{"id":"https://openalex.org/W3037606473","doi":"https://doi.org/10.1109/lra.2020.3005126","title":"Efficient Sampling-Based Maximum Entropy Inverse Reinforcement Learning With Application to Autonomous Driving","display_name":"Efficient Sampling-Based Maximum Entropy Inverse Reinforcement Learning With Application to Autonomous Driving","publication_year":2020,"publication_date":"2020-06-25","ids":{"openalex":"https://openalex.org/W3037606473","doi":"https://doi.org/10.1109/lra.2020.3005126","mag":"3037606473"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2020.3005126","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2020.3005126","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5101590595","display_name":"Zheng Wu","orcid":"https://orcid.org/0000-0001-7147-173X"},"institutions":[{"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":"Zheng Wu","raw_affiliation_strings":["Department of Mechanical Engineering, University of California, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087667477","display_name":"Liting Sun","orcid":"https://orcid.org/0000-0002-1248-2137"},"institutions":[{"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":"Liting Sun","raw_affiliation_strings":["Department of Mechanical Engineering, University of California, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1248-2137","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101770873","display_name":"Wei Zhan","orcid":"https://orcid.org/0000-0002-1474-1200"},"institutions":[{"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":"Wei Zhan","raw_affiliation_strings":["Department of Mechanical Engineering, University of California, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101678004","display_name":"Chenyu Yang","orcid":"https://orcid.org/0000-0002-0346-7541"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyu Yang","raw_affiliation_strings":["Department of Computer Science, Shanghai Jiaotong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Shanghai Jiaotong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064077634","display_name":"Masayoshi Tomizuka","orcid":"https://orcid.org/0000-0003-0206-6639"},"institutions":[{"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":"Masayoshi Tomizuka","raw_affiliation_strings":["Department of Mechanical Engineering, University of California, Berkeley, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0206-6639","affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2855,"has_fulltext":false,"cited_by_count":125,"citation_normalized_percentile":{"value":0.96428184,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"5","issue":"4","first_page":"5355","last_page":"5362"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9970999956130981,"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":0.9941999912261963,"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":0.7678946256637573},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7446791529655457},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5113162994384766},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4912082552909851},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4652441740036011},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4520823359489441},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.45036858320236206},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.43132826685905457},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.42870187759399414},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11021509766578674}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7678946256637573},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7446791529655457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5113162994384766},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4912082552909851},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4652441740036011},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4520823359489441},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.45036858320236206},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43132826685905457},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.42870187759399414},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11021509766578674},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2020.3005126","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2020.3005126","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W195033972","https://openalex.org/W1527702126","https://openalex.org/W1591675293","https://openalex.org/W1801976851","https://openalex.org/W1970916399","https://openalex.org/W1971086298","https://openalex.org/W1994648061","https://openalex.org/W1999874108","https://openalex.org/W2098774185","https://openalex.org/W2144913588","https://openalex.org/W2209116470","https://openalex.org/W2290104316","https://openalex.org/W2331890423","https://openalex.org/W2562817597","https://openalex.org/W2793066675","https://openalex.org/W2800727637","https://openalex.org/W2891385160","https://openalex.org/W2891559771","https://openalex.org/W2909906617","https://openalex.org/W2963787234","https://openalex.org/W2980087597","https://openalex.org/W2999620783","https://openalex.org/W3003808276","https://openalex.org/W3103105396","https://openalex.org/W3156047532","https://openalex.org/W6607786297","https://openalex.org/W6635261211","https://openalex.org/W6638440308","https://openalex.org/W6674884181","https://openalex.org/W6688386007","https://openalex.org/W6696380822","https://openalex.org/W6768870957","https://openalex.org/W6794156337"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W3162204513","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548"],"abstract_inverted_index":{"In":[0],"the":[1,10,28,47,68,136,142,146,151,161,179],"past":[2],"decades,":[3],"we":[4,36,62,75,110],"have":[5],"witnessed":[6],"significant":[7],"progress":[8,53],"in":[9,121,145,153],"domain":[11,148],"of":[12,65],"autonomous":[13,92],"driving.":[14],"Advanced":[15],"techniques":[16],"based":[17],"on":[18],"optimization":[19],"and":[20,40,50,88,98,103,171,191],"reinforcement":[21,117],"learning":[22,118],"become":[23],"increasingly":[24],"powerful":[25],"when":[26],"solving":[27],"forward":[29],"problem:":[30],"given":[31],"designed":[32],"reward/cost":[33],"functions,":[34,70],"how":[35],"should":[37,61],"optimize":[38,83],"them":[39],"obtain":[41],"driving":[42,166],"policies":[43],"that":[44,74,90,178],"interact":[45],"with":[46,187],"environment":[48],"safely":[49],"efficiently.":[51],"Such":[52],"has":[54],"raised":[55],"another":[56],"equally":[57],"important":[58],"question:":[59],"what":[60,78],"optimize?":[63],"Instead":[64],"manually":[66],"specifying":[67],"reward":[69,143],"it":[71],"is":[72],"desired":[73],"can":[76,139],"extract":[77],"human":[79,157],"drivers":[80],"try":[81],"to":[82,91,94,195],"from":[84,125,156],"real":[85],"traffic":[86],"data":[87],"assign":[89],"vehicles":[93],"enable":[95],"more":[96,183],"naturalistic":[97],"transparent":[99],"interaction":[100],"between":[101],"humans":[102],"intelligent":[104],"agents.":[105],"To":[106],"address":[107],"this":[108,122],"issue,":[109],"present":[111],"an":[112,131],"efficient":[113,132],"sampling-based":[114],"maximum-entropy":[115],"inverse":[116],"(IRL)":[119],"algorithm":[120,138,163,181],"letter.":[123],"Different":[124],"existing":[126],"IRL":[127,198],"algorithms,":[128],"by":[129],"introducing":[130],"continuous-domain":[133],"trajectory":[134],"sampler,":[135],"proposed":[137,162,180],"directly":[140],"learn":[141],"functions":[144],"continuous":[147],"while":[149],"considering":[150],"uncertainties":[152],"demonstrated":[154],"trajectories":[155],"drivers.":[158],"We":[159],"evaluate":[160],"via":[164],"real-world":[165],"data,":[167],"including":[168],"both":[169],"non-interactive":[170],"interactive":[172],"scenarios.":[173],"The":[174],"experimental":[175],"results":[176],"show":[177],"achieves":[182],"accurate":[184],"prediction":[185],"performance":[186],"faster":[188],"convergence":[189],"speed":[190],"better":[192],"generalization":[193],"compared":[194],"other":[196],"baseline":[197],"algorithms.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":32},{"year":2024,"cited_by_count":23},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":8}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}