{"id":"https://openalex.org/W4392966039","doi":"https://doi.org/10.3389/fnbot.2024.1338189","title":"Deep reinforcement learning navigation via decision transformer in autonomous driving","display_name":"Deep reinforcement learning navigation via decision transformer in autonomous driving","publication_year":2024,"publication_date":"2024-03-19","ids":{"openalex":"https://openalex.org/W4392966039","doi":"https://doi.org/10.3389/fnbot.2024.1338189","pmid":"https://pubmed.ncbi.nlm.nih.gov/38566892"},"language":"en","primary_location":{"id":"doi:10.3389/fnbot.2024.1338189","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fnbot.2024.1338189","pdf_url":"https://www.frontiersin.org/articles/10.3389/fnbot.2024.1338189/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S115606517","display_name":"Frontiers in Neurorobotics","issn_l":"1662-5218","issn":["1662-5218"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Neurorobotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/articles/10.3389/fnbot.2024.1338189/pdf?isPublishedV2=False","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053829722","display_name":"Lun Ge","orcid":"https://orcid.org/0000-0003-2068-5206"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lun Ge","raw_affiliation_strings":["School of Modern Post (School of Automation), Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Modern Post (School of Automation), Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101815043","display_name":"Xiaoguang Zhou","orcid":"https://orcid.org/0000-0002-1829-927X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoguang Zhou","raw_affiliation_strings":["School of Modern Post (School of Automation), Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Modern Post (School of Automation), Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101547882","display_name":"Yongqiang Li","orcid":"https://orcid.org/0000-0002-7586-9232"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yongqiang Li","raw_affiliation_strings":["Mogo Auto Intelligence and Telematics Information Technology Co., Ltd, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Mogo Auto Intelligence and Telematics Information Technology Co., Ltd, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113008983","display_name":"Yongcong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongcong Wang","raw_affiliation_strings":["Neolix Technologies Co., Ltd, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Neolix Technologies Co., Ltd, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101547882","https://openalex.org/A5101815043"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":{"value":2950,"currency":"USD","value_usd":2950},"apc_paid":{"value":2950,"currency":"USD","value_usd":2950},"fwci":5.4507,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.96136479,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"18","issue":null,"first_page":"1338189","last_page":"1338189"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9993000030517578,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8210914731025696},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7991273403167725},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6750685572624207},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5319744944572449},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5066877007484436},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4872390329837799},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.444196492433548},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.43791458010673523},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3545546531677246}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8210914731025696},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7991273403167725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6750685572624207},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5319744944572449},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5066877007484436},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4872390329837799},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.444196492433548},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.43791458010673523},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3545546531677246},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/fnbot.2024.1338189","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fnbot.2024.1338189","pdf_url":"https://www.frontiersin.org/articles/10.3389/fnbot.2024.1338189/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S115606517","display_name":"Frontiers in Neurorobotics","issn_l":"1662-5218","issn":["1662-5218"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Neurorobotics","raw_type":"journal-article"},{"id":"pmid:38566892","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38566892","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in neurorobotics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10985319","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10985319","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10985319/pdf/fnbot-18-1338189.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Neurorobot","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:f6f2ec78b1b342ca8a6d2daee4814077","is_oa":true,"landing_page_url":"https://doaj.org/article/f6f2ec78b1b342ca8a6d2daee4814077","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Neurorobotics, Vol 18 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/fnbot.2024.1338189","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fnbot.2024.1338189","pdf_url":"https://www.frontiersin.org/articles/10.3389/fnbot.2024.1338189/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S115606517","display_name":"Frontiers in Neurorobotics","issn_l":"1662-5218","issn":["1662-5218"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Neurorobotics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/11"}],"awards":[{"id":"https://openalex.org/G7470181681","display_name":null,"funder_award_id":"B08004","funder_id":"https://openalex.org/F4320327912","funder_display_name":"Higher Education Discipline Innovation Project"}],"funders":[{"id":"https://openalex.org/F4320327912","display_name":"Higher Education Discipline Innovation Project","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4392966039.pdf"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1658008008","https://openalex.org/W2121092017","https://openalex.org/W2145339207","https://openalex.org/W2168359464","https://openalex.org/W2291973609","https://openalex.org/W2306644740","https://openalex.org/W2343568200","https://openalex.org/W2607713949","https://openalex.org/W2745868649","https://openalex.org/W2904246096","https://openalex.org/W2944851425","https://openalex.org/W2957120403","https://openalex.org/W2962854145","https://openalex.org/W2968983352","https://openalex.org/W2990123902","https://openalex.org/W3021208093","https://openalex.org/W3033529678","https://openalex.org/W3035700320","https://openalex.org/W3080764280","https://openalex.org/W3094502228","https://openalex.org/W3103677861","https://openalex.org/W3127561923","https://openalex.org/W3169291081","https://openalex.org/W3210290940","https://openalex.org/W3211352205","https://openalex.org/W4225773281","https://openalex.org/W4285071848","https://openalex.org/W4285227658","https://openalex.org/W4287078276","https://openalex.org/W4287126489","https://openalex.org/W4298023569","https://openalex.org/W4298857966","https://openalex.org/W4301409532","https://openalex.org/W4309793872","https://openalex.org/W4385245566","https://openalex.org/W6637133156","https://openalex.org/W6677939520","https://openalex.org/W6684205842","https://openalex.org/W6739901393","https://openalex.org/W6751659697","https://openalex.org/W6752961934","https://openalex.org/W6763509872","https://openalex.org/W6765215732","https://openalex.org/W6768810269","https://openalex.org/W6785148927","https://openalex.org/W6796289742","https://openalex.org/W6798316476","https://openalex.org/W6804244202"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W2145836866","https://openalex.org/W4206233823","https://openalex.org/W2494202692"],"abstract_inverted_index":{"In":[0],"real-world":[1],"scenarios,":[2],"making":[3],"navigation":[4,72],"decisions":[5],"for":[6,38],"autonomous":[7,87],"driving":[8],"involves":[9,150],"a":[10,52,138,154,217],"sequential":[11],"set":[12],"of":[13,23,30,54,81,86,143,153,164,178,207,224],"steps.":[14],"These":[15],"judgments":[16],"are":[17,200],"made":[18],"based":[19],"on":[20],"partial":[21],"observations":[22,118],"the":[24,27,31,47,79,83,101,114,151,162,165,186,204,208,225,233],"environment,":[25,226],"while":[26],"underlying":[28],"model":[29,113],"environment":[32],"remains":[33],"unknown.":[34],"A":[35],"prevalent":[36],"method":[37],"resolving":[39],"such":[40],"issues":[41],"is":[42,98],"reinforcement":[43,70],"learning,":[44],"in":[45,56,90,117,124,169],"which":[46,185],"agent":[48],"acquires":[49],"knowledge":[50,223],"through":[51],"succession":[53],"rewards":[55],"addition":[57],"to":[58,77,111,132,202],"fragmentary":[59],"and":[60,119,183,236],"noisy":[61],"observations.":[62],"This":[63,121,158],"study":[64],"introduces":[65],"an":[66],"algorithm":[67],"named":[68],"deep":[69],"learning":[71],"via":[73],"decision":[74],"transformer":[75],"(DRLNDT)":[76],"address":[78],"challenge":[80],"enhancing":[82],"decision-making":[84],"capabilities":[85],"vehicles":[88],"operating":[89],"partially":[91],"observable":[92],"urban":[93],"environments.":[94],"The":[95,141,173],"DRLNDT":[96,106,214],"framework":[97],"built":[99],"around":[100],"Soft":[102],"Actor-Critic":[103],"(SAC)":[104],"algorithm.":[105],"utilizes":[107],"Transformer":[108],"neural":[109],"networks":[110],"effectively":[112,160],"temporal":[115],"dependencies":[116],"actions.":[120],"approach":[122],"aids":[123],"mitigating":[125],"judgment":[126],"errors":[127],"that":[128,213,240],"may":[129,215],"arise":[130],"due":[131],"sensor":[133],"noise":[134],"or":[135,229],"occlusion":[136],"within":[137],"given":[139],"state.":[140],"process":[142],"extracting":[144],"latent":[145,194],"vectors":[146,195],"from":[147,197],"high-quality":[148,198],"images":[149,199],"utilization":[152],"variational":[155],"autoencoder":[156],"(VAE).":[157],"technique":[159,235],"reduces":[161],"dimensionality":[163],"state":[166,175],"space,":[167],"resulting":[168],"enhanced":[170],"training":[171],"efficiency.":[172],"multimodal":[174],"space":[176],"consists":[177],"vector":[179],"states,":[180],"including":[181],"velocity":[182],"position,":[184],"vehicle's":[187],"intrinsic":[188],"sensors":[189],"can":[190],"readily":[191],"obtain.":[192],"Additionally,":[193],"derived":[196],"incorporated":[201],"facilitate":[203],"Agent's":[205],"assessment":[206],"present":[209],"trajectory.":[210],"Experiments":[211],"demonstrate":[212],"achieve":[216],"superior":[218],"optimal":[219],"policy":[220,238],"without":[221],"prior":[222],"detailed":[227],"maps,":[228],"routing":[230],"assistance,":[231],"surpassing":[232],"baseline":[234],"other":[237],"methods":[239],"lack":[241],"historical":[242],"data.":[243]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}