{"id":"https://openalex.org/W3089829004","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207403","title":"On the Role of Reward Functions for Reinforcement Learning in the Traffic Assignment Problem","display_name":"On the Role of Reward Functions for Reinforcement Learning in the Traffic Assignment Problem","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3089829004","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207403","mag":"3089829004"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9207403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5027755211","display_name":"Ricardo Grunitzki","orcid":null},"institutions":[{"id":"https://openalex.org/I4210151455","display_name":"Ministry of Science, Technology and Innovation","ror":"https://ror.org/050zdnc69","country_code":"BR","type":"government","lineage":["https://openalex.org/I4210151455"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Ricardo Grunitzki","raw_affiliation_strings":["Mobile Innovation Lab, SIDIA Institute of Science and Technology, Manaus, Brazil"],"affiliations":[{"raw_affiliation_string":"Mobile Innovation Lab, SIDIA Institute of Science and Technology, Manaus, Brazil","institution_ids":["https://openalex.org/I4210151455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000440246","display_name":"Gabriel de Oliveira Ramos","orcid":"https://orcid.org/0000-0002-6488-7654"},"institutions":[{"id":"https://openalex.org/I4210151455","display_name":"Ministry of Science, Technology and Innovation","ror":"https://ror.org/050zdnc69","country_code":"BR","type":"government","lineage":["https://openalex.org/I4210151455"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Gabriel de Oliveira Ramos","raw_affiliation_strings":["Mobile Innovation Lab, SIDIA Institute of Science and Technology, Manaus, Brazil"],"affiliations":[{"raw_affiliation_string":"Mobile Innovation Lab, SIDIA Institute of Science and Technology, Manaus, Brazil","institution_ids":["https://openalex.org/I4210151455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5027755211"],"corresponding_institution_ids":["https://openalex.org/I4210151455"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.10326287,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10698","display_name":"Transportation Planning and Optimization","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10698","display_name":"Transportation Planning and Optimization","score":0.9998000264167786,"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/T10524","display_name":"Traffic control and management","score":0.9984999895095825,"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/T11942","display_name":"Transportation and Mobility Innovations","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"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":0.8307077288627625},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6905285120010376},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5480473637580872},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.5021498203277588},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4830218255519867},{"id":"https://openalex.org/keywords/traffic-congestion","display_name":"Traffic congestion","score":0.4518822431564331},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.42328739166259766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3512246012687683},{"id":"https://openalex.org/keywords/transport-engineering","display_name":"Transport engineering","score":0.20371034741401672},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.142942875623703}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8307077288627625},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6905285120010376},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5480473637580872},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.5021498203277588},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4830218255519867},{"id":"https://openalex.org/C2779888511","wikidata":"https://www.wikidata.org/wiki/Q244156","display_name":"Traffic congestion","level":2,"score":0.4518822431564331},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42328739166259766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3512246012687683},{"id":"https://openalex.org/C22212356","wikidata":"https://www.wikidata.org/wiki/Q775325","display_name":"Transport engineering","level":1,"score":0.20371034741401672},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.142942875623703},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9207403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W41554520","https://openalex.org/W1486707268","https://openalex.org/W1503017385","https://openalex.org/W1777239053","https://openalex.org/W1977031068","https://openalex.org/W1980358463","https://openalex.org/W2003912133","https://openalex.org/W2011282943","https://openalex.org/W2014394432","https://openalex.org/W2014482607","https://openalex.org/W2025149596","https://openalex.org/W2025565923","https://openalex.org/W2031571562","https://openalex.org/W2037067712","https://openalex.org/W2053806224","https://openalex.org/W2069855531","https://openalex.org/W2082569289","https://openalex.org/W2088595989","https://openalex.org/W2099618002","https://openalex.org/W2104602264","https://openalex.org/W2123408238","https://openalex.org/W2139612737","https://openalex.org/W2160088187","https://openalex.org/W2163602945","https://openalex.org/W2164424353","https://openalex.org/W2184028858","https://openalex.org/W2480177474","https://openalex.org/W2495333748","https://openalex.org/W2556366151","https://openalex.org/W2572460713","https://openalex.org/W2592535843","https://openalex.org/W2620929994","https://openalex.org/W2621111958","https://openalex.org/W2751816856","https://openalex.org/W2783289783","https://openalex.org/W2897200624","https://openalex.org/W3136236940","https://openalex.org/W6628902087","https://openalex.org/W6638088447","https://openalex.org/W6669779600","https://openalex.org/W6675811377","https://openalex.org/W6680292960","https://openalex.org/W6683991275","https://openalex.org/W6731786310"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"The":[0],"traffic":[1,16,91],"assignment":[2],"problem":[3,52,99],"(TAP)":[4],"consists":[5],"of":[6,27,51,104,129,132,196],"assigning":[7],"routes":[8,35],"to":[9,14,36,77,161,178],"road":[10,37,57,157],"users":[11,58],"in":[12,47,75,88,193],"order":[13,76],"minimize":[15],"congestion.":[17],"Traditional":[18],"methods":[19],"for":[20,63],"solving":[21,48],"the":[22,25,79,102,130,137,171,181,184,194,197],"TAP":[23],"assume":[24],"existence":[26],"a":[28,71,85,126],"central":[29],"authority":[30],"who":[31],"computes":[32],"and":[33,115],"dictates":[34],"users.":[38],"Multi-agent":[39],"reinforcement":[40],"learning":[41,164,182],"(MARL)":[42],"approaches":[43,68],"are":[44],"more":[45,89],"realistic":[46,90],"this":[49,94,98,147],"kind":[50],"because":[53],"they":[54],"consider":[55],"that":[56],"(agents)":[59],"have":[60],"complete":[61],"autonomy":[62],"choosing":[64],"routes.":[65],"However,":[66],"MARL":[67],"usually":[69],"require":[70],"long":[72],"training":[73],"period":[74],"compute":[78],"optimal":[80],"routes,":[81],"which":[82],"could":[83],"be":[84],"major":[86],"limitation":[87],"scenarios.":[92],"In":[93,119],"paper,":[95],"we":[96,149],"tackle":[97],"by":[100],"evaluating":[101],"performance":[103],"three":[105],"conceptually":[106],"different":[107,156],"reward":[108,134,173,186],"functions,":[109],"namely:":[110],"expert-designed":[111],"rewards,":[112,114],"difference":[113],"intrinsically":[116],"motivated":[117],"rewards.":[118],"particular,":[120],"our":[121],"focus":[122],"lies":[123],"on":[124,136,155],"providing":[125],"deeper":[127],"understanding":[128],"impact":[131],"these":[133],"functions":[135,174],"agents'":[138],"performance,":[139],"thus":[140],"contributing":[141],"towards":[142],"reducing":[143],"congestion":[144],"levels.":[145],"To":[146],"end,":[148],"perform":[150],"an":[151,190],"extensive":[152],"experimental":[153],"evaluation":[154],"networks,":[158],"including":[159],"up":[160,180],"360,600":[162],"concurrently":[163],"agents.":[165],"Our":[166],"results":[167],"show":[168],"that,":[169],"although":[170],"adopted":[172],"were":[175],"not":[176],"able":[177],"speed":[179],"process,":[183],"correct":[185],"function":[187],"choice":[188],"plays":[189],"important":[191],"role":[192],"quality":[195],"learned":[198],"solution.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}