{"id":"https://openalex.org/W2400904432","doi":"https://doi.org/10.3233/978-1-61499-096-3-95","title":"Reward Function Learning for Dialogue Management","display_name":"Reward Function Learning for Dialogue Management","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W2400904432","doi":"https://doi.org/10.3233/978-1-61499-096-3-95","mag":"2400904432"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-096-3-95","is_oa":true,"landing_page_url":"https://doi.org/10.3233/978-1-61499-096-3-95","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/978-1-61499-096-3-95","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"El Asri Layla","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"El Asri Layla","raw_affiliation_strings":["IMS : Information, Multimodalit\u00e9 & Signal (2 rue Edouard Belin - - 57070 METZ - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IMS : Information, Multimodalit\u00e9 & Signal (2 rue Edouard Belin - - 57070 METZ - France)","institution_ids":["https://openalex.org/I4210160189"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Laroche Romain","orcid":null},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Laroche Romain","raw_affiliation_strings":["Orange Labs [Issy les Moulineaux] (38-40 Rue du G\u00e9n\u00e9ral Leclerc, Issy les Moulineaux Cedex 9, 92794, France - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Orange Labs [Issy les Moulineaux] (38-40 Rue du G\u00e9n\u00e9ral Leclerc, Issy les Moulineaux Cedex 9, 92794, France - France)","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"last","author":{"id":null,"display_name":"Pietquin Olivier","orcid":null},"institutions":[{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Pietquin Olivier","raw_affiliation_strings":["IMS : Information, Multimodalit\u00e9 & Signal (2 rue Edouard Belin - - 57070 METZ - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IMS : Information, Multimodalit\u00e9 & Signal (2 rue Edouard Belin - - 57070 METZ - France)","institution_ids":["https://openalex.org/I4210160189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5731,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.93966333,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"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/T12031","display_name":"Speech and dialogue systems","score":0.9998999834060669,"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":0.9998999834060669,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9901999831199646,"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":0.8259690999984741},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7543055415153503},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.6328637599945068},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5693520903587341},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5676405429840088},{"id":"https://openalex.org/keywords/line","display_name":"Line (geometry)","score":0.5521711111068726},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5105965733528137},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41459307074546814},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4111568331718445},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32529574632644653},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08396643400192261}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8259690999984741},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7543055415153503},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6328637599945068},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5693520903587341},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5676405429840088},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.5521711111068726},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5105965733528137},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41459307074546814},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4111568331718445},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32529574632644653},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08396643400192261},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":2,"locations":[{"id":"doi:10.3233/978-1-61499-096-3-95","is_oa":true,"landing_page_url":"https://doi.org/10.3233/978-1-61499-096-3-95","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"pmh:oai:HAL:hal-00749430v1","is_oa":false,"landing_page_url":"https://centralesupelec.hal.science/hal-00749430","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":"STAIRS 2012, Aug 2012, Montpellier, France. pp.95-106, ⟨10.3233/978-1-61499-096-3-95⟩","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.3233/978-1-61499-096-3-95","is_oa":true,"landing_page_url":"https://doi.org/10.3233/978-1-61499-096-3-95","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W30493077","https://openalex.org/W268459713","https://openalex.org/W1777239053","https://openalex.org/W2031571562","https://openalex.org/W2057244568","https://openalex.org/W2101308260","https://openalex.org/W2117989772"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W3009457412","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"This":[0,18],"paper":[1,88],"addresses":[2],"the":[3,23,50,78,125,132],"problem":[4],"of":[5,25,58,80],"defining,":[6],"from":[7,44,90,145],"data,":[8],"a":[9,13,69,93],"reward":[10,96],"function":[11,97],"in":[12,37,86,122],"Reinforcement":[14],"Learning":[15],"(RL)":[16],"problem.":[17],"issue":[19],"is":[20,54,60,119,139],"applied":[21],"to":[22,35,73,77,131,141,148],"case":[24],"Spoken":[26],"Dialogue":[27],"Systems":[28],"(SDS),":[29],"which":[30,98],"are":[31,108,112,129],"interfaces":[32],"enabling":[33],"users":[34],"interact":[36],"natural":[38],"language.":[39],"A":[40,56],"new":[41],"methodology":[42],"which,":[43],"system":[45],"evaluation,":[46],"apportions":[47],"rewards":[48,128],"over":[49],"system's":[51],"state":[52],"space,":[53],"suggested.":[55],"corpus":[57],"dialogues":[59],"collected":[61],"on-line":[62,150],"and":[63,117,135],"then":[64],"evaluated":[65],"by":[66],"experts,":[67],"assigning":[68],"numerical":[70,127],"performance":[71,133,146],"score":[72],"each":[74],"dialogue":[75,81],"according":[76],"quality":[79],"management.":[82],"The":[83],"approach":[84],"described":[85],"this":[87,106],"infers,":[89],"these":[91],"scores,":[92],"locally":[94],"distributed":[95],"can":[99],"be":[100],"used":[101],"on-line.":[102],"Two":[103],"algorithms":[104,111],"achieving":[105],"goal":[107],"proposed.":[109],"These":[110],"tested":[113],"on":[114],"an":[115],"SDS":[116],"it":[118,138],"showed":[120],"that":[121,137],"both":[123],"cases,":[124],"resulting":[126],"close":[130],"scores":[134],"thus,":[136],"possible":[140],"extract":[142],"relevant":[143],"information":[144],"evaluation":[147],"optimise":[149],"learning.":[151]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2016-06-24T00:00:00"}