{"id":"https://openalex.org/W2783922473","doi":"https://doi.org/10.1109/cdc.2017.8264535","title":"Gradient-based inverse risk-sensitive reinforcement learning","display_name":"Gradient-based inverse risk-sensitive reinforcement learning","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2783922473","doi":"https://doi.org/10.1109/cdc.2017.8264535","mag":"2783922473"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2017.8264535","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2017.8264535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 56th Annual Conference on Decision and Control (CDC)","raw_type":"proceedings-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/A5089549365","display_name":"Eric Mazumdar","orcid":"https://orcid.org/0000-0002-1815-269X"},"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":true,"raw_author_name":"Eric Mazumdar","raw_affiliation_strings":["Electrical Engineering and Computer Sciences Department at the University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Sciences Department at the University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008161296","display_name":"Lillian J. Ratliff","orcid":"https://orcid.org/0000-0001-8936-0229"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lillian J. Ratliff","raw_affiliation_strings":["Electrical Engineering Department at the University of Washington, Seattle"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering Department at the University of Washington, Seattle","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065508644","display_name":"Tanner Fiez","orcid":"https://orcid.org/0000-0003-0005-3009"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tanner Fiez","raw_affiliation_strings":["Electrical Engineering Department at the University of Washington, Seattle"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering Department at the University of Washington, Seattle","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103101043","display_name":"S. Shankar Sastry","orcid":null},"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":"S. Shankar Sastry","raw_affiliation_strings":["Electrical Engineering and Computer Sciences Department at the University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering and Computer Sciences Department at the University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5089549365"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.713,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.76647237,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5796","last_page":"5801"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11942","display_name":"Transportation and Mobility Innovations","score":0.9998000264167786,"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/T11942","display_name":"Transportation and Mobility Innovations","score":0.9998000264167786,"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/T10768","display_name":"Electric Vehicles and Infrastructure","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10298","display_name":"Urban Transport and Accessibility","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8598518967628479},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6890512704849243},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6426017880439758},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5295672416687012},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5289566516876221},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5183573365211487},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.44518017768859863},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.4282096028327942},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4203246831893921},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.4193151593208313},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40461403131484985},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.370689332485199},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17408493161201477},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11196708679199219},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08796072006225586},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.08249929547309875}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8598518967628479},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6890512704849243},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6426017880439758},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5295672416687012},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5289566516876221},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5183573365211487},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.44518017768859863},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4282096028327942},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4203246831893921},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.4193151593208313},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40461403131484985},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.370689332485199},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17408493161201477},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11196708679199219},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08796072006225586},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.08249929547309875},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cdc.2017.8264535","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2017.8264535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 56th Annual Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:authors.library.caltech.edu:110738","is_oa":false,"landing_page_url":"https://authors.library.caltech.edu/110738/","pdf_url":null,"source":{"id":"https://openalex.org/S4306402161","display_name":"CaltechAUTHORS (California Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122411786","host_organization_name":"California Institute of Technology","host_organization_lineage":["https://openalex.org/I122411786"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Book Section"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1557270667","https://openalex.org/W1585575029","https://openalex.org/W1588514005","https://openalex.org/W1982921646","https://openalex.org/W1986646649","https://openalex.org/W2019291268","https://openalex.org/W2030874315","https://openalex.org/W2041946752","https://openalex.org/W2046396733","https://openalex.org/W2067893130","https://openalex.org/W2088646424","https://openalex.org/W2096452841","https://openalex.org/W2107431923","https://openalex.org/W2133469585","https://openalex.org/W2169206416","https://openalex.org/W2205644127","https://openalex.org/W2599958883","https://openalex.org/W2962951833","https://openalex.org/W3011865677","https://openalex.org/W3104184956","https://openalex.org/W3125893104","https://openalex.org/W4229984434","https://openalex.org/W4245409838"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W2379651310"],"abstract_inverted_index":{"We":[0,43,61],"address":[1],"the":[2,13,58,63,66,72,77,83,96,111,117],"problem":[3],"of":[4,30,32,65,74,85,116],"inverse":[5,47],"reinforcement":[6,24,48],"learning":[7,25,49],"in":[8,22,38],"Markov":[9],"decision":[10],"processes":[11],"where":[12],"agent":[14],"is":[15,76,87],"risksensitive.":[16],"In":[17,95],"particular,":[18],"we":[19,98],"model":[20],"risk-sensitivity":[21],"a":[23,45,53,106],"framework":[26],"by":[27],"making":[28],"use":[29,99],"models":[31],"human":[33],"decision-making":[34],"having":[35],"their":[36],"origins":[37],"behavioral":[39],"psychology":[40],"and":[41,82,101,114],"economics.":[42],"propose":[44],"gradient-based":[46],"algorithm":[50],"that":[51],"minimizes":[52],"loss":[54],"function":[55],"defined":[56],"on":[57,69],"observed":[59],"behavior.":[60],"demonstrate":[62],"performance":[64],"proposed":[67],"technique":[68],"two":[70],"examples,":[71],"first":[73],"which":[75,86],"canonical":[78],"Grid":[79],"World":[80],"example":[81],"second":[84],"an":[88],"MDP":[89],"modeling":[90],"passengers'":[91],"decisions":[92],"regarding":[93],"ride-sharing.":[94],"latter,":[97],"pricing":[100],"travel":[102],"time":[103],"data":[104],"from":[105],"ride-sharing":[107],"company":[108],"to":[109],"construct":[110],"transition":[112],"probabilities":[113],"rewards":[115],"MDP.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}