{"id":"https://openalex.org/W2769287835","doi":"https://doi.org/10.1177/0278364918772017","title":"Risk-sensitive inverse reinforcement learning via semi- and non-parametric methods","display_name":"Risk-sensitive inverse reinforcement learning via semi- and non-parametric methods","publication_year":2018,"publication_date":"2018-05-22","ids":{"openalex":"https://openalex.org/W2769287835","doi":"https://doi.org/10.1177/0278364918772017","mag":"2769287835"},"language":"en","primary_location":{"id":"doi:10.1177/0278364918772017","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0278364918772017","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1711.10055","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101898346","display_name":"Sumeet Singh","orcid":"https://orcid.org/0000-0003-4510-5853"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sumeet Singh","raw_affiliation_strings":["Department of Aeronautics and Astronautics, Stanford University, USA"],"raw_orcid":"https://orcid.org/0000-0003-4510-5853","affiliations":[{"raw_affiliation_string":"Department of Aeronautics and Astronautics, Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064802020","display_name":"Jonathan Lacotte","orcid":"https://orcid.org/0000-0003-2041-9311"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Lacotte","raw_affiliation_strings":["Department of Electrical Engineering, Stanford University, USA","Dept. of Electrical Engineering Stanford University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Dept. of Electrical Engineering Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013839863","display_name":"Anirudha Majumdar","orcid":null},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anirudha Majumdar","raw_affiliation_strings":["Department of Mechanical and Aerospace Engineering, Princeton University, USA","Mechanical & Aerospace Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical and Aerospace Engineering, Princeton University, USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Mechanical & Aerospace Engineering","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050003000","display_name":"Marco Pavone","orcid":"https://orcid.org/0000-0002-0206-4337"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marco Pavone","raw_affiliation_strings":["Department of Aeronautics and Astronautics, Stanford University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Aeronautics and Astronautics, Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2199,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52869724,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":"37","issue":"13-14","first_page":"1713","last_page":"1740"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10370","display_name":"Traffic and Road Safety","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"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/T10370","display_name":"Traffic and Road Safety","score":0.9909999966621399,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9725000262260437,"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/T10315","display_name":"Decision-Making and Behavioral Economics","score":0.9639000296592712,"subfield":{"id":"https://openalex.org/subfields/1800","display_name":"General Decision Sciences"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6886664032936096},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6352155804634094},{"id":"https://openalex.org/keywords/risk-neutral","display_name":"Risk neutral","score":0.5130420923233032},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4973640739917755},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4567926228046417},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4272615909576416},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3866842985153198},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3659520149230957},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.26671767234802246},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16403645277023315},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1495622992515564},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08407649397850037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6886664032936096},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6352155804634094},{"id":"https://openalex.org/C2780910948","wikidata":"https://www.wikidata.org/wiki/Q2154775","display_name":"Risk neutral","level":2,"score":0.5130420923233032},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4973640739917755},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4567926228046417},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4272615909576416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3866842985153198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3659520149230957},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.26671767234802246},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16403645277023315},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1495622992515564},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08407649397850037},{"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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","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":4,"locations":[{"id":"doi:10.1177/0278364918772017","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0278364918772017","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1711.10055","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1711.10055","pdf_url":"https://arxiv.org/pdf/1711.10055","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1711.10055","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1711.10055","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:2769287835","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1711.10055","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1711.10055","pdf_url":"https://arxiv.org/pdf/1711.10055","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7900000214576721}],"awards":[{"id":"https://openalex.org/G6156054438","display_name":null,"funder_award_id":"N00014-15-1-2673","funder_id":"https://openalex.org/F4320338298","funder_display_name":"Office of Naval Research Global"}],"funders":[{"id":"https://openalex.org/F4320338298","display_name":"Office of Naval Research Global","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2769287835.pdf","grobid_xml":"https://content.openalex.org/works/W2769287835.grobid-xml"},"referenced_works_count":71,"referenced_works":["https://openalex.org/W174509281","https://openalex.org/W580164506","https://openalex.org/W1527702126","https://openalex.org/W1585575029","https://openalex.org/W1647779468","https://openalex.org/W1929981607","https://openalex.org/W1965878388","https://openalex.org/W1987073631","https://openalex.org/W1996625075","https://openalex.org/W1999874108","https://openalex.org/W2001009060","https://openalex.org/W2001697694","https://openalex.org/W2012997954","https://openalex.org/W2019291268","https://openalex.org/W2027047704","https://openalex.org/W2027106436","https://openalex.org/W2037997802","https://openalex.org/W2042223112","https://openalex.org/W2056819186","https://openalex.org/W2057510529","https://openalex.org/W2061562262","https://openalex.org/W2064942524","https://openalex.org/W2067477904","https://openalex.org/W2077673559","https://openalex.org/W2078864591","https://openalex.org/W2088413745","https://openalex.org/W2098000549","https://openalex.org/W2098774185","https://openalex.org/W2101075098","https://openalex.org/W2101821104","https://openalex.org/W2104346961","https://openalex.org/W2105947986","https://openalex.org/W2109122936","https://openalex.org/W2132527237","https://openalex.org/W2133469585","https://openalex.org/W2144846366","https://openalex.org/W2145341417","https://openalex.org/W2147707995","https://openalex.org/W2155866677","https://openalex.org/W2162849300","https://openalex.org/W2165428239","https://openalex.org/W2169206416","https://openalex.org/W2227909145","https://openalex.org/W2290104316","https://openalex.org/W2294586855","https://openalex.org/W2333311386","https://openalex.org/W2411577903","https://openalex.org/W2531491639","https://openalex.org/W2536620281","https://openalex.org/W2560555438","https://openalex.org/W2561666900","https://openalex.org/W2565370028","https://openalex.org/W2570532759","https://openalex.org/W2599958883","https://openalex.org/W2734346390","https://openalex.org/W2950270546","https://openalex.org/W2950465931","https://openalex.org/W2954940391","https://openalex.org/W2962951833","https://openalex.org/W2963584844","https://openalex.org/W2983690517","https://openalex.org/W3011865677","https://openalex.org/W3021487874","https://openalex.org/W3022853033","https://openalex.org/W3106238320","https://openalex.org/W3122620151","https://openalex.org/W3124407081","https://openalex.org/W3125893104","https://openalex.org/W3125997868","https://openalex.org/W3215946589","https://openalex.org/W4254077898"],"related_works":["https://openalex.org/W2892124927","https://openalex.org/W3183345341","https://openalex.org/W2736273880","https://openalex.org/W3163277370","https://openalex.org/W3191940631","https://openalex.org/W3033230862","https://openalex.org/W3038745855","https://openalex.org/W2904188519","https://openalex.org/W3158992539","https://openalex.org/W3214411709","https://openalex.org/W3129059619","https://openalex.org/W2772798595","https://openalex.org/W3213949275","https://openalex.org/W3033510099","https://openalex.org/W2989664601","https://openalex.org/W3002749996","https://openalex.org/W3105461370","https://openalex.org/W3036513508","https://openalex.org/W3185990877","https://openalex.org/W2129929734"],"abstract_inverted_index":{"The":[0,133],"literature":[1],"on":[2,76,103,110,138],"inverse":[3],"reinforcement":[4],"learning":[5],"(IRL)":[6],"typically":[7],"assumes":[8],"that":[9,23,185],"humans":[10,24,31],"take":[11],"actions":[12],"to":[13,49,57,83,94,151,167],"minimize":[14],"the":[15,43,177,186],"expected":[16],"value":[17],"of":[18,45,73,88,127,158,176],"a":[19,51,61,70,115,124,139,155,171,181],"cost":[20,121],"function,":[21],"i.e.,":[22],"are":[25,32],"risk":[26,37,63,78,89,92,118,165,168],"neutral.":[27,38],"Yet,":[28],"in":[29,170,200],"practice,":[30],"often":[33],"far":[34],"from":[35,91,163],"being":[36],"To":[39,65],"fill":[40],"this":[41,46,66],"gap,":[42],"objective":[44],"paper":[47],"is":[48,136,149],"devise":[50],"framework":[52,188],"for":[53,60,113,123],"risk-sensitive":[54],"(RS)":[55],"IRL":[56],"explicitly":[58],"account":[59],"human\u2019s":[62,116],"sensitivity.":[64],"end,":[67],"we":[68],"propose":[69,98],"flexible":[71],"class":[72,126],"models":[74],"based":[75,102,109],"coherent":[77],"measures,":[79],"which":[80],"allow":[81],"us":[82],"capture":[84],"an":[85],"entire":[86],"spectrum":[87],"preferences":[90],"neutral":[93,169],"worst":[95],"case.":[96],"We":[97],"efficient":[99],"non-parametric":[100],"algorithms":[101,108],"linear":[104],"programming":[105],"and":[106,120,129,153,197],"semi-parametric":[107],"maximum":[111],"likelihood":[112],"inferring":[114],"underlying":[117],"measure":[119],"function":[122],"rich":[125],"static":[128],"dynamic":[130],"decision-making":[131],"settings.":[132],"resulting":[134],"approach":[135,179],"demonstrated":[137],"simulated":[140],"driving":[141,161],"game":[142],"with":[143,180],"10":[144],"human":[145],"participants.":[146],"Our":[147],"method":[148],"able":[150],"infer":[152],"mimic":[154],"wide":[156],"range":[157],"qualitatively":[159,196],"different":[160],"styles":[162],"highly":[164],"averse":[166],"data-efficient":[172],"manner.":[173],"Moreover,":[174],"comparisons":[175],"RS-IRL":[178,187],"risk-neutral":[182],"model":[183],"show":[184],"more":[189],"accurately":[190],"captures":[191],"observed":[192],"participant":[193],"behavior":[194],"both":[195],"quantitatively,":[198],"especially":[199],"scenarios":[201],"where":[202],"catastrophic":[203],"outcomes":[204],"such":[205],"as":[206],"collisions":[207],"can":[208],"occur.":[209]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2022-10-01T00:00:00"}