{"id":"https://openalex.org/W4286306503","doi":"https://doi.org/10.23919/ascc56756.2022.9828324","title":"Control using Q-learning for networked coordination games","display_name":"Control using Q-learning for networked coordination games","publication_year":2022,"publication_date":"2022-05-04","ids":{"openalex":"https://openalex.org/W4286306503","doi":"https://doi.org/10.23919/ascc56756.2022.9828324"},"language":"en","primary_location":{"id":"doi:10.23919/ascc56756.2022.9828324","is_oa":false,"landing_page_url":"https://doi.org/10.23919/ascc56756.2022.9828324","pdf_url":null,"source":{"id":"https://openalex.org/S4363607827","display_name":"2022 13th Asian Control Conference (ASCC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 13th Asian Control Conference (ASCC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.rug.nl/en/publications/3e59e0ce-f3ee-40a4-821d-2be8ab8739ed","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004366934","display_name":"Bo Jin","orcid":"https://orcid.org/0000-0001-9255-5772"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Bo Jin","raw_affiliation_strings":["University of Groningen,ENTEG, Faculty of Science and Engineering,Groningen,The Netherlands","ENTEG, Faculty of Science and Engineering, University of Groningen, Groningen, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Groningen,ENTEG, Faculty of Science and Engineering,Groningen,The Netherlands","institution_ids":["https://openalex.org/I169381384"]},{"raw_affiliation_string":"ENTEG, Faculty of Science and Engineering, University of Groningen, Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021403340","display_name":"Ming Cao","orcid":"https://orcid.org/0000-0001-5472-562X"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ming Cao","raw_affiliation_strings":["University of Groningen,ENTEG, Faculty of Science and Engineering,Groningen,The Netherlands","ENTEG, Faculty of Science and Engineering, University of Groningen, Groningen, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Groningen,ENTEG, Faculty of Science and Engineering,Groningen,The Netherlands","institution_ids":["https://openalex.org/I169381384"]},{"raw_affiliation_string":"ENTEG, Faculty of Science and Engineering, University of Groningen, Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I169381384"],"apc_list":null,"apc_paid":null,"fwci":0.1038,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.27134906,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"941","last_page":"946"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9937000274658203,"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":0.9937000274658203,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9829999804496765,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9509999752044678,"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/computer-science","display_name":"Computer science","score":0.6135194301605225},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5858133435249329},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.46348410844802856},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3536760210990906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2829434275627136},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.1987747848033905}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6135194301605225},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5858133435249329},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.46348410844802856},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3536760210990906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2829434275627136},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.1987747848033905}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.23919/ascc56756.2022.9828324","is_oa":false,"landing_page_url":"https://doi.org/10.23919/ascc56756.2022.9828324","pdf_url":null,"source":{"id":"https://openalex.org/S4363607827","display_name":"2022 13th Asian Control Conference (ASCC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 13th Asian Control Conference (ASCC)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.rug.nl:openaire/3e59e0ce-f3ee-40a4-821d-2be8ab8739ed","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/3e59e0ce-f3ee-40a4-821d-2be8ab8739ed","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Jin, B & Cao, M 2022, Control using Q-learning for networked coordination games. in ASCC 2022 - 2022 13th Asian Control Conference, Proceedings. ASCC 2022 - 2022 13th Asian Control Conference, Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 941-946, 13th Asian Control Conference, ASCC 2022, Jeju, Korea, Republic of, 04/05/2022. https://doi.org/10.23919/ASCC56756.2022.9828324","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:pure.rug.nl:openaire_cris_publications/3e59e0ce-f3ee-40a4-821d-2be8ab8739ed","is_oa":true,"landing_page_url":"https://hdl.handle.net/11370/3e59e0ce-f3ee-40a4-821d-2be8ab8739ed","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"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":"Jin, B & Cao, M 2022, Control using Q-learning for networked coordination games. in ASCC 2022 - 2022 13th Asian Control Conference, Proceedings. ASCC 2022 - 2022 13th Asian Control Conference, Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 941-946, 13th Asian Control Conference, ASCC 2022, Jeju, Korea, Republic of, 04/05/2022. https://doi.org/10.23919/ASCC56756.2022.9828324","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:pure.rug.nl:openaire/3e59e0ce-f3ee-40a4-821d-2be8ab8739ed","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/3e59e0ce-f3ee-40a4-821d-2be8ab8739ed","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Jin, B & Cao, M 2022, Control using Q-learning for networked coordination games. in ASCC 2022 - 2022 13th Asian Control Conference, Proceedings. ASCC 2022 - 2022 13th Asian Control Conference, Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 941-946, 13th Asian Control Conference, ASCC 2022, Jeju, Korea, Republic of, 04/05/2022. https://doi.org/10.23919/ASCC56756.2022.9828324","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8100000023841858}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1591723504","https://openalex.org/W2062873261","https://openalex.org/W2076465870","https://openalex.org/W2104834796","https://openalex.org/W2159047277","https://openalex.org/W2166155636","https://openalex.org/W2344776626","https://openalex.org/W2540486267","https://openalex.org/W2806261144","https://openalex.org/W2915158806","https://openalex.org/W2963618387","https://openalex.org/W3035602106","https://openalex.org/W3155303979","https://openalex.org/W4233696721","https://openalex.org/W4238955406","https://openalex.org/W4240902844"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"We":[0,94,127],"consider":[1],"a":[2,10,38,52,63,100,108],"population":[3,23,60],"of":[4,28,40],"individuals":[5,13],"playing":[6],"coordination":[7,18,149],"games":[8],"on":[9],"network,":[11],"where":[12],"may":[14],"differ":[15],"in":[16],"their":[17],"biases":[19,150],"and":[20,48,85,104,132],"thus":[21,49],"the":[22,29,32,58,121,124,147,152],"is":[24,70],"heterogeneous.":[25],"While":[26],"most":[27],"agents":[30,81],"follow":[31],"standard":[33],"asynchronous":[34],"best-response":[35],"game-play":[36],"strategy,":[37],"group":[39],"agents,":[41,44],"called":[42],"\"targeted\"":[43],"are":[45,151,155],"under":[46],"control":[47,68,97],"can":[50,138],"use":[51],"different":[53],"strategy":[54],"designed":[55],"to":[56,61,72,116,119,123,141],"guide":[57],"overall":[59],"achieve":[62],"pre-specified":[64],"collective":[65],"state.":[66],"The":[67],"objective":[69],"then":[71,133],"find":[73],"an":[74],"optimal":[75,125],"policy":[76],"that":[77,136],"specifies":[78],"which":[79],"targeted":[80],"should":[82,89],"be":[83,117,139,142],"forced":[84],"what":[86],"strategies":[87],"they":[88],"employ":[90],"at":[91],"each":[92],"time.":[93],"formulate":[95],"this":[96,129],"problem":[98],"as":[99],"Markov":[101],"decision":[102],"process":[103],"solve":[105],"it":[106,137],"using":[107],"Q-learning":[109],"algorithm.":[110],"An":[111],"ergodicity":[112,130],"condition":[113,131],"turns":[114],"out":[115],"key":[118],"guarantee":[120],"convergence":[122],"Q-value.":[126],"interpret":[128],"further":[134],"prove":[135],"simplified":[140],"checked":[143],"efficiently":[144],"when":[145],"all":[146,156,159],"individuals\u2019":[148],"same":[153],"or":[154,158],"below":[157],"above":[160],"1/2.":[161]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}