{"id":"https://openalex.org/W2187006281","doi":null,"title":"Inverse reinforcement learning with locally consistent reward functions","display_name":"Inverse reinforcement learning with locally consistent reward functions","publication_year":2015,"publication_date":"2015-12-07","ids":{"openalex":"https://openalex.org/W2187006281","mag":"2187006281"},"language":"en","primary_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/113094","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/113094","pdf_url":"http://hdl.handle.net/1721.1/113094","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems (NIPS)","raw_type":"http://purl.org/eprint/type/ConferencePaper"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/1721.1/113094","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003654479","display_name":"Quoc Phong Nguyen","orcid":"https://orcid.org/0000-0002-0183-2525","observed_orcids":["https://orcid.org/0000-0002-0183-2525"]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Quoc Phong Nguyen","raw_affiliation_strings":["Dept. of Computer Science, National University of Singapore, Republic of Singapore#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-0183-2525","affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, National University of Singapore, Republic of Singapore#TAB#","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110628584","display_name":"Kian Hsiang Low","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kian Hsiang Low","raw_affiliation_strings":["Dept. of Computer Science, National University of Singapore, Republic of Singapore#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, National University of Singapore, Republic of Singapore#TAB#","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109246810","display_name":"Patrick Jaillet","orcid":"https://orcid.org/0000-0002-8585-6566","observed_orcids":["https://orcid.org/0000-0002-8585-6566"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Jaillet","raw_affiliation_strings":["Dept. of Electrical Engineering & Computer Science, Massachusetts Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engineering & Computer Science, Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5062,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":{"value":0.91969352,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":"28","issue":null,"first_page":"1747","last_page":"1755"},"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":9.999999747378752e-05,"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/T10906","display_name":"AI-based Problem Solving and Planning","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"}}],"keywords":[{"id":"https://openalex.org/keywords/inverse-reinforcement-learning","display_name":"inverse reinforcement learning","score":1.0},{"id":"https://openalex.org/keywords/probabilistic-graphical-models","display_name":"probabilistic graphical models","score":0.7559999823570251},{"id":"https://openalex.org/keywords/expectation-maximization-algorithm","display_name":"expectation-maximization algorithm","score":0.8889999985694885},{"id":"https://openalex.org/keywords/trajectory-segmentation","display_name":"trajectory segmentation","score":0.7459999918937683},{"id":"https://openalex.org/keywords/expert-trajectories","display_name":"expert trajectories","score":0.593999981880188},{"id":"https://openalex.org/keywords/em-clustering","display_name":"EM clustering","score":0.550000011920929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6560583114624023},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6402668952941895},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5618722438812256},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5574853420257568},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5414329767227173},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5330753326416016},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.5057005882263184},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.49860215187072754},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4531340003013611},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4363708198070526},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.28589755296707153},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24824824929237366},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.2195948362350464},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:dspace.mit.edu:1721.1/113094","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/113094","pdf_url":"http://hdl.handle.net/1721.1/113094","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems (NIPS)","raw_type":"http://purl.org/eprint/type/ConferencePaper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.724.8832","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.724.8832","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.comp.nus.edu.sg/%7Elowkh/pubs/nips2015.pdf","raw_type":"text"},{"id":"mag:2187006281","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/5882-inverse-reinforcement-learning-with-locally-consistent-reward-functions.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/113094","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/1721.1/113094","pdf_url":"http://hdl.handle.net/1721.1/113094","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems (NIPS)","raw_type":"http://purl.org/eprint/type/ConferencePaper"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2187006281.pdf","grobid_xml":"https://content.openalex.org/works/W2187006281.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W36550046","https://openalex.org/W1486632395","https://openalex.org/W1535554606","https://openalex.org/W1559990548","https://openalex.org/W1591675293","https://openalex.org/W1594849649","https://openalex.org/W1743803520","https://openalex.org/W1886178467","https://openalex.org/W1999874108","https://openalex.org/W2011509463","https://openalex.org/W2031571562","https://openalex.org/W2061562262","https://openalex.org/W2098774185","https://openalex.org/W2102847492","https://openalex.org/W2113023245","https://openalex.org/W2116442740","https://openalex.org/W2117675763","https://openalex.org/W2119785746","https://openalex.org/W2119914747","https://openalex.org/W2125838338","https://openalex.org/W2135822894","https://openalex.org/W2181849516","https://openalex.org/W2255848560","https://openalex.org/W2274772358","https://openalex.org/W2963479359","https://openalex.org/W2963970308","https://openalex.org/W2964206586"],"related_works":["https://openalex.org/W2786878425","https://openalex.org/W2100401322","https://openalex.org/W3027397596","https://openalex.org/W2267646830","https://openalex.org/W2069855531","https://openalex.org/W3215946589","https://openalex.org/W2988776167","https://openalex.org/W2977411425","https://openalex.org/W4415089443","https://openalex.org/W4415796705"],"abstract_inverted_index":{"Existing":[0],"inverse":[1],"reinforcement":[2],"learning":[3,62],"(IRL)":[4],"algorithms":[5],"have":[6],"assumed":[7],"each":[8,33],"expert\u2019s":[9,118],"demonstrated":[10,119],"trajectory":[11,34,130],"to":[12,35,46,96,111],"be":[13,36,94,146],"produced":[14],"by":[15,38,143],"only":[16,61],"a":[17,24,85,122,129,172],"single":[18],"reward":[19,42,64,101,140],"function.":[20],"This":[21],"paper":[22],"presents":[23],"novel":[25],"generalization":[26],"of":[27,116,128,175],"the":[28,68,99,104,114,117,124,161],"IRL":[29,56,82,158],"problem":[30,57,83],"that":[31,133,156],"allows":[32],"generated":[37,135],"multiple":[39],"locally":[40,138],"consistent":[41,139],"functions,":[43],"hence":[44],"catering":[45],"more":[47],"realistic":[48],"and":[49,103,152],"complex":[50],"experts\u2019":[51],"behaviors.":[52],"Solving":[53],"our":[54,81,157,176],"generalized":[55],"thus":[58],"involves":[59],"not":[60],"these":[63],"functions":[65,102,141],"but":[66],"also":[67],"stochastic":[69,105],"transitions":[70,106],"between":[71,107],"them":[72,108],"at":[73],"any":[74],"state":[75],"(including":[76],"unvisited":[77],"states).":[78],"By":[79],"representing":[80],"with":[84,165],"probabilistic":[86],"graphical":[87],"model,":[88],"an":[89],"expectation-maximization":[90],"(EM)":[91],"algorithm":[92,159],"can":[93,145],"devised":[95],"iteratively":[97],"learn":[98],"different":[100,137],"in":[109],"order":[110],"jointly":[112],"improve":[113],"likelihood":[115,167],"trajectories.":[120],"As":[121],"result,":[123],"most":[125],"likely":[126],"partition":[127],"into":[131],"segments":[132],"are":[134],"from":[136],"selected":[142],"EM":[144,163],"derived.":[147],"Empirical":[148],"evaluation":[149],"on":[150],"synthetic":[151],"real-world":[153],"datasets":[154],"shows":[155],"outperforms":[160],"state-of-the-art":[162],"clustering":[164],"maximum":[166],"IRL,":[168],"which":[169],"is,":[170],"interestingly,":[171],"reduced":[173],"variant":[174],"approach.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":3}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}