{"id":"https://openalex.org/W2896288931","doi":"https://doi.org/10.1109/ivs.2018.8500666","title":"Inverse Reinforcement Learning via Neural Network in Driver Behavior Modeling","display_name":"Inverse Reinforcement Learning via Neural Network in Driver Behavior Modeling","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2896288931","doi":"https://doi.org/10.1109/ivs.2018.8500666","mag":"2896288931"},"language":"en","primary_location":{"id":"doi:10.1109/ivs.2018.8500666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ivs.2018.8500666","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5048867734","display_name":"Qijie Zou","orcid":"https://orcid.org/0000-0003-2580-1560"},"institutions":[{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"QiJie Zou","raw_affiliation_strings":["BeiDou High Precision Positioning Service Technology Engineering Laboratory Information Engineering College, Dalian University, DaLian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BeiDou High Precision Positioning Service Technology Engineering Laboratory Information Engineering College, Dalian University, DaLian, China","institution_ids":["https://openalex.org/I4210092944"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100358570","display_name":"Haoyu Li","orcid":"https://orcid.org/0000-0002-7138-8263"},"institutions":[{"id":"https://openalex.org/I4210092944","display_name":"Dalian University","ror":"https://ror.org/00g2ypp58","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210092944"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyu Li","raw_affiliation_strings":["BeiDou High Precision Positioning Service Technology Engineering Laboratory Information Engineering College, Dalian University, DaLian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BeiDou High Precision Positioning Service Technology Engineering Laboratory Information Engineering College, Dalian University, DaLian, China","institution_ids":["https://openalex.org/I4210092944"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101735545","display_name":"Rubo Zhang","orcid":"https://orcid.org/0000-0002-3211-6273"},"institutions":[{"id":"https://openalex.org/I61565387","display_name":"Dalian Minzu University","ror":"https://ror.org/02hxfx521","country_code":"CN","type":"education","lineage":["https://openalex.org/I61565387"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rubo Zhang","raw_affiliation_strings":["Mechanical and Electrical Engineering College, Dalian Minzu University, DaLian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mechanical and Electrical Engineering College, Dalian Minzu University, DaLian, China","institution_ids":["https://openalex.org/I61565387"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1245","last_page":"1250"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9990000128746033,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9975000023841858,"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/T10524","display_name":"Traffic control and management","score":0.9933000206947327,"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/computer-science","display_name":"Computer science","score":0.7471047639846802},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7290419340133667},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.696657657623291},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6560323238372803},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6107019782066345},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5816437602043152},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5525988936424255},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5123683214187622},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48670271039009094},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4832506775856018},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4791783094406128},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.47904789447784424},{"id":"https://openalex.org/keywords/inverse-function","display_name":"Inverse function","score":0.45673251152038574},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.43527644872665405},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.42176929116249084},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4196184575557709},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.4126991331577301},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.30808472633361816},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21258699893951416},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.1896764039993286},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13229280710220337},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11397579312324524}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7471047639846802},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7290419340133667},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.696657657623291},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6560323238372803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6107019782066345},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5816437602043152},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5525988936424255},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5123683214187622},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48670271039009094},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4832506775856018},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4791783094406128},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.47904789447784424},{"id":"https://openalex.org/C140528856","wikidata":"https://www.wikidata.org/wiki/Q191884","display_name":"Inverse function","level":3,"score":0.45673251152038574},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.43527644872665405},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.42176929116249084},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4196184575557709},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4126991331577301},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.30808472633361816},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21258699893951416},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.1896764039993286},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13229280710220337},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11397579312324524},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ivs.2018.8500666","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ivs.2018.8500666","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W640212618","https://openalex.org/W1577754176","https://openalex.org/W1968199746","https://openalex.org/W1977655452","https://openalex.org/W1994955764","https://openalex.org/W1998327697","https://openalex.org/W2000478733","https://openalex.org/W2062431576","https://openalex.org/W2064355448","https://openalex.org/W2073750743","https://openalex.org/W2142578527","https://openalex.org/W2342840547","https://openalex.org/W2953319434"],"related_works":["https://openalex.org/W2152670157","https://openalex.org/W2386410636","https://openalex.org/W176737593","https://openalex.org/W2808418668","https://openalex.org/W2903299703","https://openalex.org/W2156021013","https://openalex.org/W2016648086","https://openalex.org/W3105579180","https://openalex.org/W4399157305","https://openalex.org/W2807018115"],"abstract_inverted_index":{"Inverse":[0],"Reinforcement":[1],"Learning(IRL)":[2],"is":[3,50],"formulated":[4],"within":[5],"the":[6,30,40,60,70,80,92,111,137,143,150,157,164,173,180,185],"framework":[7],"of":[8,56,72,175,193],"Markov":[9],"decision":[10],"process(MDP)":[11],"where":[12,22],"we":[13,24,33,126],"are":[14,83],"not":[15],"explicitly":[16],"given":[17],"a":[18,46,53,190,199],"reward":[19,47,61,112],"function,":[20],"but":[21],"instead":[23],"can":[25,88],"observe":[26],"an":[27,98],"expert":[28,41],"demonstrating":[29],"task":[31],"that":[32,49,172],"want":[34],"to":[35,37,44,69,96,104,141,155],"learn":[36],"perform.":[38],"Then":[39],"as":[42,52,76],"trying":[43],"maximize":[45],"function":[48],"expressible":[51],"linear":[54],"combination":[55],"known":[57],"features":[58],"specifying":[59],"function.":[62],"However,":[63],"in":[64,118,179,184],"autonomous":[65],"driving":[66,129],"tasks,":[67],"due":[68],"difference":[71],"scene":[73,188],"factor,":[74],"such":[75],"obstacle":[77],"and":[78,86,148,183],"weather,":[79],"state":[81,121,145],"spaces":[82],"frequently":[84],"large":[85,191],"demonstrations":[87],"hardly":[89],"visit":[90],"all":[91],"states.":[93],"it's":[94],"hard":[95],"get":[97],"optimal":[99],"policy":[100,151],"with":[101,115,132,163,189],"RL":[102],"method":[103,117,134,167,197],"express":[105,149],"driver":[106],"behavior":[107,130],"model":[108],"based":[109],"on":[110,128,168],"which":[113,135],"recovered":[114],"IRL":[116,133],"this":[119,124,196],"large-scale":[120],"space.":[122],"In":[123],"paper,":[125],"focus":[127],"modeling":[131],"introduces":[136],"convolutional":[138],"neural":[139,153],"network":[140,154],"extract":[142],"associated":[144],"feature":[146],"automatically,":[147],"by":[152],"generalize":[156],"expert's":[158],"behaviors.":[159],"Experimental":[160],"results":[161],"compared":[162],"traditional":[165],"end-to-end":[166],"simulated":[169],"vehicle":[170],"show":[171],"accuracy":[174],"decision-making":[176],"greatly":[177],"improved":[178],"train":[181],"curve,":[182],"new":[186],"curve":[187],"number":[192],"unvisited":[194],"state,":[195],"shows":[198],"perfect":[200],"generalization":[201],"efficiency.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}