{"id":"https://openalex.org/W3211071471","doi":"https://doi.org/10.1109/itsc48978.2021.9564731","title":"Designing Reinforcement Learning Agents for Traffic Signal Control with the Right Goals: a Time-Loss based Approach","display_name":"Designing Reinforcement Learning Agents for Traffic Signal Control with the Right Goals: a Time-Loss based Approach","publication_year":2021,"publication_date":"2021-09-19","ids":{"openalex":"https://openalex.org/W3211071471","doi":"https://doi.org/10.1109/itsc48978.2021.9564731","mag":"3211071471"},"language":"en","primary_location":{"id":"doi:10.1109/itsc48978.2021.9564731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc48978.2021.9564731","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Intelligent Transportation Systems Conference (ITSC)","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/A5068499082","display_name":"Marcelo Andrade Rodrigues D\u2019Almeida","orcid":null},"institutions":[{"id":"https://openalex.org/I161127581","display_name":"Universidade Federal Fluminense","ror":"https://ror.org/02rjhbb08","country_code":"BR","type":"education","lineage":["https://openalex.org/I161127581"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Marcelo D'Almeida","raw_affiliation_strings":["MD and AP are with Universidade Federal, Fluminense, Brazil"],"affiliations":[{"raw_affiliation_string":"MD and AP are with Universidade Federal, Fluminense, Brazil","institution_ids":["https://openalex.org/I161127581"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045549996","display_name":"Aline Paes","orcid":"https://orcid.org/0000-0002-9089-7303"},"institutions":[{"id":"https://openalex.org/I161127581","display_name":"Universidade Federal Fluminense","ror":"https://ror.org/02rjhbb08","country_code":"BR","type":"education","lineage":["https://openalex.org/I161127581"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Aline Paes","raw_affiliation_strings":["MD and AP are with Universidade Federal, Fluminense, Brazil"],"affiliations":[{"raw_affiliation_string":"MD and AP are with Universidade Federal, Fluminense, Brazil","institution_ids":["https://openalex.org/I161127581"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088337929","display_name":"Daniel Moss\u00e9","orcid":"https://orcid.org/0000-0002-9508-9815"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Mosse","raw_affiliation_strings":["DM is with University of Pittsburgh, USA"],"affiliations":[{"raw_affiliation_string":"DM is with University of Pittsburgh, USA","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068499082"],"corresponding_institution_ids":["https://openalex.org/I161127581"],"apc_list":null,"apc_paid":null,"fwci":0.1373,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.4644469,"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":"1412","last_page":"1418"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9968000054359436,"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":0.9965999722480774,"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":0.8408889770507812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7246931791305542},{"id":"https://openalex.org/keywords/deadlock","display_name":"Deadlock","score":0.6972758769989014},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5520617365837097},{"id":"https://openalex.org/keywords/travel-time","display_name":"Travel time","score":0.5458812713623047},{"id":"https://openalex.org/keywords/traffic-signal","display_name":"Traffic signal","score":0.4530678391456604},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.43862175941467285},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.43494874238967896},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4261828362941742},{"id":"https://openalex.org/keywords/time-allocation","display_name":"Time allocation","score":0.42339402437210083},{"id":"https://openalex.org/keywords/time-point","display_name":"Time point","score":0.41957318782806396},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.41333794593811035},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.4108225405216217},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24518120288848877},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16466385126113892},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.14126914739608765},{"id":"https://openalex.org/keywords/transport-engineering","display_name":"Transport engineering","score":0.12533867359161377},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10398989915847778},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08612853288650513}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8408889770507812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7246931791305542},{"id":"https://openalex.org/C159023740","wikidata":"https://www.wikidata.org/wiki/Q623276","display_name":"Deadlock","level":2,"score":0.6972758769989014},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5520617365837097},{"id":"https://openalex.org/C2985733770","wikidata":"https://www.wikidata.org/wiki/Q1233007","display_name":"Travel time","level":2,"score":0.5458812713623047},{"id":"https://openalex.org/C2987419075","wikidata":"https://www.wikidata.org/wiki/Q8004","display_name":"Traffic signal","level":2,"score":0.4530678391456604},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.43862175941467285},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.43494874238967896},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4261828362941742},{"id":"https://openalex.org/C180518391","wikidata":"https://www.wikidata.org/wiki/Q355217","display_name":"Time allocation","level":2,"score":0.42339402437210083},{"id":"https://openalex.org/C2779466056","wikidata":"https://www.wikidata.org/wiki/Q107630651","display_name":"Time point","level":2,"score":0.41957318782806396},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.41333794593811035},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.4108225405216217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24518120288848877},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16466385126113892},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.14126914739608765},{"id":"https://openalex.org/C22212356","wikidata":"https://www.wikidata.org/wiki/Q775325","display_name":"Transport engineering","level":1,"score":0.12533867359161377},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10398989915847778},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08612853288650513},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc48978.2021.9564731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc48978.2021.9564731","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Intelligent Transportation Systems Conference (ITSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W5525483","https://openalex.org/W41554520","https://openalex.org/W573924038","https://openalex.org/W1555857857","https://openalex.org/W1595704756","https://openalex.org/W2049593940","https://openalex.org/W2121863487","https://openalex.org/W2766381093","https://openalex.org/W2766413382","https://openalex.org/W2789443414","https://openalex.org/W2798666732","https://openalex.org/W2903709398","https://openalex.org/W2904065660","https://openalex.org/W2915117209","https://openalex.org/W2939228328","https://openalex.org/W2964749398","https://openalex.org/W2983178256","https://openalex.org/W2988973041","https://openalex.org/W2998187693","https://openalex.org/W2998332605","https://openalex.org/W3005974022","https://openalex.org/W3086530824","https://openalex.org/W3090940203","https://openalex.org/W3096739060","https://openalex.org/W3098136553","https://openalex.org/W3102059892","https://openalex.org/W3105017587","https://openalex.org/W3110888614","https://openalex.org/W3124050193","https://openalex.org/W3127572859","https://openalex.org/W3128049868","https://openalex.org/W6616526780","https://openalex.org/W6635531434","https://openalex.org/W6655832309","https://openalex.org/W6662880373","https://openalex.org/W6745594345","https://openalex.org/W6759553562","https://openalex.org/W6761871375","https://openalex.org/W6786402820","https://openalex.org/W6786518016","https://openalex.org/W6790275738","https://openalex.org/W6790686233"],"related_works":["https://openalex.org/W397120980","https://openalex.org/W1528537929","https://openalex.org/W2359800014","https://openalex.org/W2074817166","https://openalex.org/W2893081576","https://openalex.org/W4392428071","https://openalex.org/W113157769","https://openalex.org/W4384812167","https://openalex.org/W2019836907","https://openalex.org/W2053911168"],"abstract_inverted_index":{"In":[0,72],"recent":[1],"years,":[2],"several":[3],"studies":[4,28],"proposed":[5],"different":[6],"Reinforcement":[7],"Learning":[8],"(RL)":[9],"methods":[10],"and":[11,22,69,91,113,125],"formulations":[12],"for":[13,31,67],"the":[14,36,60,121,126,141],"Traffic":[15],"Signal":[16],"Control":[17],"problem,":[18],"presenting":[19],"promising":[20],"results":[21,66,131],"flexible":[23],"traffic":[24],"light":[25],"solutions.":[26],"These":[27],"generally":[29],"decide":[30],"optimizing":[32],"travel":[33,39,99,111],"time":[34,40,58,83,87,93,100,107,112,122,136,142],"as":[35],"objective.":[37],"However,":[38],"has":[41],"some":[42],"crucial":[43],"shortcomings:":[44],"it":[45,52,63],"is":[46,116],"not":[47],"easily":[48],"decomposable":[49],"into":[50],"rewards;":[51],"hinders":[53],"analysis":[54],"at":[55],"any":[56],"simulation":[57],"but":[59],"very":[61],"end;":[62],"produces":[64],"unrealistic":[65],"deadlock":[68],"starvation":[70],"situations.":[71],"this":[73],"paper,":[74],"we":[75],"propose":[76],"two":[77],"versions":[78],"of":[79],"objectives":[80],"based":[81],"on":[82],"loss,":[84],"namely":[85],"instant":[86],"loss":[88,94,108,123],"per":[89,95],"driver":[90],"consolidated":[92],"driver,":[96],"to":[97,148],"address":[98],"shortcomings.":[101],"We":[102],"also":[103],"show":[104],"that":[105,114,134],"improving":[106,110],"implies":[109],"there":[115],"a":[117],"direct":[118],"relationship":[119],"between":[120],"objective":[124],"agents'":[127],"reward.":[128],"Our":[129],"experimental":[130],"point":[132],"out":[133],"our":[135],"loss-based":[137],"RL":[138],"formulation":[139],"improves":[140],"savings":[143],"by":[144],"6%":[145],"when":[146],"compared":[147],"other":[149],"commonly-adopted":[150],"state-of-the-art":[151],"formulations.":[152]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}