{"id":"https://openalex.org/W2991138762","doi":"https://doi.org/10.1109/itsc.2019.8916952","title":"Accelerated Inverse Reinforcement Learning with Randomly Pre-sampled Policies for Autonomous Driving Reward Design","display_name":"Accelerated Inverse Reinforcement Learning with Randomly Pre-sampled Policies for Autonomous Driving Reward Design","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2991138762","doi":"https://doi.org/10.1109/itsc.2019.8916952","mag":"2991138762"},"language":"en","primary_location":{"id":"doi:10.1109/itsc.2019.8916952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc.2019.8916952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","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/A5101532324","display_name":"Long Xin","orcid":"https://orcid.org/0000-0002-4849-1959"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Xin","raw_affiliation_strings":["State Key Laboratory of Automotive Safety and Energy and School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Safety and Energy and School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100747108","display_name":"Shengbo Eben Li","orcid":"https://orcid.org/0000-0003-4923-3633"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengbo Eben Li","raw_affiliation_strings":["State Key Laboratory of Automotive Safety and Energy and School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Safety and Energy and School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044924773","display_name":"Pin Wang","orcid":"https://orcid.org/0000-0002-4214-0488"},"institutions":[{"id":"https://openalex.org/I1304598786","display_name":"Program for Appropriate Technology in Health","ror":"https://ror.org/02ycvrx49","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1304598786"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pin Wang","raw_affiliation_strings":["California PATH, University of California, Berkeley, Richmond, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"California PATH, University of California, Berkeley, Richmond, CA, USA","institution_ids":["https://openalex.org/I1304598786","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102751432","display_name":"Wenhan Cao","orcid":"https://orcid.org/0009-0001-1367-4210"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhan Cao","raw_affiliation_strings":["State Key Laboratory of Automotive Safety and Energy and School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Safety and Energy and School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037502323","display_name":"Bingbing Nie","orcid":"https://orcid.org/0000-0002-8529-8613"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingbing Nie","raw_affiliation_strings":["State Key Laboratory of Automotive Safety and Energy and School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Safety and Energy and School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014661259","display_name":"Ching\u2010Yao Chan","orcid":"https://orcid.org/0000-0003-3992-2312"},"institutions":[{"id":"https://openalex.org/I1304598786","display_name":"Program for Appropriate Technology in Health","ror":"https://ror.org/02ycvrx49","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1304598786"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ching-Yao Chan","raw_affiliation_strings":["California PATH, University of California, Berkeley, Richmond, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"California PATH, University of California, Berkeley, Richmond, CA, USA","institution_ids":["https://openalex.org/I1304598786","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100640936","display_name":"Bo Cheng","orcid":"https://orcid.org/0000-0002-1753-2922"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Cheng","raw_affiliation_strings":["State Key Laboratory of Automotive Safety and Energy and School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Automotive Safety and Energy and School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8747,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.80719679,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2757","last_page":"2764"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9984999895095825,"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":0.9927999973297119,"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/trajectory","display_name":"Trajectory","score":0.8487858772277832},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8243280053138733},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7264191508293152},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5850043892860413},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5219654440879822},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.5107736587524414},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5060147643089294},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.5059582591056824},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36718565225601196},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.33974868059158325},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.199310302734375}],"concepts":[{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.8487858772277832},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8243280053138733},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7264191508293152},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5850043892860413},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5219654440879822},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.5107736587524414},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5060147643089294},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.5059582591056824},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36718565225601196},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33974868059158325},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.199310302734375},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc.2019.8916952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc.2019.8916952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W630739203","https://openalex.org/W1527702126","https://openalex.org/W1929981607","https://openalex.org/W1992610163","https://openalex.org/W1999874108","https://openalex.org/W2032558547","https://openalex.org/W2061562262","https://openalex.org/W2098774185","https://openalex.org/W2100401322","https://openalex.org/W2133068870","https://openalex.org/W2168577686","https://openalex.org/W2169498096","https://openalex.org/W2181849516","https://openalex.org/W2897676672","https://openalex.org/W2905301806","https://openalex.org/W2963322416","https://openalex.org/W2970619889","https://openalex.org/W3002044607","https://openalex.org/W6640443443","https://openalex.org/W6674884181","https://openalex.org/W6675341372","https://openalex.org/W6679958247","https://openalex.org/W6685962732"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4323768008","https://openalex.org/W1941703695","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W3131574667","https://openalex.org/W4391331176"],"abstract_inverted_index":{"To":[0],"learn":[1],"a":[2,6],"reward":[3,56,171],"function":[4,172],"that":[5,31,149],"driver":[7],"adheres":[8],"to":[9,13,155],"is":[10,25,124],"of":[11,17,27,44,78,163],"importance":[12],"the":[14,28,41,67,84,99,114,118,158,164,169],"human-like":[15],"design":[16],"autonomous":[18,135],"driving":[19,146],"systems.":[20],"Inverse":[21],"reinforcement":[22,49],"learning":[23,50,129],"(IRL)":[24],"one":[26],"recent":[29],"advances":[30],"can":[32],"achieve":[33],"this":[34],"objective,":[35],"but":[36],"it":[37,80,150],"often":[38],"suffers":[39],"from":[40],"low":[42],"efficiency":[43,130],"generating":[45],"optimal":[46,68,95],"policy":[47,69,86],"by":[48,65,104,112],"(RL)":[51],"each":[52],"time":[53],"when":[54],"updating":[55],"weights.":[57],"This":[58],"paper":[59],"presents":[60],"an":[61,94],"accelerated":[62],"IRL":[63],"method":[64,123],"approaching":[66],"among":[70],"randomly":[71],"pre-sampled":[72,105],"policies":[73,139],"in":[74,83,98],"designed":[75],"sub-space":[76],"instead":[77],"finding":[79],"through":[81],"RL":[82],"whole":[85],"space.":[87],"The":[88,107,121],"corresponding":[89],"trajectories":[90,116,166],"are":[91,110,140],"targeted":[92],"via":[93],"trajectory":[96,101],"selector":[97],"candidate":[100],"library":[102],"generated":[103],"policies.":[106],"weights":[108],"then":[109],"updated":[111],"comparing":[113],"selected":[115],"and":[117],"expert":[119,138],"ones.":[120],"proposed":[122],"very":[125],"suitable":[126],"for":[127,131],"improving":[128],"low-dimensional":[132],"problems":[133],"like":[134],"driving,":[136],"whose":[137],"nearly":[141],"tractable.":[142],"Results":[143],"with":[144],"simulated":[145],"data":[147],"show":[148],"only":[151,174],"took":[152],"11":[153],"iterations":[154],"converge,":[156],"while":[157],"average":[159],"longitudinal":[160],"RMS":[161],"error":[162],"recovered":[165],"based":[167],"on":[168],"learned":[170],"was":[173],"2.14m.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}