{"id":"https://openalex.org/W1211946649","doi":"https://doi.org/10.21437/interspeech.2009-659","title":"Reinforcement learning for dialog management using least-squares Policy iteration and fast feature selection","display_name":"Reinforcement learning for dialog management using least-squares Policy iteration and fast feature selection","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W1211946649","doi":"https://doi.org/10.21437/interspeech.2009-659","mag":"1211946649"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-659","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-659","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","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/A5100711454","display_name":"Lihong Li","orcid":"https://orcid.org/0000-0002-5440-8242"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lihong Li","raw_affiliation_strings":["Rutgers, University"],"affiliations":[{"raw_affiliation_string":"Rutgers, University","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103246485","display_name":"J. D. Williams","orcid":"https://orcid.org/0000-0003-2460-9673"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason D. Williams","raw_affiliation_strings":["At&T#TAB#"],"affiliations":[{"raw_affiliation_string":"At&T#TAB#","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103676594","display_name":"Suhrid Balakrishnan","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suhrid Balakrishnan","raw_affiliation_strings":["At&T#TAB#"],"affiliations":[{"raw_affiliation_string":"At&T#TAB#","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100711454"],"corresponding_institution_ids":["https://openalex.org/I102322142"],"apc_list":null,"apc_paid":null,"fwci":8.1293,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.97382357,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2475","last_page":"2478"},"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":0.9970999956130981,"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":0.9965999722480774,"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":0.9142906069755554},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.9127717018127441},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8000306487083435},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.62794029712677},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5999906063079834},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5690022110939026},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5584591627120972},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5562107563018799},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48727214336395264},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.460050106048584}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9142906069755554},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.9127717018127441},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8000306487083435},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.62794029712677},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5999906063079834},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5690022110939026},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5584591627120972},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5562107563018799},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48727214336395264},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.460050106048584},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2009-659","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-659","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.3675","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.3675","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.rutgers.edu/~lihong/pub/Li09Reinforcement.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.193.1559","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.193.1559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.att.com/%7Ejdw/papers/li2009interspeech.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W228407633","https://openalex.org/W2007221309","https://openalex.org/W2021151961","https://openalex.org/W2100677568","https://openalex.org/W2118120353","https://openalex.org/W2121863487","https://openalex.org/W2130339357","https://openalex.org/W2132997613","https://openalex.org/W2138326839","https://openalex.org/W2157751731","https://openalex.org/W2161795906","https://openalex.org/W2408200822","https://openalex.org/W2468040214","https://openalex.org/W3099293669","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W48079147","https://openalex.org/W2563921006","https://openalex.org/W1963944933","https://openalex.org/W1600043506","https://openalex.org/W2174703168","https://openalex.org/W2111550420","https://openalex.org/W2549666521","https://openalex.org/W3133893348","https://openalex.org/W2920931047","https://openalex.org/W1977846844"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"is":[3,32,47,54,87,98,116],"a":[4,9,37,67,75,93,105,120,126],"promising":[5],"technique":[6],"for":[7,77],"creating":[8],"dialog":[10,18,112,128],"manager.":[11],"RL":[12,78,95,122],"accepts":[13],"features":[14],"of":[15,40],"the":[16,24,51],"current":[17],"state":[19],"and":[20,101],"seeks":[21],"to":[22,35,49,57,64],"find":[23,50],"best":[25],"action":[26],"given":[27],"those":[28],"features.":[29],"Although":[30],"it":[31,46,115],"often":[33],"easy":[34],"posit":[36],"large":[38,55],"set":[39],"potentially":[41],"useful":[42,59],"features,":[43],"in":[44,111],"practice,":[45],"difficult":[48],"subset":[52],"which":[53,80,97],"enough":[56,63],"contain":[58],"information":[60],"yet":[61],"compact":[62],"reliably":[65],"learn":[66,103],"good":[68],"policy.":[69],"In":[70],"this":[71],"paper,":[72],"we":[73],"propose":[74],"method":[76],"optimization":[79],"automatically":[81],"performs":[82],"feature":[83],"selection.":[84],"The":[85],"algorithm":[86,96,123],"based":[88],"on":[89],"least-squares":[90],"policy":[91],"iteration,":[92],"state-of-the-art":[94],"highly":[99],"sampleefficient":[100],"can":[102],"from":[104,125],"static":[106],"corpus":[107],"or":[108],"on-line.":[109],"Experiments":[110],"simulation":[113],"show":[114],"more":[117],"stable":[118],"than":[119],"baseline":[121],"taken":[124],"working":[127],"system.":[129]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":11}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}