{"id":"https://openalex.org/W2151904921","doi":"https://doi.org/10.1109/icassp.2012.6289040","title":"Off-policy learning in large-scale POMDP-based dialogue systems","display_name":"Off-policy learning in large-scale POMDP-based dialogue systems","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2151904921","doi":"https://doi.org/10.1109/icassp.2012.6289040","mag":"2151904921"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6289040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6289040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","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/A5072253501","display_name":"Lucie Daubigney","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"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"]},{"id":"https://openalex.org/I102475099","display_name":"Sup\u00e9lec","ror":"https://ror.org/00n7gwn90","country_code":"FR","type":"education","lineage":["https://openalex.org/I102475099"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Lucie Daubigney","raw_affiliation_strings":["IMS, Sup\u00e9lec, Metz, France","Project-Team MAIA, Loria, Nancy, France"],"affiliations":[{"raw_affiliation_string":"IMS, Sup\u00e9lec, Metz, France","institution_ids":["https://openalex.org/I102475099","https://openalex.org/I4210160189"]},{"raw_affiliation_string":"Project-Team MAIA, Loria, Nancy, France","institution_ids":["https://openalex.org/I4210121838"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110482875","display_name":"Matthieu Geist","orcid":null},"institutions":[{"id":"https://openalex.org/I102475099","display_name":"Sup\u00e9lec","ror":"https://ror.org/00n7gwn90","country_code":"FR","type":"education","lineage":["https://openalex.org/I102475099"]},{"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":"Matthieu Geist","raw_affiliation_strings":["IMS, Sup\u00e9lec, Metz, France"],"affiliations":[{"raw_affiliation_string":"IMS, Sup\u00e9lec, Metz, France","institution_ids":["https://openalex.org/I102475099","https://openalex.org/I4210160189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065100569","display_name":"Olivier Pietquin","orcid":"https://orcid.org/0000-0002-5386-465X"},"institutions":[{"id":"https://openalex.org/I102475099","display_name":"Sup\u00e9lec","ror":"https://ror.org/00n7gwn90","country_code":"FR","type":"education","lineage":["https://openalex.org/I102475099"]},{"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":"Olivier Pietquin","raw_affiliation_strings":["IMS, Sup\u00e9lec, Metz, France"],"affiliations":[{"raw_affiliation_string":"IMS, Sup\u00e9lec, Metz, France","institution_ids":["https://openalex.org/I102475099","https://openalex.org/I4210160189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5072253501"],"corresponding_institution_ids":["https://openalex.org/I4210121838","https://openalex.org/I4210160189","https://openalex.org/I102475099"],"apc_list":null,"apc_paid":null,"fwci":6.06322721,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.96836854,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4989","last_page":"4992"},"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.9916999936103821,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8912711143493652},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7904679179191589},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6553844809532166},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6064001321792603},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.5455935597419739},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.542927622795105},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5164030194282532},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5159526467323303},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.49502676725387573},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47407689690589905},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.4452275335788727},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4152998924255371},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4100600779056549},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.36535605788230896},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.36356306076049805},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2874630093574524},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.22585701942443848},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.12744325399398804},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10350710153579712},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.08119642734527588}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8912711143493652},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7904679179191589},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6553844809532166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6064001321792603},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.5455935597419739},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.542927622795105},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5164030194282532},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5159526467323303},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.49502676725387573},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47407689690589905},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.4452275335788727},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4152998924255371},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4100600779056549},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.36535605788230896},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.36356306076049805},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2874630093574524},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.22585701942443848},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.12744325399398804},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10350710153579712},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.08119642734527588},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2012.6289040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6289040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W52170320","https://openalex.org/W196536594","https://openalex.org/W1778387566","https://openalex.org/W2062175565","https://openalex.org/W2099118758","https://openalex.org/W2106547558","https://openalex.org/W2107961737","https://openalex.org/W2115101920","https://openalex.org/W2121863487","https://openalex.org/W2124352385","https://openalex.org/W2132997613","https://openalex.org/W2134051188","https://openalex.org/W2134466368","https://openalex.org/W2141562047","https://openalex.org/W2156974606","https://openalex.org/W2158984235","https://openalex.org/W2163068732","https://openalex.org/W2168490009","https://openalex.org/W2180877127","https://openalex.org/W2438667436","https://openalex.org/W4214717370","https://openalex.org/W6676426613","https://openalex.org/W6683794156","https://openalex.org/W7046658373"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1589140671","https://openalex.org/W1515117609","https://openalex.org/W4323315247","https://openalex.org/W2294884454","https://openalex.org/W3169161914","https://openalex.org/W4321379664","https://openalex.org/W2211790881"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,87],"(RL)":[2],"is":[3,49,86,114,123],"now":[4],"part":[5],"of":[6,9,15],"the":[7,10,13,38],"state":[8],"art":[11],"in":[12,37,58],"domain":[14],"spoken":[16],"dialogue":[17],"systems":[18],"(SDS)":[19],"optimisation.":[20],"Most":[21],"performant":[22],"RL":[23,112],"methods,":[24],"such":[25],"as":[26,43],"those":[27],"based":[28],"on":[29,51],"Gaussian":[30],"Processes,":[31],"require":[32],"to":[33,40,93,116,125,137],"test":[34],"small":[35],"changes":[36],"policy":[39,52],"assess":[41],"them":[42],"improvements":[44],"or":[45],"degradations.":[46],"This":[47,121],"process":[48],"called":[50],"learning.":[53],"Nevertheless,":[54],"it":[55],"can":[56],"result":[57],"system":[59],"behaviours":[60],"that":[61,85],"are":[62,97],"not":[63,99],"acceptable":[64,83],"by":[65,75,79],"users.":[66],"Learning":[67],"algorithms":[68],"should":[69],"ideally":[70],"infer":[71],"an":[72,118],"optimal":[73,119],"strategy":[74],"observing":[76],"interactions":[77],"generated":[78],"a":[80,107,126,133],"non-optimal":[81],"but":[82],"strategy,":[84],"off-policy.":[88],"Such":[89],"methods":[90],"usually":[91],"fail":[92],"scale":[94,140],"up":[95],"and":[96,110],"thus":[98],"suited":[100],"for":[101],"real-world":[102],"systems.":[103,141],"In":[104],"this":[105],"contribution,":[106],"sample-efficient,":[108],"online":[109],"off-policy":[111],"algorithm":[113,122],"proposed":[115],"learn":[117],"policy.":[120],"combined":[124],"compact":[127],"non-linear":[128],"value":[129],"function":[130],"representation":[131],"(namely":[132],"multi-layers":[134],"perceptron)":[135],"enabling":[136],"handle":[138],"large":[139]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}