{"id":"https://openalex.org/W3172113494","doi":"https://doi.org/10.1007/s10458-021-09506-w","title":"Analysing factorizations of action-value networks for cooperative multi-agent reinforcement learning","display_name":"Analysing factorizations of action-value networks for cooperative multi-agent reinforcement learning","publication_year":2021,"publication_date":"2021-06-07","ids":{"openalex":"https://openalex.org/W3172113494","doi":"https://doi.org/10.1007/s10458-021-09506-w","mag":"3172113494","pmid":"https://pubmed.ncbi.nlm.nih.gov/34720685"},"language":"en","primary_location":{"id":"doi:10.1007/s10458-021-09506-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10458-021-09506-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10458-021-09506-w.pdf","source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10458-021-09506-w.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068772408","display_name":"Jacopo Castellini","orcid":null},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jacopo Castellini","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, Liverpool, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Liverpool, UK","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009493909","display_name":"Frans A. Oliehoek","orcid":"https://orcid.org/0000-0003-4372-5055"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Frans A. Oliehoek","raw_affiliation_strings":["Interactive Intelligence Group, Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interactive Intelligence Group, Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084692264","display_name":"Rahul Savani","orcid":"https://orcid.org/0000-0003-1262-7831"},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rahul Savani","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, Liverpool, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Liverpool, UK","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056879203","display_name":"Shimon Whiteson","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shimon Whiteson","raw_affiliation_strings":["Department of Computer Science, University of Oxford, Oxford, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Oxford, Oxford, UK","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5068772408"],"corresponding_institution_ids":["https://openalex.org/I146655781"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.4197,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68762832,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"35","issue":"2","first_page":"25","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.939300000667572,"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":0.872153639793396},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7494262456893921},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.5621746182441711},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5591875314712524},{"id":"https://openalex.org/keywords/simplicity","display_name":"Simplicity","score":0.4695247709751129},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.46697020530700684},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.44287368655204773},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.42819416522979736},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.29733285307884216}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.872153639793396},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7494262456893921},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.5621746182441711},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5591875314712524},{"id":"https://openalex.org/C2776372474","wikidata":"https://www.wikidata.org/wiki/Q508291","display_name":"Simplicity","level":2,"score":0.4695247709751129},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.46697020530700684},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.44287368655204773},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.42819416522979736},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29733285307884216},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1007/s10458-021-09506-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10458-021-09506-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10458-021-09506-w.pdf","source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},{"id":"pmid:34720685","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34720685","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous agents and multi-agent systems","raw_type":null},{"id":"pmh:oai:arXiv.org:1902.07497","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.07497","pdf_url":"https://arxiv.org/pdf/1902.07497","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:tudelft.nl:uuid:49288083-b5f9-431f-8371-47dc4b789134","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:49288083-b5f9-431f-8371-47dc4b789134","pdf_url":"http://resolver.tudelft.nl/uuid:49288083-b5f9-431f-8371-47dc4b789134","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"},{"id":"pmh:oai:europepmc.org:7442719","is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC8550438","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:6906d9db-e09b-494c-b1ee-cb1a21c7de9c","is_oa":true,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:6906d9db-e09b-494c-b1ee-cb1a21c7de9c","pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symplectic Elements","raw_type":"Journal article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8550438","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8550438","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Auton Agent Multi Agent Syst","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1007/s10458-021-09506-w","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10458-021-09506-w","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10458-021-09506-w.pdf","source":{"id":"https://openalex.org/S5405189","display_name":"Autonomous Agents and Multi-Agent Systems","issn_l":"1387-2532","issn":["1387-2532","1573-7454"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Agents and Multi-Agent Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","score":0.46000000834465027,"display_name":"Partnerships for the goals"}],"awards":[{"id":"https://openalex.org/G1073366937","display_name":"Influence-based Decision-making in Uncertain Environments","funder_award_id":"758824","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G1710232961","display_name":null,"funder_award_id":"EP/R001227/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G221468001","display_name":null,"funder_award_id":"First Grant EP/R001227/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7072063281","display_name":"Learning to Efficiently Plan in Flexible Distributed Organizations","funder_award_id":"EP/R001227/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3172113494.pdf","grobid_xml":"https://content.openalex.org/works/W3172113494.grobid-xml"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W329015778","https://openalex.org/W1542941925","https://openalex.org/W1557517019","https://openalex.org/W1641379095","https://openalex.org/W1731081199","https://openalex.org/W2004677728","https://openalex.org/W2014852613","https://openalex.org/W2026662445","https://openalex.org/W2064675550","https://openalex.org/W2065090389","https://openalex.org/W2095701584","https://openalex.org/W2096145798","https://openalex.org/W2096622112","https://openalex.org/W2099618002","https://openalex.org/W2104602264","https://openalex.org/W2109100253","https://openalex.org/W2110906765","https://openalex.org/W2118318536","https://openalex.org/W2134779831","https://openalex.org/W2139510727","https://openalex.org/W2145339207","https://openalex.org/W2156060009","https://openalex.org/W2170400507","https://openalex.org/W2173248099","https://openalex.org/W2260756217","https://openalex.org/W2292533394","https://openalex.org/W2395575420","https://openalex.org/W2400387077","https://openalex.org/W2402402867","https://openalex.org/W2466211196","https://openalex.org/W2592798481","https://openalex.org/W2594794854","https://openalex.org/W2617547828","https://openalex.org/W2623431351","https://openalex.org/W2683628546","https://openalex.org/W2734878594","https://openalex.org/W2768629321","https://openalex.org/W2794643322","https://openalex.org/W2807741983","https://openalex.org/W2932081708","https://openalex.org/W2945043829","https://openalex.org/W2946606218","https://openalex.org/W2949201811","https://openalex.org/W2949963774","https://openalex.org/W2962938168","https://openalex.org/W2963485523","https://openalex.org/W2963658727","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2970514967","https://openalex.org/W2989068617","https://openalex.org/W3035250588","https://openalex.org/W3103882218","https://openalex.org/W6676468133","https://openalex.org/W6677834374","https://openalex.org/W6680096503","https://openalex.org/W6767327128","https://openalex.org/W6779713346","https://openalex.org/W7039511152"],"related_works":["https://openalex.org/W2368019753","https://openalex.org/W2333930193","https://openalex.org/W2737356002","https://openalex.org/W2246241526","https://openalex.org/W2374150061","https://openalex.org/W4301122218","https://openalex.org/W2081340182","https://openalex.org/W2369703001","https://openalex.org/W2372323577","https://openalex.org/W2494202692"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2],"seen":[3],"the":[4,21,30,46,58,79,85,97,114,143,151,161],"application":[5],"of":[6,23,61,68,78,93,99,113,160],"deep":[7],"reinforcement":[8],"learning":[9,42,59],"techniques":[10],"to":[11,44],"cooperative":[12],"multi-agent":[13,86],"systems,":[14],"with":[15],"great":[16],"empirical":[17],"success.":[18],"However,":[19],"given":[20],"lack":[22,98],"theoretical":[24],"insight,":[25],"it":[26],"remains":[27],"unclear":[28],"what":[29],"employed":[31],"neural":[32],"networks":[33],"are":[34],"learning,":[35],"or":[36,96,163],"how":[37,137],"we":[38,55],"should":[39],"enhance":[40],"their":[41,72],"power":[43,60],"address":[45],"problems":[47,81],"on":[48,65,118],"which":[49],"they":[50],"fail.":[51],"In":[52],"this":[53],"work,":[54],"empirically":[56],"investigate":[57],"various":[62,139],"network":[63],"architectures":[64],"a":[66],"series":[67],"one-shot":[69],"games.":[70],"Despite":[71],"simplicity,":[73],"these":[74],"games":[75],"capture":[76],"many":[77],"crucial":[80],"that":[82,153],"arise":[83],"in":[84,108],"setting,":[87],"such":[88],"as":[89],"an":[90,100],"exponential":[91],"number":[92],"joint":[94],"actions":[95],"explicit":[101],"coordination":[102,166],"mechanism.":[103],"Our":[104],"results":[105],"extend":[106],"those":[107],"Castellini":[109],"et":[110],"al.":[111],"(Proceedings":[112],"18th":[115],"International":[116],"Conference":[117],"Autonomous":[119,127],"Agents":[120,128],"and":[121,129,135,147],"MultiAgent":[122],"Systems,":[123,131],"AAMAS'19.International":[124],"Foundation":[125],"for":[126],"Multiagent":[130],"pp":[132],"1862-1864,":[133],"2019)":[134],"quantify":[136],"well":[138],"approaches":[140],"can":[141,154],"represent":[142],"requisite":[144],"value":[145],"functions,":[146],"help":[148],"us":[149],"identify":[150],"reasons":[152],"impede":[155],"good":[156],"performance,":[157],"like":[158],"sparsity":[159],"values":[162],"too":[164],"tight":[165],"requirements.":[167]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}