{"id":"https://openalex.org/W2945895484","doi":"https://doi.org/10.48550/arxiv.1905.08513","title":"Stochastic Inverse Reinforcement Learning","display_name":"Stochastic Inverse Reinforcement Learning","publication_year":2019,"publication_date":"2019-05-21","ids":{"openalex":"https://openalex.org/W2945895484","doi":"https://doi.org/10.48550/arxiv.1905.08513","mag":"2945895484"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1905.08513","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.08513","pdf_url":"https://arxiv.org/pdf/1905.08513","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1905.08513","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100774577","display_name":"Ce Ju","orcid":"https://orcid.org/0000-0002-0753-2179","observed_orcids":["https://orcid.org/0000-0002-0753-2179"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Ju, Ce","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100774577"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":1.0,"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":1.0,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.0,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/inverse-reinforcement-learning","display_name":"inverse reinforcement learning","score":0.8769999742507935},{"id":"https://openalex.org/keywords/expert-demonstrations","display_name":"expert demonstrations","score":0.8009999990463257},{"id":"https://openalex.org/keywords/monte-carlo-expectation-maximization","display_name":"Monte Carlo expectation-maximization","score":0.925000011920929},{"id":"https://openalex.org/keywords/ill-posed-inverse-problems","display_name":"ill-posed inverse problems","score":0.8960000276565552},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.3449999988079071}],"concepts":[{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5924071073532104},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.5923060178756714},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.586437463760376},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.573255717754364},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5366888046264648},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.5213721394538879},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5146077871322632},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.49081000685691833},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.48192501068115234},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.42965978384017944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31593507528305054},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2760436236858368},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08409774303436279},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:1905.08513","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.08513","pdf_url":"https://arxiv.org/pdf/1905.08513","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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.1905.08513","doi":"https://doi.org/10.48550/arxiv.1905.08513","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1905.08513","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1905.08513","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.08513","pdf_url":"https://arxiv.org/pdf/1905.08513","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1583833196","https://openalex.org/W1591675293","https://openalex.org/W1600437712","https://openalex.org/W1929981607","https://openalex.org/W1972336342","https://openalex.org/W1975593377","https://openalex.org/W1999874108","https://openalex.org/W2008668767","https://openalex.org/W2036375318","https://openalex.org/W2057134775","https://openalex.org/W2061562262","https://openalex.org/W2072634211","https://openalex.org/W2090692107","https://openalex.org/W2098774185","https://openalex.org/W2113023245","https://openalex.org/W2117675763","https://openalex.org/W2142828048","https://openalex.org/W2158782408","https://openalex.org/W2163037893","https://openalex.org/W2169498096","https://openalex.org/W2227909145","https://openalex.org/W2290104316","https://openalex.org/W2322259366","https://openalex.org/W2401592218","https://openalex.org/W2434014514","https://openalex.org/W2566467060","https://openalex.org/W2766610320","https://openalex.org/W2780624097","https://openalex.org/W2962779270","https://openalex.org/W2963221965","https://openalex.org/W2963328631","https://openalex.org/W6903351479"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2088734424","https://openalex.org/W129490210"],"abstract_inverted_index":{"The":[0,101],"goal":[1],"of":[2,89,132],"the":[3,12,19,28,32,55,71,79,87,90,94,98,118,129,133,148],"inverse":[4,25,65],"reinforcement":[5,66],"learning":[6,67,110],"(IRL)":[7],"problem":[8,21,26,57,63,135],"is":[9,103,125],"to":[10,58,69,85,97,117,127],"recover":[11,70],"reward":[13,39,75],"functions":[14],"from":[15,136],"expert":[16,42],"demonstrations.":[17],"However,":[18],"IRL":[20,56,119,134],"like":[22],"any":[23],"ill-posed":[24],"suffers":[27],"congenital":[29],"defect":[30],"that":[31],"policy":[33],"may":[34,44],"be":[35,45],"optimal":[36,46],"for":[37,47,108],"many":[38,48],"functions,":[40],"and":[41,106,112,140],"demonstrations":[43],"policies.":[49],"In":[50],"this":[51],"work,":[52],"we":[53],"generalize":[54],"a":[59,109,137,144],"well-posed":[60],"expectation":[61],"optimization":[62],"stochastic":[64],"(SIRL)":[68],"probability":[72,91],"distribution":[73,92],"over":[74],"functions.":[76],"We":[77],"adopt":[78],"Monte":[80],"Carlo":[81],"expectation-maximization":[82],"(MCEM)":[83],"method":[84],"estimate":[86],"parameter":[88],"as":[93],"first":[95],"solution":[96,102],"SIRL":[99],"problem.":[100,120],"succinct,":[104],"robust,":[105],"transferable":[107],"task":[111],"can":[113],"generate":[114],"alternative":[115],"solutions":[116],"Through":[121],"our":[122,141],"formulation,":[123],"it":[124],"possible":[126],"observe":[128],"intrinsic":[130],"property":[131],"global":[138],"viewpoint,":[139],"approach":[142],"achieves":[143],"considerable":[145],"performance":[146],"on":[147],"objectworld.":[149]},"counts_by_year":[],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}