{"id":"https://openalex.org/W2804327232","doi":null,"title":"Learning to Coordinate with Coordination Graphs in Repeated Single-Stage Multi-Agent Decision Problems","display_name":"Learning to Coordinate with Coordination Graphs in Repeated Single-Stage Multi-Agent Decision Problems","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2804327232","mag":"2804327232"},"language":"en","primary_location":{"id":"pmh:oai:vubissmart:VUBISSMART:2000:1615","doi":null,"is_oa":true,"landing_page_url":"https://biblio.vub.ac.be/vubir/learning-to-coordinate-with-coordination-graphs-in-repeated-singlestage-multiagent-decision-problems(f4e3e291-6300-4c2a-a5b4-101d65ef04b3).html","pdf_url":"http://proceedings.mlr.press/v80/bargiacchi18a/bargiacchi18a.pdf","source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"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":"article"},"volume":null,"type":"article","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://proceedings.mlr.press/v80/bargiacchi18a/bargiacchi18a.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047553332","display_name":"Eugenio Bargiacchi","orcid":"https://orcid.org/0000-0003-2824-7200","observed_orcids":["https://orcid.org/0000-0003-2824-7200"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bargiacchi, Eugenio","raw_affiliation_strings":["Informatics and Applied Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Informatics and Applied Informatics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028997809","display_name":"Timothy Verstraeten","orcid":"https://orcid.org/0000-0003-3036-617X","observed_orcids":["https://orcid.org/0000-0003-3036-617X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Verstraeten, Timothy","raw_affiliation_strings":["Faculty of Sciences and Bioengineering Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Sciences and Bioengineering Sciences","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081436755","display_name":"Diederik M. Roijers","orcid":"https://orcid.org/0000-0002-2825-2491","observed_orcids":["https://orcid.org/0000-0002-2825-2491"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roiiers, Diederik M.","raw_affiliation_strings":["Informatics and Applied Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Informatics and Applied Informatics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064553018","display_name":"Ann Now\u00e9","orcid":"https://orcid.org/0000-0001-6346-4564","observed_orcids":["https://orcid.org/0000-0001-6346-4564"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nowe, Ann","raw_affiliation_strings":["Electronics and Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electronics and Informatics","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033135596","display_name":"Hado P. van Hasselt","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":"Van Hasselt, Hado","raw_affiliation_strings":["DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125574748","display_name":"Jennifer Dy","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dy, Jennifer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5151036995","display_name":"Andreas Krause","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Krause, Andreas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.0189,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.9155505,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9994999766349792,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.0005000000237487257,"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/T12072","display_name":"Machine Learning and Algorithms","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"}}],"keywords":[{"id":"https://openalex.org/keywords/multiagent-coordination","display_name":"multi-agent coordination","score":0.8330000042915344},{"id":"https://openalex.org/keywords/coordination-graphs","display_name":"coordination graphs","score":0.968999981880188},{"id":"https://openalex.org/keywords/multi-agent-multi-armed-bandits","display_name":"multi-agent multi-armed bandit","score":0.9589999914169312},{"id":"https://openalex.org/keywords/regret-bounds","display_name":"regret bounds","score":0.8209999799728394},{"id":"https://openalex.org/keywords/multi-agent-reinforcement-learning","display_name":"multi-agent reinforcement learning","score":0.7239999771118164},{"id":"https://openalex.org/keywords/combinatorial-multi-armed-bandit","display_name":"combinatorial bandits","score":0.8149999976158142}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.844353973865509},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.687177300453186},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6404845714569092},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.5462732315063477},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4802111089229584},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.45916658639907837},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.4376481771469116},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4341531991958618},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4285309314727783},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.41580989956855774},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.41203010082244873},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34473055601119995},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1989516317844391},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"pmh:oai:vubissmart:VUBISSMART:2000:1615","doi":null,"is_oa":true,"landing_page_url":"https://biblio.vub.ac.be/vubir/learning-to-coordinate-with-coordination-graphs-in-repeated-singlestage-multiagent-decision-problems(f4e3e291-6300-4c2a-a5b4-101d65ef04b3).html","pdf_url":"http://proceedings.mlr.press/v80/bargiacchi18a/bargiacchi18a.pdf","source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"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":"article"},{"id":"pmh:oai:research.vu.nl:openaire_cris_publications/c23270d8-4751-4b4d-b08b-0e567e60df8e","doi":null,"is_oa":false,"landing_page_url":"https://research.vu.nl/en/publications/c23270d8-4751-4b4d-b08b-0e567e60df8e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bargiacchi , E , Verstraeten , T , Roijers , D M , Now\u00e9 , A & Van Hasselt , H 2018 , ' Learning to Coordinate with Coordination Graphs in Repeated Single-Stage Multi-Agent Decision Problems ' , Proceedings of Machine Learning Research , vol. 80 , pp. 482-490 .","raw_type":"article"},{"id":"pmh:oai:research.vu.nl:openaire_cris_publications/d0eb6081-bd3e-4d66-971a-671c7a8cb927","doi":null,"is_oa":false,"landing_page_url":"https://research.vu.nl/en/publications/d0eb6081-bd3e-4d66-971a-671c7a8cb927","pdf_url":null,"source":{"id":"https://openalex.org/S4306401107","display_name":"VU Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I865915315","host_organization_name":"Vrije Universiteit Amsterdam","host_organization_lineage":["https://openalex.org/I865915315"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bargiacchi, E, Verstraeten, T, Roiiers, D M, Nowe, A & Van Hasselt, H 2018, Learning to coordinate with coordination graphs in repeated single-stage multi-agent decision problems. in J Dy & A Krause (eds), 35th International Conference on Machine Learning, ICML 2018. vol. 2, International Machine Learning Society (IMLS), pp. 810-818, 35th International Conference on Machine Learning, ICML 2018, Stockholm, Sweden, 10/07/18.","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:1616","doi":null,"is_oa":false,"landing_page_url":"https://biblio.vub.ac.be/vubir/learning-to-coordinate-with-coordination-graphs-in-repeated-singlestage-multiagent-decision-problems(b813d8ba-512c-4025-8cca-7d077a65c917).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"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":"article"},{"id":"pmh:vu:oai:research.vu.nl:publications/c23270d8-4751-4b4d-b08b-0e567e60df8e","doi":null,"is_oa":false,"landing_page_url":"https://research.vu.nl/en/publications/c23270d8-4751-4b4d-b08b-0e567e60df8e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning, 10-15 July 2018, Stockholmsm\u00e4ssan, Stockholm Sweden: Proceedings of the 35th International Conference on Machine Learning, ICML 2018, 482 - 490","raw_type":"info:eu-repo/semantics/conferencepaper"},{"id":"pmh:vu:oai:research.vu.nl:publications/d0eb6081-bd3e-4d66-971a-671c7a8cb927","doi":null,"is_oa":false,"landing_page_url":"https://research.vu.nl/en/publications/d0eb6081-bd3e-4d66-971a-671c7a8cb927","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"35th International Conference on Machine Learning, ICML 2018, 2, 810 - 818","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":{"id":"pmh:oai:vubissmart:VUBISSMART:2000:1615","doi":null,"is_oa":true,"landing_page_url":"https://biblio.vub.ac.be/vubir/learning-to-coordinate-with-coordination-graphs-in-repeated-singlestage-multiagent-decision-problems(f4e3e291-6300-4c2a-a5b4-101d65ef04b3).html","pdf_url":"http://proceedings.mlr.press/v80/bargiacchi18a/bargiacchi18a.pdf","source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"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":"article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320313460","display_name":"Agentschap Innoveren en Ondernemen","ror":"https://ror.org/032xdry56"},{"id":"https://openalex.org/F4320321730","display_name":"Fonds Wetenschappelijk Onderzoek","ror":"https://ror.org/03qtxy027"},{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2804327232.pdf","grobid_xml":"https://content.openalex.org/works/W2804327232.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W33871791","https://openalex.org/W1911551976","https://openalex.org/W2039522160","https://openalex.org/W2110906765","https://openalex.org/W2134779831","https://openalex.org/W2153066670","https://openalex.org/W2153427071","https://openalex.org/W2168405694","https://openalex.org/W2481147314","https://openalex.org/W2527362732","https://openalex.org/W2545853213","https://openalex.org/W2601109552","https://openalex.org/W2606733399","https://openalex.org/W2951667255"],"related_works":["https://openalex.org/W3109014439","https://openalex.org/W7111563094","https://openalex.org/W3017252927","https://openalex.org/W11035765","https://openalex.org/W7096028525","https://openalex.org/W3197294986","https://openalex.org/W4388117515","https://openalex.org/W4402263747","https://openalex.org/W3168414797","https://openalex.org/W7047436498"],"abstract_inverted_index":{"Learning":[0],"to":[1,15,17,72,97],"coordinate":[2,18],"between":[3,26],"multiple":[4],"agents":[5],"is":[6,19,78],"an":[7],"important":[8],"problem":[9],"in":[10,33,42,80,89],"many":[11],"reinforcement":[12],"learning":[13,16,32,120],"problems.Key":[14],"exploiting":[20],"loose":[21,67],"couplings,":[22,68],"i.e.,":[23],"conditional":[24],"independences":[25],"agents.In":[27],"this":[28],"paper":[29],"we":[30],"study":[31],"repeated":[34],"fully":[35],"cooperative":[36,99],"games,":[37],"multi-agent":[38,55],"multi-armed":[39],"bandits":[40],"(MAMABs),":[41],"which":[43,69],"the":[44,81,90],"expected":[45],"rewards":[46],"can":[47],"be":[48],"expressed":[49],"as":[50],"a":[51,60,74,102,115],"coordination":[52],"graph.We":[53],"propose":[54],"upper":[56],"confidence":[57],"exploration":[58],"(MAUCE),":[59],"new":[61],"algorithm":[62],"for":[63,123],"MAMABs":[64],"that":[65,77,109],"exploits":[66],"enables":[70],"us":[71],"prove":[73],"regret":[75],"bound":[76],"logarithmic":[79],"number":[82,91],"of":[83,92,117],"arm":[84],"pulls":[85],"and":[86,101,107],"only":[87],"linear":[88],"agents.We":[93],"empirically":[94],"compare":[95],"MAUCE":[96],"sparse":[98],"Q-learning,":[100],"state-of-the-art":[103],"combinatorial":[104],"bandit":[105],"approach,":[106],"show":[108],"it":[110],"performs":[111],"much":[112],"better":[113],"on":[114],"variety":[116],"settings,":[118],"including":[119],"control":[121],"policies":[122],"wind":[124],"farms.":[125]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":3}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2018-06-01T00:00:00"}