{"id":"https://openalex.org/W2086645471","doi":"https://doi.org/10.1109/asru.2013.6707714","title":"Expert-based reward shaping and exploration scheme for boosting policy learning of dialogue management","display_name":"Expert-based reward shaping and exploration scheme for boosting policy learning of dialogue management","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2086645471","doi":"https://doi.org/10.1109/asru.2013.6707714","mag":"2086645471"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2013.6707714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","raw_type":"proceedings-article"},"type":"article","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/A5007099438","display_name":"Emmanuel Ferreira","orcid":null},"institutions":[{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Emmanuel Ferreira","raw_affiliation_strings":["LIA, University of Avignon, Avignon Cedex 9, France","LIA - University of Avignon, Avignon, France#TAB#"],"affiliations":[{"raw_affiliation_string":"LIA, University of Avignon, Avignon Cedex 9, France","institution_ids":["https://openalex.org/I198415970"]},{"raw_affiliation_string":"LIA - University of Avignon, Avignon, France#TAB#","institution_ids":["https://openalex.org/I198415970"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103414469","display_name":"Fabrice Lef\u00e8vre","orcid":null},"institutions":[{"id":"https://openalex.org/I198415970","display_name":"Universit\u00e9 d'Avignon et des Pays de Vaucluse","ror":"https://ror.org/00mfpxb84","country_code":"FR","type":"education","lineage":["https://openalex.org/I198415970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fabrice Lefevre","raw_affiliation_strings":["LIA, University of Avignon, Avignon Cedex 9, France","LIA - University of Avignon, Avignon, France#TAB#"],"affiliations":[{"raw_affiliation_string":"LIA, University of Avignon, Avignon Cedex 9, France","institution_ids":["https://openalex.org/I198415970"]},{"raw_affiliation_string":"LIA - University of Avignon, Avignon, France#TAB#","institution_ids":["https://openalex.org/I198415970"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5007099438"],"corresponding_institution_ids":["https://openalex.org/I198415970"],"apc_list":null,"apc_paid":null,"fwci":1.4427,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.86091628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"39","issue":null,"first_page":"108","last_page":"113"},"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/T10028","display_name":"Topic Modeling","score":0.9984999895095825,"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":0.9983000159263611,"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":0.8371940851211548},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7856593728065491},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.7628111243247986},{"id":"https://openalex.org/keywords/dilemma","display_name":"Dilemma","score":0.6048407554626465},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5434948801994324},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.510665237903595},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5076245069503784},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.502194881439209},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.3405725955963135}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8371940851211548},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7856593728065491},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.7628111243247986},{"id":"https://openalex.org/C2778496695","wikidata":"https://www.wikidata.org/wiki/Q254128","display_name":"Dilemma","level":2,"score":0.6048407554626465},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5434948801994324},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.510665237903595},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5076245069503784},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.502194881439209},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3405725955963135},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2013.6707714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707714","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5799999833106995}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320273","display_name":"University of Cambridge","ror":"https://ror.org/013meh722"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1777239053","https://openalex.org/W1778387566","https://openalex.org/W2021151961","https://openalex.org/W2034684560","https://openalex.org/W2054716580","https://openalex.org/W2105934661","https://openalex.org/W2115101920","https://openalex.org/W2117989772","https://openalex.org/W2119015791","https://openalex.org/W2121863487","https://openalex.org/W2134051188","https://openalex.org/W2137375617","https://openalex.org/W2158984235","https://openalex.org/W2168359464","https://openalex.org/W2168490009","https://openalex.org/W2180877127","https://openalex.org/W2396863940","https://openalex.org/W2468040214","https://openalex.org/W4214717370","https://openalex.org/W4323322863","https://openalex.org/W6637924565","https://openalex.org/W6638088447","https://openalex.org/W6680123468","https://openalex.org/W6680322746","https://openalex.org/W6720222513"],"related_works":["https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W4231274751","https://openalex.org/W1549363203","https://openalex.org/W2154063878","https://openalex.org/W2556012038","https://openalex.org/W1489772951","https://openalex.org/W2350209916","https://openalex.org/W1538046993","https://openalex.org/W4239293476"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,14,84,89,121],"conditions":[4],"under":[5],"which":[6],"expert":[7,67],"knowledge":[8],"can":[9],"be":[10],"used":[11],"to":[12,30,39,82,95],"accelerate":[13],"policy":[15],"optimization":[16],"of":[17],"a":[18,53,115],"learning":[19,25,76],"agent.":[20],"Recent":[21],"works":[22],"on":[23,63,109],"reinforcement":[24],"for":[26,34],"dialogue":[27,118],"management":[28,119],"allowed":[29],"devise":[31],"sophisticated":[32],"methods":[33],"value":[35],"estimation":[36],"in":[37],"order":[38],"deal":[40],"all":[41],"together":[42],"with":[43,71,97],"exploration/exploitation":[44],"dilemma,":[45],"sample-efficiency":[46],"and":[47,57,111],"non-stationary":[48],"environments.":[49],"In":[50],"this":[51],"paper,":[52],"reward":[54],"shaping":[55],"method":[56],"an":[58,72],"exploration":[59],"scheme,":[60],"both":[61],"based":[62,108],"some":[64],"intuitive":[65],"hand-coded":[66],"advices,":[68],"are":[69,104],"combined":[70],"efficient":[73],"temporal":[74],"difference-based":[75],"procedure.":[77],"The":[78],"key":[79],"objective":[80],"is":[81,91],"boost":[83],"initial":[85],"training":[86],"stage,":[87],"when":[88],"system":[90],"not":[92],"sufficiently":[93],"reliable":[94],"interact":[96],"real":[98],"users":[99],"(e.g.":[100],"clients).":[101],"Our":[102],"claims":[103],"illustrated":[105],"by":[106],"experiments":[107],"simulation":[110],"carried":[112],"out":[113],"using":[114],"state-of-the-art":[116],"goal-oriented":[117],"framework,":[120],"Hidden":[122],"Information":[123],"State":[124],"(HIS).":[125]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"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":3},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}