{"id":"https://openalex.org/W1994480928","doi":"https://doi.org/10.1145/2493525.2493529","title":"Inverse reinforcement learning for interactive systems","display_name":"Inverse reinforcement learning for interactive systems","publication_year":2013,"publication_date":"2013-07-30","ids":{"openalex":"https://openalex.org/W1994480928","doi":"https://doi.org/10.1145/2493525.2493529","mag":"1994480928"},"language":"en","primary_location":{"id":"doi:10.1145/2493525.2493529","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2493525.2493529","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on Machine Learning for Interactive Systems: Bridging the Gap Between Perception, Action and Communication","raw_type":"proceedings-article"},"type":"conference-paper","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/A5065100569","display_name":"Olivier Pietquin","orcid":"https://orcid.org/0000-0002-5386-465X"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I4210089931","display_name":"Georgia Tech-CNRS Laboratory","ror":"https://ror.org/00avmbz91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1288283403","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I130701444","https://openalex.org/I4210089931","https://openalex.org/I4210095849","https://openalex.org/I4405256580","https://openalex.org/I90183372"]}],"countries":["FR","US"],"is_corresponding":true,"raw_author_name":"Olivier Pietquin","raw_affiliation_strings":["SUPELEC - UMI (GeorgiaTech-CNRS), Metz - France","SUPELEC - UMI (GeorgiaTech-CNRS), Metz - France#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SUPELEC - UMI (GeorgiaTech-CNRS), Metz - France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210089931"]},{"raw_affiliation_string":"SUPELEC - UMI (GeorgiaTech-CNRS), Metz - France#TAB#","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5065100569"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I130701444","https://openalex.org/I4210089931"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"71","last_page":"75"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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/T12031","display_name":"Speech and dialogue systems","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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9987000226974487,"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/T10028","display_name":"Topic Modeling","score":0.9965000152587891,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8103694915771484},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7974029779434204},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6441483497619629},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6426147222518921},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.6087383031845093},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5128614902496338},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48911982774734497},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.46603816747665405},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44677990674972534}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8103694915771484},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7974029779434204},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6441483497619629},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6426147222518921},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.6087383031845093},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5128614902496338},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48911982774734497},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.46603816747665405},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44677990674972534},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2493525.2493529","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2493525.2493529","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd Workshop on Machine Learning for Interactive Systems: Bridging the Gap Between Perception, Action and Communication","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-00869812v1","is_oa":false,"landing_page_url":"https://centralesupelec.hal.science/hal-00869812","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"MLIS '13, Aug 2013, Beijing, China. pp.71-75, ⟨10.1145/2493525.2493529⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7699999809265137,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G77717376","display_name":null,"funder_award_id":"270780","funder_id":"https://openalex.org/F4320334960","funder_display_name":"Seventh Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320334960","display_name":"Seventh Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W51070445","https://openalex.org/W268459713","https://openalex.org/W396357221","https://openalex.org/W1211946649","https://openalex.org/W1508165687","https://openalex.org/W1515851193","https://openalex.org/W1544894162","https://openalex.org/W1605030600","https://openalex.org/W1645937837","https://openalex.org/W1757949796","https://openalex.org/W1778387566","https://openalex.org/W1971681797","https://openalex.org/W1973933596","https://openalex.org/W1996957559","https://openalex.org/W1999874108","https://openalex.org/W2031571562","https://openalex.org/W2040123554","https://openalex.org/W2054716580","https://openalex.org/W2061562262","https://openalex.org/W2062175565","https://openalex.org/W2083205357","https://openalex.org/W2100401322","https://openalex.org/W2109038907","https://openalex.org/W2115969092","https://openalex.org/W2116154161","https://openalex.org/W2116774898","https://openalex.org/W2119785746","https://openalex.org/W2120045257","https://openalex.org/W2121863487","https://openalex.org/W2126810476","https://openalex.org/W2127829921","https://openalex.org/W2128965063","https://openalex.org/W2134051188","https://openalex.org/W2134466368","https://openalex.org/W2140208615","https://openalex.org/W2146364776","https://openalex.org/W2151814822","https://openalex.org/W2154740693","https://openalex.org/W2163068732","https://openalex.org/W2168490009","https://openalex.org/W2170903322","https://openalex.org/W2313752741","https://openalex.org/W2341171179","https://openalex.org/W2394629376","https://openalex.org/W2398995054","https://openalex.org/W2438667436","https://openalex.org/W2757979647","https://openalex.org/W2788204336","https://openalex.org/W2914907514","https://openalex.org/W3141239769","https://openalex.org/W3158638686","https://openalex.org/W4323322863","https://openalex.org/W6610883684","https://openalex.org/W6683794156","https://openalex.org/W6704298589","https://openalex.org/W6712035640","https://openalex.org/W7071444332"],"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/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"Human":[0],"machine":[1,7,40],"interaction":[2,24,66],"is":[3,9,26,89],"a":[4,70,82,110,114],"field":[5,59],"where":[6],"learning":[8,41,53,79,113,124],"present":[10],"at":[11],"almost":[12],"any":[13],"level,":[14],"from":[15,39],"human":[16,151],"activity":[17],"recognition":[18],"to":[19,131,148],"natural":[20,68],"language":[21],"generation.":[22],"The":[23],"manager":[25],"probably":[27],"one":[28],"of":[29,33,63,134,150],"the":[30,44,58,61,65,78,93,102,135],"latest":[31],"components":[32],"an":[34],"interactive":[35],"system":[36,94],"that":[37],"benefited":[38],"techniques.":[42],"In":[43,104],"late":[45],"90's,":[46],"sequential":[47],"decision":[48],"making":[49,64],"algorithms":[50,75],"like":[51],"reinforcement":[52,123],"have":[54],"been":[55],"introduced":[56],"in":[57,69,101],"with":[60,81],"aim":[62],"more":[67],"measurable":[71],"way.":[72],"Yet,":[73],"these":[74],"require":[76],"providing":[77],"agent":[80],"reward":[83,88,115],"after":[84],"each":[85],"interaction.":[86],"This":[87],"generally":[90],"handcrafted":[91],"by":[92,117],"designer":[95],"who":[96],"introduces":[97],"again":[98],"some":[99],"expertise":[100],"system.":[103],"this":[105],"paper,":[106],"we":[107],"will":[108,127],"discuss":[109],"method":[111],"for":[112],"function":[116],"observing":[118],"expert":[119],"humans,":[120],"namely":[121],"inverse":[122],"(IRL).":[125],"IRL":[126],"then":[128],"be":[129],"applied":[130],"several":[132],"steps":[133],"spoken":[136],"dialogue":[137],"management":[138],"design":[139],"such":[140],"as":[141],"user":[142,152],"simulation":[143],"and":[144,153],"clustering":[145],"but":[146],"also":[147],"co-adaptation":[149],"machine.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}