{"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":"2012-08-27","ids":{"openalex":"https://openalex.org/W2400904432","doi":"https://doi.org/10.3233/978-1-61499-096-3-95","mag":"2400904432"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://hal-supelec.archives-ouvertes.fr/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":true,"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":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"proceedings-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/A5049090525","display_name":"Layla El Asri","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Layla El Asri","raw_affiliation_strings":["IMS : Information, Multimodalit\u00e9 & Signal"],"affiliations":[{"raw_affiliation_string":"IMS : Information, Multimodalit\u00e9 & Signal","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089214987","display_name":"Romain Laroche","orcid":"https://orcid.org/0000-0001-7180-2746"},"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":"Romain Laroche","raw_affiliation_strings":["Orange Labs [Issy les Moulineaux]"],"affiliations":[{"raw_affiliation_string":"Orange Labs [Issy les Moulineaux]","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065100569","display_name":"Olivier Pietquin","orcid":"https://orcid.org/0000-0002-5386-465X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Olivier Pietquin","raw_affiliation_strings":["IMS : Information, Multimodalit\u00e9 & Signal"],"affiliations":[{"raw_affiliation_string":"IMS : Information, Multimodalit\u00e9 & Signal","institution_ids":[]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.952733,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":91},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9999,"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":0.9999,"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":0.9987,"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":0.9897,"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/line","display_name":"Line (geometry)","score":0.52456546}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8454335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8091423},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6297477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.57981265},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5437665},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.52456546},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.50045824},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45604733},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3216972},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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":3,"locations":[{"is_oa":false,"landing_page_url":"https://hal-supelec.archives-ouvertes.fr/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":true,"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":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"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":true,"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":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://hal-centralesupelec.archives-ouvertes.fr/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":true,"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":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":7,"referenced_works":["https://openalex.org/W1777239053","https://openalex.org/W2031571562","https://openalex.org/W2057244568","https://openalex.org/W2101308260","https://openalex.org/W2117989772","https://openalex.org/W268459713","https://openalex.org/W30493077"],"related_works":["https://openalex.org/W4391331176","https://openalex.org/W4380318855","https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W3049728571","https://openalex.org/W2964765435","https://openalex.org/W2586732548","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2024136090"],"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\u2019s":[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]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2400904432","counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2024-12-14T06:31:30.468669","created_date":"2016-06-24"}