{"id":"https://openalex.org/W2995359469","doi":"https://doi.org/10.1145/3368756.3369038","title":"Deep reinforcement learning with external control","display_name":"Deep reinforcement learning with external control","publication_year":2019,"publication_date":"2019-10-02","ids":{"openalex":"https://openalex.org/W2995359469","doi":"https://doi.org/10.1145/3368756.3369038","mag":"2995359469"},"language":"en","primary_location":{"id":"doi:10.1145/3368756.3369038","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3368756.3369038","pdf_url":null,"source":{"id":"https://openalex.org/S4306523848","display_name":"Proceedings of the 4th International Conference on Smart City Applications","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":"Proceedings of the 4th International Conference on Smart City Applications","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/A5018416138","display_name":"Fenjiro Youssef","orcid":null},"institutions":[{"id":"https://openalex.org/I126477371","display_name":"Mohammed V University","ror":"https://ror.org/00r8w8f84","country_code":"MA","type":"education","lineage":["https://openalex.org/I126477371"]}],"countries":["MA"],"is_corresponding":true,"raw_author_name":"Fenjiro Youssef","raw_affiliation_strings":["Mohammed V University, Rabat, Morocco"],"affiliations":[{"raw_affiliation_string":"Mohammed V University, Rabat, Morocco","institution_ids":["https://openalex.org/I126477371"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065627637","display_name":"Houda Benbrahim","orcid":"https://orcid.org/0009-0005-2797-212X"},"institutions":[{"id":"https://openalex.org/I126477371","display_name":"Mohammed V University","ror":"https://ror.org/00r8w8f84","country_code":"MA","type":"education","lineage":["https://openalex.org/I126477371"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Benbrahim Houda","raw_affiliation_strings":["Mohammed V University, Rabat, Morocco"],"affiliations":[{"raw_affiliation_string":"Mohammed V University, Rabat, Morocco","institution_ids":["https://openalex.org/I126477371"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5018416138"],"corresponding_institution_ids":["https://openalex.org/I126477371"],"apc_list":null,"apc_paid":null,"fwci":0.3936,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69220223,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.998199999332428,"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/T10524","display_name":"Traffic control and management","score":0.9825999736785889,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.902856707572937},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.8570898771286011},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7456920146942139},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6206236481666565},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5868505239486694},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.530989944934845},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5286296606063843},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4733926057815552},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45604023337364197},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.44417765736579895},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4194507896900177},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.34332990646362305},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1441572904586792},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.11869120597839355}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.902856707572937},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.8570898771286011},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7456920146942139},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6206236481666565},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5868505239486694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.530989944934845},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5286296606063843},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4733926057815552},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45604023337364197},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.44417765736579895},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4194507896900177},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.34332990646362305},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1441572904586792},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.11869120597839355},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3368756.3369038","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3368756.3369038","pdf_url":null,"source":{"id":"https://openalex.org/S4306523848","display_name":"Proceedings of the 4th International Conference on Smart City Applications","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":"Proceedings of the 4th International Conference on Smart City Applications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8299999833106995,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1574474448","https://openalex.org/W1583161923","https://openalex.org/W1751228448","https://openalex.org/W1836465849","https://openalex.org/W1931877416","https://openalex.org/W2106187441","https://openalex.org/W2119112357","https://openalex.org/W2123487810","https://openalex.org/W2145339207","https://openalex.org/W2155682648","https://openalex.org/W2173248099","https://openalex.org/W2260756217","https://openalex.org/W2270257869","https://openalex.org/W2615547864","https://openalex.org/W2727840223","https://openalex.org/W2749928749","https://openalex.org/W2760878839","https://openalex.org/W2798645699","https://openalex.org/W2799745602","https://openalex.org/W2799831549","https://openalex.org/W2885467852","https://openalex.org/W2905173465","https://openalex.org/W2907953482","https://openalex.org/W2941499360","https://openalex.org/W2946943579","https://openalex.org/W3100397002","https://openalex.org/W4244354771","https://openalex.org/W6638018090","https://openalex.org/W6704559304","https://openalex.org/W6729788943","https://openalex.org/W6741002519","https://openalex.org/W6745935785","https://openalex.org/W6747439198","https://openalex.org/W6748219870"],"related_works":["https://openalex.org/W2171408034","https://openalex.org/W3003320923","https://openalex.org/W2106140982","https://openalex.org/W2883256816","https://openalex.org/W2152313554","https://openalex.org/W3048672182","https://openalex.org/W1509300825","https://openalex.org/W3092582874","https://openalex.org/W2065450024","https://openalex.org/W2207517346"],"abstract_inverted_index":{"A":[0],"Self-driving":[1],"car":[2],"using":[3],"an":[4,36],"end-to-end":[5],"deep":[6],"reinforcement":[7],"learning[1]":[8],"algorithms":[9],"trained":[10],"on":[11,83,129],"lane-keeping":[12],"task":[13],"performs":[14,127],"well":[15,128],"in":[16,35,112],"circuits":[17],"that":[18,63,70,139],"don't":[19],"need":[20],"decision":[21],"making":[22],"but":[23],"cannot":[24],"deal":[25],"with":[26],"situations":[27],"like":[28],"choosing":[29],"to":[30,41,50,103,117,135,144],"turn":[31],"left":[32],"or":[33,46],"right":[34,147],"upcoming":[37],"crossroads,":[38],"deciding":[39],"when":[40],"leave":[42],"a":[43,57,94,100],"traffic":[44],"circle":[45],"toward":[47],"which":[48],"path/destination":[49],"go.":[51],"In":[52],"this":[53],"paper":[54],"we":[55,71,78],"propose":[56],"new":[58,108],"Deep":[59,74,85],"Reinforcement":[60,75],"Learning":[61,76],"architecture":[62,82],"supports":[64],"external":[65,137],"command":[66],"as":[67,99],"high-level":[68],"input,":[69],"call":[72],"Steered":[73,123],"(SDRL),":[77],"apply":[79],"the":[80,84,107,130,136,141,146],"SDRL":[81],"Deterministic":[86],"Policy":[87],"Gradient":[88],"algorithm":[89],"DDPG":[90,124],"and":[91,105,120,132],"use":[92],"CARLA":[93],"High-fidelity":[95],"realistic":[96],"driving":[97,142],"simulator":[98],"testbed":[101],"environment":[102],"train":[104],"experiment":[106],"model,":[109],"since":[110],"testing":[111],"ground":[113],"truth":[114],"turns":[115],"out":[116],"be":[118],"costly":[119],"risky.":[121],"The":[122],"(SDDPG)":[125],"model":[126],"road/roundabouts":[131],"responds":[133],"correctly":[134],"commands":[138],"allow":[140],"agent":[143],"take":[145],"turns.":[148]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}