{"id":"https://openalex.org/W3118619025","doi":"https://doi.org/10.1109/ssci47803.2020.9308525","title":"Optimizing Agent Training with Deep Q-Learning on a Self-Driving Reinforcement Learning Environment","display_name":"Optimizing Agent Training with Deep Q-Learning on a Self-Driving Reinforcement Learning Environment","publication_year":2020,"publication_date":"2020-12-01","ids":{"openalex":"https://openalex.org/W3118619025","doi":"https://doi.org/10.1109/ssci47803.2020.9308525","mag":"3118619025"},"language":"en","primary_location":{"id":"doi:10.1109/ssci47803.2020.9308525","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci47803.2020.9308525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Symposium Series on Computational Intelligence (SSCI)","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/A5084608979","display_name":"Pedro Rodrigues","orcid":"https://orcid.org/0000-0002-0555-2029"},"institutions":[{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Pedro Rodrigues","raw_affiliation_strings":["IDMEC - Instituto Superior T\u00e9cnico Universidade de Lisboa, Lisbon, Portugal"],"affiliations":[{"raw_affiliation_string":"IDMEC - Instituto Superior T\u00e9cnico Universidade de Lisboa, Lisbon, Portugal","institution_ids":["https://openalex.org/I141596103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023524727","display_name":"Susana M. Vieira","orcid":"https://orcid.org/0000-0001-7961-1004"},"institutions":[{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Susana Vieira","raw_affiliation_strings":["IDMEC - Instituto Superior T\u00e9cnico Universidade de Lisboa, Lisbon, Portugal"],"affiliations":[{"raw_affiliation_string":"IDMEC - Instituto Superior T\u00e9cnico Universidade de Lisboa, Lisbon, Portugal","institution_ids":["https://openalex.org/I141596103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5084608979"],"corresponding_institution_ids":["https://openalex.org/I141596103"],"apc_list":null,"apc_paid":null,"fwci":0.3977,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.70220803,"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":"745","last_page":"752"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9959999918937683,"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":0.9959999918937683,"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":0.9916999936103821,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9869999885559082,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9064154028892517},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8294351100921631},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6291680335998535},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6183540225028992},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.5946167707443237},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5893746018409729},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4775163233280182},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4756864309310913},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.46835795044898987},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.44021591544151306},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43260079622268677},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3959520757198334},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09261241555213928}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9064154028892517},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8294351100921631},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6291680335998535},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6183540225028992},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.5946167707443237},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5893746018409729},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4775163233280182},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4756864309310913},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.46835795044898987},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.44021591544151306},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43260079622268677},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3959520757198334},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09261241555213928},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/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/ssci47803.2020.9308525","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci47803.2020.9308525","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Symposium Series on Computational Intelligence (SSCI)","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":27,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1796544916","https://openalex.org/W2121092017","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2163605009","https://openalex.org/W2173564293","https://openalex.org/W2201581102","https://openalex.org/W2626017178","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2890208753","https://openalex.org/W2951799221","https://openalex.org/W2954989419","https://openalex.org/W2962938178","https://openalex.org/W2963477884","https://openalex.org/W2964291307","https://openalex.org/W2970866842","https://openalex.org/W4288333794","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6677939520","https://openalex.org/W6684191040","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6754184789","https://openalex.org/W6764965709"],"related_works":["https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3133861977","https://openalex.org/W2951211570","https://openalex.org/W3103566983","https://openalex.org/W3167935049","https://openalex.org/W3029198973","https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W2166117066"],"abstract_inverted_index":{"Nowadays,":[0],"there":[1],"are":[2],"many":[3],"Deep":[4,23,153],"Q-Learning":[5],"(DQL)":[6],"variants":[7],"and":[8,70,107,117,156],"Reinforcement":[9],"Learning":[10],"(RL)":[11],"algorithms":[12],"that":[13,136],"have":[14],"outperformed":[15],"the":[16,42,74,86,89,132,137,145,161],"original":[17,75],"DQL":[18,76,147],"algorithm":[19,92],"using":[20,60,118],"a":[21,49,61,123],"simple":[22],"Q-Network":[24,154],"(DQN)":[25],"architecture":[26],"on":[27,41,73,83,94,144],"several":[28],"RL":[29,163],"applications.":[30],"In":[31],"this":[32,95],"paper,":[33],"we":[34,78],"present":[35],"an":[36],"environment-oriented":[37],"adapted":[38,139],"DQN":[39,91,140],"implementation":[40],"OpenAI":[43],"Gym":[44],"CarRacing":[45,162],"self-driving":[46],"environment":[47],"where":[48],"driver":[50],"agent":[51,99,141,150],"successfully":[52],"learns":[53],"difficult":[54],"control":[55],"policies":[56],"from":[57],"raw":[58],"pixels":[59],"deep":[62],"convolutional":[63],"neural":[64],"network.":[65],"By":[66],"implementing":[67],"multiple":[68,157],"optimizations":[69],"environment-specific":[71],"adaptations":[72],"algorithm,":[77],"were":[79],"able":[80,102],"to":[81,103],"improve":[82],"some":[84],"of":[85,88],"limitations":[87],"base":[90,146],"significantly":[93],"platform.":[96],"Our":[97,149],"trained":[98],"was":[100],"therefore":[101],"produce":[104],"successful":[105],"results":[106,133],"obtain":[108],"higher":[109],"convergence":[110],"scores":[111],"while":[112],"being":[113],"more":[114],"time":[115],"efficient":[116],"less":[119],"computational":[120],"resources.":[121],"Obtaining":[122],"promising":[124],"average":[125],"score":[126],"over":[127],"one":[128],"hundred":[129],"consecutive":[130],"trials,":[131],"achieved":[134],"suggest":[135],"proposed":[138],"improves":[142],"substantially":[143],"algorithm.":[148],"surpassed":[151],"Double":[152],"(DDQN)":[155],"other":[158],"approaches":[159],"in":[160],"environment.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-25T21:42:39.735039","created_date":"2025-10-10T00:00:00"}