{"id":"https://openalex.org/W2027628482","doi":"https://doi.org/10.1109/cdc.2014.7039557","title":"Kernel-based reinforcement learning for traffic signal control with adaptive feature selection","display_name":"Kernel-based reinforcement learning for traffic signal control with adaptive feature selection","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2027628482","doi":"https://doi.org/10.1109/cdc.2014.7039557","mag":"2027628482"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2014.7039557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2014.7039557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"53rd IEEE Conference on Decision and Control","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/A5101737502","display_name":"Tianshu Chu","orcid":"https://orcid.org/0000-0002-9404-3348"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tianshu Chu","raw_affiliation_strings":["Department of Civil and Environmental Engineering, Stanford University, CA, USA","Dept. of Civil and Environmental Engineering, Stanford University, CA 94305, USA"],"affiliations":[{"raw_affiliation_string":"Department of Civil and Environmental Engineering, Stanford University, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Dept. of Civil and Environmental Engineering, Stanford University, CA 94305, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101422661","display_name":"Jie Wang","orcid":"https://orcid.org/0000-0003-1857-5569"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Wang","raw_affiliation_strings":["Department of Civil and Environmental Engineering, Stanford University, CA, USA","Dept. of Civil and Environmental Engineering, Stanford University, CA 94305, USA"],"affiliations":[{"raw_affiliation_string":"Department of Civil and Environmental Engineering, Stanford University, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Dept. of Civil and Environmental Engineering, Stanford University, CA 94305, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100648774","display_name":"Jian Cao","orcid":"https://orcid.org/0000-0002-0036-9436"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Cao","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai JiaoTong University, Shanghai, China","Department of Computer Science and Engineering, Shanghai Jiaotong University, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai JiaoTong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiaotong University, China#TAB#","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101737502"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":2.8721,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.90949592,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1277","last_page":"1282"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9987000226974487,"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":0.9987000226974487,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9848999977111816,"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"}},{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.9697999954223633,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7164600491523743},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6929097175598145},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5916905403137207},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5381629467010498},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5341612100601196},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.5184047222137451},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.5094419121742249},{"id":"https://openalex.org/keywords/reproducing-kernel-hilbert-space","display_name":"Reproducing kernel Hilbert space","score":0.45905670523643494},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.45160093903541565},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38245517015457153},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3589986562728882},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.27009183168411255},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.20038267970085144},{"id":"https://openalex.org/keywords/hilbert-space","display_name":"Hilbert space","score":0.14077064394950867}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7164600491523743},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6929097175598145},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5916905403137207},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5381629467010498},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5341612100601196},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.5184047222137451},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.5094419121742249},{"id":"https://openalex.org/C80884492","wikidata":"https://www.wikidata.org/wiki/Q3345678","display_name":"Reproducing kernel Hilbert space","level":3,"score":0.45905670523643494},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.45160093903541565},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38245517015457153},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3589986562728882},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.27009183168411255},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.20038267970085144},{"id":"https://openalex.org/C62799726","wikidata":"https://www.wikidata.org/wiki/Q190056","display_name":"Hilbert space","level":2,"score":0.14077064394950867},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2014.7039557","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2014.7039557","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"53rd IEEE Conference on Decision and Control","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","display_name":"No poverty","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1506832649","https://openalex.org/W1550698229","https://openalex.org/W1928215159","https://openalex.org/W1986659999","https://openalex.org/W2073384958","https://openalex.org/W2076337359","https://openalex.org/W2098432798","https://openalex.org/W2101460915","https://openalex.org/W2107726111","https://openalex.org/W2107977784","https://openalex.org/W2117359296","https://openalex.org/W2120346334","https://openalex.org/W2121863487","https://openalex.org/W2134289401","https://openalex.org/W2146544184","https://openalex.org/W2147750403","https://openalex.org/W2165421048","https://openalex.org/W2169982856","https://openalex.org/W4211221179","https://openalex.org/W4214717370","https://openalex.org/W4233696721","https://openalex.org/W4245296547","https://openalex.org/W6630376126","https://openalex.org/W6676007687","https://openalex.org/W6677737365","https://openalex.org/W6679703492","https://openalex.org/W6684096483","https://openalex.org/W6996005239","https://openalex.org/W7001212498"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W3009056573","https://openalex.org/W2160166502","https://openalex.org/W4322615556","https://openalex.org/W3133651710","https://openalex.org/W2056283567","https://openalex.org/W4287555349","https://openalex.org/W3113111988","https://openalex.org/W3198417070"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,64],"in":[2,123,147,154,195,211],"a":[3,24,27,51,78,84,95,115,196],"large-scale":[4],"system":[5,58,139],"is":[6,18,92,145,169,199,207,215],"computationally":[7],"challenging":[8],"due":[9],"to":[10,19,61,75,178],"the":[11,14,21,34,40,57,62,89,124,128,135,138,155,158,164,184,191,202,213],"curse":[12],"of":[13,26,83,157,166,181,204],"dimensionality.":[15],"One":[16],"approach":[17],"approximate":[20,129],"Q-function":[22,130,182,214],"as":[23,134],"function":[25],"state-action":[28,102,220],"related":[29],"feature":[30,48,80,90],"vector,":[31,49],"then":[32],"learn":[33],"parameters":[35],"instead.":[36],"Although":[37],"assumptions":[38],"from":[39,94],"priori":[41],"knowledge":[42,136],"can":[43,109],"potentially":[44],"explore":[45],"an":[46,120],"appropriate":[47],"selecting":[50],"biased":[52],"one":[53,122],"that":[54],"insufficiently":[55],"represents":[56],"usually":[59],"leads":[60],"poor":[63],"performance.":[65],"To":[66],"avoid":[67,179],"this":[68,70,167,205],"disadvantage,":[69],"paper":[71],"introduces":[72],"kernel":[73],"methods":[74,175],"implicitly":[76],"propose":[77],"learnable":[79],"vector":[81,91],"instead":[82],"pre-selected":[85],"one.":[86],"More":[87],"specifically,":[88],"estimated":[93,217],"reference":[96,125],"set":[97],"which":[98,212],"contains":[99],"all":[100],"critical":[101],"pairs":[103],"observed":[104],"so":[105],"far,":[106],"and":[107,151,201],"it":[108],"be":[110],"updated":[111],"by":[112],"either":[113],"adding":[114],"new":[116],"pair":[117,221],"or":[118],"replace":[119],"existing":[121],"set.":[126],"Thus":[127],"keeps":[131],"adjusting":[132],"itself":[133],"about":[137],"accumulates":[140],"via":[141],"observations.":[142,186],"Our":[143],"algorithm":[144,168,206],"designed":[146],"both":[148],"batch":[149],"mode":[150,153],"online":[152],"context":[156],"traffic":[159,192],"signal":[160,193],"control.":[161],"In":[162],"addition,":[163],"convergence":[165],"experimentally":[170],"supported.":[171],"Furthermore,":[172],"some":[173],"regularization":[174],"are":[176],"proposed":[177],"overfitting":[180],"on":[183,190],"noisy":[185],"Finally,":[187],"A":[188],"simulation":[189],"control":[194],"single":[197],"intersection":[198],"provided,":[200],"performance":[203],"compared":[208],"with":[209],"Q-learning,":[210],"numerically":[216],"for":[218],"each":[219],"without":[222],"approximation.":[223]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-17T23:14:22.571179","created_date":"2025-10-10T00:00:00"}