{"id":"https://openalex.org/W3027397596","doi":"https://doi.org/10.5555/1953048.2021028","title":"Inverse Reinforcement Learning in Partially Observable Environments","display_name":"Inverse Reinforcement Learning in Partially Observable Environments","publication_year":2011,"publication_date":"2011-07-01","ids":{"openalex":"https://openalex.org/W3027397596","doi":"https://doi.org/10.5555/1953048.2021028","mag":"3027397596"},"language":"en","primary_location":{"id":"mag:3027397596","is_oa":false,"landing_page_url":"https://dl.acm.org/doi/10.5555/1953048.2021028","pdf_url":null,"source":{"id":"https://openalex.org/S118988714","display_name":"Journal of Machine Learning Research","issn_l":"1532-4435","issn":["1532-4435","1533-7928"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Journal of Machine Learning Research","raw_type":null},"type":"article","indexed_in":[],"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/A5010941407","display_name":"ChoiJaedeug","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"ChoiJaedeug","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5041755281","display_name":"KimKee-Eung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"KimKee-Eung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6379,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.91446992,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6269999742507935,"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":0.6269999742507935,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.7589257955551147},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6279438734054565},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5547142624855042},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5298870205879211},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5156680345535278},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.5147299766540527},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.489298552274704},{"id":"https://openalex.org/keywords/inverse-problem","display_name":"Inverse problem","score":0.4463309049606323},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.35538724064826965},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.26970693469047546},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14374953508377075},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11400496959686279},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.09145909547805786}],"concepts":[{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.7589257955551147},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6279438734054565},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5547142624855042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5298870205879211},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5156680345535278},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.5147299766540527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.489298552274704},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.4463309049606323},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35538724064826965},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26970693469047546},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14374953508377075},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11400496959686279},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.09145909547805786},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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":"mag:3027397596","is_oa":false,"landing_page_url":"https://dl.acm.org/doi/10.5555/1953048.2021028","pdf_url":null,"source":{"id":"https://openalex.org/S118988714","display_name":"Journal of Machine Learning Research","issn_l":"1532-4435","issn":["1532-4435","1533-7928"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Journal of Machine Learning Research","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2945642643","https://openalex.org/W2567252694","https://openalex.org/W3124546976","https://openalex.org/W3130596985","https://openalex.org/W2984409990","https://openalex.org/W2945895484","https://openalex.org/W2211252706","https://openalex.org/W2352770069","https://openalex.org/W1984988829","https://openalex.org/W3098394517","https://openalex.org/W2978807153","https://openalex.org/W1591675293","https://openalex.org/W2187006281","https://openalex.org/W3159394959","https://openalex.org/W2803256544","https://openalex.org/W3174426278","https://openalex.org/W2338865890","https://openalex.org/W2974892902","https://openalex.org/W2592605409","https://openalex.org/W2100401322"],"abstract_inverted_index":{"Inverse":[0],"reinforcement":[1],"learning":[2],"(IRL)":[3],"is":[4,29],"the":[5,9,14,21,27],"problem":[6],"of":[7,16,20],"recovering":[8],"underlying":[10],"reward":[11],"function":[12],"from":[13],"behavior":[15],"an":[17],"expert.":[18],"Most":[19],"existing":[22],"IRL":[23],"algorithms":[24],"assume":[25],"that":[26],"environment":[28],"m...":[30]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}