{"id":"https://openalex.org/W4387188098","doi":"https://doi.org/10.3233/aic-220305","title":"Transferring experiences in k-nearest neighbors based multiagent reinforcement learning: an application to traffic signal control","display_name":"Transferring experiences in k-nearest neighbors based multiagent reinforcement learning: an application to traffic signal control","publication_year":2023,"publication_date":"2023-09-29","ids":{"openalex":"https://openalex.org/W4387188098","doi":"https://doi.org/10.3233/aic-220305"},"language":"en","primary_location":{"id":"doi:10.3233/aic-220305","is_oa":false,"landing_page_url":"https://doi.org/10.3233/aic-220305","pdf_url":null,"source":{"id":"https://openalex.org/S176303223","display_name":"AI Communications","issn_l":"0921-7126","issn":["0921-7126","1875-8452"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AI Communications","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/A5028225369","display_name":"Ana L. C. Bazzan","orcid":"https://orcid.org/0000-0002-2803-9607"},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Ana Lucia C. Bazzan","raw_affiliation_strings":["Instituto da Inform\u00e1tica, Universidade Federal do Rio Grande do Sul (UFRGS), Brazil"],"affiliations":[{"raw_affiliation_string":"Instituto da Inform\u00e1tica, Universidade Federal do Rio Grande do Sul (UFRGS), Brazil","institution_ids":["https://openalex.org/I130442723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102561584","display_name":"Vicente Nejar de Almeida","orcid":null},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Vicente N. de\u00a0Almeida","raw_affiliation_strings":["Instituto da Inform\u00e1tica, Universidade Federal do Rio Grande do Sul (UFRGS), Brazil"],"affiliations":[{"raw_affiliation_string":"Instituto da Inform\u00e1tica, Universidade Federal do Rio Grande do Sul (UFRGS), Brazil","institution_ids":["https://openalex.org/I130442723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102561584","display_name":"Vicente Nejar de Almeida","orcid":null},"institutions":[{"id":"https://openalex.org/I130442723","display_name":"Universidade Federal do Rio Grande do Sul","ror":"https://ror.org/041yk2d64","country_code":"BR","type":"education","lineage":["https://openalex.org/I130442723"]},{"id":"https://openalex.org/I48379061","display_name":"Shahid Beheshti University","ror":"https://ror.org/0091vmj44","country_code":"IR","type":"education","lineage":["https://openalex.org/I48379061"]}],"countries":["BR","IR"],"is_corresponding":false,"raw_author_name":"Vicente N. de\u00a0Almeida","raw_affiliation_strings":["Instituto da Inform\u00e1tica, Universidade Federal do Rio Grande do Sul (UFRGS), Brazil","Faculty of Computer Science and Engineering, Shahid Beheshti University, Iran"],"affiliations":[{"raw_affiliation_string":"Instituto da Inform\u00e1tica, Universidade Federal do Rio Grande do Sul (UFRGS), Brazil","institution_ids":["https://openalex.org/I130442723"]},{"raw_affiliation_string":"Faculty of Computer Science and Engineering, Shahid Beheshti University, Iran","institution_ids":["https://openalex.org/I48379061"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054982019","display_name":"Monireh Abdoos","orcid":"https://orcid.org/0000-0002-3106-503X"},"institutions":[{"id":"https://openalex.org/I48379061","display_name":"Shahid Beheshti University","ror":"https://ror.org/0091vmj44","country_code":"IR","type":"education","lineage":["https://openalex.org/I48379061"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Monireh Abdoos","raw_affiliation_strings":["Faculty of Computer Science and Engineering, Shahid Beheshti University, Iran"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Engineering, Shahid Beheshti University, Iran","institution_ids":["https://openalex.org/I48379061"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054982019","display_name":"Monireh Abdoos","orcid":"https://orcid.org/0000-0002-3106-503X"},"institutions":[{"id":"https://openalex.org/I48379061","display_name":"Shahid Beheshti University","ror":"https://ror.org/0091vmj44","country_code":"IR","type":"education","lineage":["https://openalex.org/I48379061"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Monireh Abdoos","raw_affiliation_strings":["Faculty of Computer Science and Engineering, Shahid Beheshti University, Iran"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Engineering, Shahid Beheshti University, Iran","institution_ids":["https://openalex.org/I48379061"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5028225369","https://openalex.org/A5054982019","https://openalex.org/A5102561584"],"corresponding_institution_ids":["https://openalex.org/I130442723","https://openalex.org/I48379061"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14812111,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":"2","first_page":"247","last_page":"259"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10698","display_name":"Transportation Planning and Optimization","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.9879999756813049,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8758949041366577},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8309774398803711},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5893238186836243},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5463985204696655},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5387369990348816},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5130296945571899},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5008804798126221},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4881373345851898},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4673123061656952},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4392596483230591},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4285367727279663},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3265012502670288},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11301648616790771}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8758949041366577},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8309774398803711},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5893238186836243},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5463985204696655},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5387369990348816},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5130296945571899},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5008804798126221},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4881373345851898},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4673123061656952},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4392596483230591},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4285367727279663},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3265012502670288},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11301648616790771},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/aic-220305","is_oa":false,"landing_page_url":"https://doi.org/10.3233/aic-220305","pdf_url":null,"source":{"id":"https://openalex.org/S176303223","display_name":"AI Communications","issn_l":"0921-7126","issn":["0921-7126","1875-8452"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"AI Communications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1646707810","https://openalex.org/W1832110895","https://openalex.org/W1969050456","https://openalex.org/W2020070197","https://openalex.org/W2054314161","https://openalex.org/W2082310090","https://openalex.org/W2088595989","https://openalex.org/W2097381042","https://openalex.org/W2139728973","https://openalex.org/W2161695237","https://openalex.org/W2480177474","https://openalex.org/W2725582697","https://openalex.org/W2735073981","https://openalex.org/W2766381093","https://openalex.org/W2809148419","https://openalex.org/W2813428123","https://openalex.org/W2903709398","https://openalex.org/W2921955147","https://openalex.org/W3016110208","https://openalex.org/W3037790399","https://openalex.org/W3108439758","https://openalex.org/W3123082711","https://openalex.org/W3124050193","https://openalex.org/W3176187537","https://openalex.org/W4233405566","https://openalex.org/W6674600207","https://openalex.org/W6777314378"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"The":[0],"increasing":[1],"demand":[2],"for":[3],"mobility":[4],"in":[5,16,21,51,175],"our":[6,186],"society":[7],"poses":[8,80],"various":[9],"challenges":[10],"to":[11,62,72,96,100,188,214],"traffic":[12,52,64,166,173,180,218],"engineering,":[13],"computer":[14],"science":[15],"general,":[17],"and":[18,54,90,142,184,195],"artificial":[19],"intelligence":[20],"particular.":[22],"Increasing":[23],"the":[24,39,63,81,84,105,135,148,179,205],"capacity":[25],"of":[26,38,104,145,160],"road":[27],"networks":[28],"is":[29,43,47,68,87,94,126],"not":[30,155],"always":[31],"possible,":[32],"thus":[33,92],"a":[34,69,112,120,157,172],"more":[35],"efficient":[36],"use":[37],"available":[40],"transportation":[41],"infrastructure":[42],"required.":[44],"Another":[45],"issue":[46],"that":[48,83,204],"many":[49],"problems":[50],"management":[53],"control":[55],"are":[56],"inherently":[57],"decentralized":[58],"and/or":[59],"require":[60],"adaptation":[61],"situation.":[65,219],"Hence,":[66],"there":[67],"close":[70],"relationship":[71],"multiagent":[73,113],"reinforcement":[74,78,193],"learning.":[75],"However,":[76],"using":[77],"learning":[79,117,121,194],"challenge":[82],"state":[85,106],"space":[86],"normally":[88],"large":[89],"continuous,":[91],"it":[93],"necessary":[95],"find":[97],"appropriate":[98],"schemes":[99],"deal":[101,164],"with":[102,115,165],"discretization":[103],"space.":[107],"To":[108],"address":[109],"these":[110],"issues,":[111],"system":[114],"agents":[116],"independently":[118],"via":[119],"algorithm":[122],"was":[123],"proposed,":[124],"which":[125,176],"based":[127,197],"on":[128,171,198],"estimating":[129],"Q-values":[130],"from":[131],"k-nearest":[132],"neighbors.":[133],"In":[134],"present":[136],"paper,":[137],"we":[138,177],"extend":[139],"this":[140],"approach":[141,187],"include":[143],"transfer":[144],"experiences":[146],"among":[147],"agents,":[149],"especially":[150],"when":[151,210],"an":[152,211,215],"agent":[153,212],"does":[154],"have":[156],"good":[158],"set":[159],"k":[161],"experiences.":[162],"We":[163],"signal":[167],"control,":[168],"running":[169],"experiments":[170],"network":[174],"vary":[178],"situation":[181],"along":[182],"time,":[183],"compare":[185],"two":[189],"baselines":[190],"(one":[191],"involving":[192],"one":[196],"fixed":[199],"times).":[200],"Our":[201],"results":[202],"show":[203],"extended":[206],"method":[207],"pays":[208],"off":[209],"returns":[213],"already":[216],"experienced":[217]},"counts_by_year":[],"updated_date":"2026-04-13T06:00:40.992929","created_date":"2025-10-10T00:00:00"}