMind Technologies, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind Technologies, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051619646","display_name":"Thore Graepel","orcid":"https://orcid.org/0000-0003-3957-0310","observed_orcids":["https://orcid.org/0000-0003-3957-0310"]},"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":"Thore Graepel","raw_affiliation_strings":["DeepMind Technologies, London, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind Technologies, London, United Kingdom","institution_ids":["https://openalex.org/I4210090411"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210090411"],"apc_list":null,"apc_paid":null,"fwci":22.7733,"has_fulltext":false,"cited_by_count":833,"citation_normalized_percentile":{"value":0.99508146,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2085","last_page":"2087"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.0,"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":0.0,"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/value-decomposition-networks","display_name":"value decomposition networks","score":0.9309999942779541},{"id":"https://openalex.org/keywords/cooperative-multi-agent-reinforcement-learning","display_name":"cooperative multi-agent reinforcement learning","score":0.9860000014305115},{"id":"https://openalex.org/keywords/team-incentives","display_name":"team incentives","score":0.8899999856948853},{"id":"https://openalex.org/keywords/partial-observability","display_name":"partial observability","score":0.9890000224113464},{"id":"https://openalex.org/keywords/value-function-decomposition","display_name":"value function decomposition","score":0.6259999871253967},{"id":"https://openalex.org/keywords/centralized-training-with-decentralized-execution","display_name":"centralized training decentralized execution","score":0.5860000252723694}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8412624597549438},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.7352725863456726},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7110810875892639},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.5810263752937317},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5608798861503601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5538236498832703},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5173208713531494},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.5106855034828186},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4749622046947479},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4532207250595093},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3649415373802185},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33349475264549255},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14142298698425293},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.65109/jsrc7365","doi":"https://doi.org/10.65109/jsrc7365","is_oa":false,"landing_page_url":"https://doi.org/10.65109/jsrc7365","pdf_url":null,"source":{"id":"https://openalex.org/S4306417597","display_name":"Adaptive Agents and Multi-Agents Systems","issn_l":"1548-8403","issn":["1548-8403"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Joint Conference on Autonomous Agents and Multiagent Systems","raw_type":"proceedings-article"},{"id":"mag:2807741983","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/atal/aamas2018.html#SunehagLGCZJLSL18","pdf_url":null,"source":{"id":"https://openalex.org/S4306417597","display_name":"Adaptive Agents and Multi-Agents Systems","issn_l":"1548-8403","issn":["1548-8403"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Adaptive Agents and Multi-Agents Systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1503017385","https://openalex.org/W1518858799","https://openalex.org/W1579184372","https://openalex.org/W1639167632","https://openalex.org/W1969302761","https://openalex.org/W2099618002","https://openalex.org/W2104602264","https://openalex.org/W2104689655","https://openalex.org/W2107544712","https://openalex.org/W2136202932","https://openalex.org/W2137647991","https://openalex.org/W2189058185","https://openalex.org/W2402402867","https://openalex.org/W2410877381","https://openalex.org/W2572491855","https://openalex.org/W2594794854","https://openalex.org/W2606342131","https://openalex.org/W2617547828","https://openalex.org/W2747213132","https://openalex.org/W3093287223","https://openalex.org/W6884722281","https://openalex.org/W7124214921"],"related_works":["https://openalex.org/W7124322579","https://openalex.org/W2980784261","https://openalex.org/W3176501542","https://openalex.org/W3160712241","https://openalex.org/W7124263057","https://openalex.org/W3172113494","https://openalex.org/W3036329728","https://openalex.org/W952364276","https://openalex.org/W4391020470","https://openalex.org/W7124248611"],"abstract_inverted_index":{"We":[0,61],"study":[1],"the":[2,24,33,41,51,79],"problem":[3,42],"of":[4,17,23,43],"cooperative":[5],"multi-agent":[6],"reinforcement":[7],"learning":[8,18],"with":[9,69],"a":[10,47,70],"single":[11],"joint":[12],"reward":[13],"signal.":[14],"This":[15],"class":[16],"problems":[19,64],"is":[20],"difficult":[21],"because":[22],"often":[25],"large":[26],"combined":[27],"action":[28],"and":[29,36,46],"observation":[30],"spaces.":[31],"In":[32],"fully":[34],"centralized":[35],"decentralized":[37],"approaches,":[38],"we":[39,49],"find":[40],"spurious":[44],"rewards":[45],"phenomenon":[48],"call":[50],"\"lazy":[52],"agent''":[53],"problem,":[54],"which":[55,75],"arises":[56],"due":[57],"to":[58,77],"partial":[59],"observability.":[60],"address":[62],"these":[63],"by":[65],"training":[66],"individual":[67],"agents":[68],"novel":[71],"value-decomposition":[72],"network":[73],"architecture,":[74],"learns":[76],"decompose":[78],"team":[80],"value":[81,85],"function":[82],"into":[83],"agent-wise":[84],"functions.":[86]},"counts_by_year":[{"year":2026,"cited_by_count":186},{"year":2025,"cited_by_count":88},{"year":2024,"cited_by_count":123},{"year":2023,"cited_by_count":111},{"year":2022,"cited_by_count":99},{"year":2021,"cited_by_count":129},{"year":2020,"cited_by_count":66},{"year":2019,"cited_by_count":28},{"year":2018,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2018-06-21T00:00:00"}