{"id":"https://openalex.org/W156932648","doi":"https://doi.org/10.21437/interspeech.2006-149","title":"Learning multi-goal dialogue strategies using reinforcement learning with reduced state-action spaces","display_name":"Learning multi-goal dialogue strategies using reinforcement learning with reduced state-action spaces","publication_year":2006,"publication_date":"2006-09-17","ids":{"openalex":"https://openalex.org/W156932648","doi":"https://doi.org/10.21437/interspeech.2006-149","mag":"156932648"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2006-149","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-149","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.pure.ed.ac.uk/ws/files/27377487/rss_icslp2006.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036357777","display_name":"Heriberto Cuay\u00e1huitl","orcid":"https://orcid.org/0000-0002-1937-9837"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Heriberto Cuay\u00e1huitl","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steve Renals","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010949145","display_name":"Oliver Lemon","orcid":"https://orcid.org/0000-0001-9497-4743"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oliver Lemon","raw_affiliation_strings":["School of Mathematical & Computer Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical & Computer Sciences","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062792381","display_name":"Hiroshi Shimodaira","orcid":"https://orcid.org/0000-0001-8956-2816"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hiroshi Shimodaira","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"paper 1282","last_page":"Mon2FoP.6"},"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":0.9965999722480774,"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"}},{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9957000017166138,"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":0.9301358461380005},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7471407651901245},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.672946572303772},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5792193412780762},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5741679072380066},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5533018708229065},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5069499015808105},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.500389575958252},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.46765488386154175},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.45071351528167725},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.449124813079834},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44625362753868103},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.41677623987197876},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09227770566940308},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09182935953140259},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07989341020584106}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9301358461380005},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7471407651901245},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.672946572303772},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5792193412780762},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5741679072380066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5533018708229065},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5069499015808105},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.500389575958252},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.46765488386154175},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.45071351528167725},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.449124813079834},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44625362753868103},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.41677623987197876},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09227770566940308},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09182935953140259},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07989341020584106},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2006-149","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-149","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/b1b36e32-9e44-473c-a70b-d03e9c8f483f","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/b1b36e32-9e44-473c-a70b-d03e9c8f483f","pdf_url":"https://www.pure.ed.ac.uk/ws/files/27377487/rss_icslp2006.pdf","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.67.112","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.67.112","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.ed.ac.uk/downloads/publications/2006/rss-icslp2006.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/b1b36e32-9e44-473c-a70b-d03e9c8f483f","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/b1b36e32-9e44-473c-a70b-d03e9c8f483f","pdf_url":"https://www.pure.ed.ac.uk/ws/files/27377487/rss_icslp2006.pdf","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322938","display_name":"Universidad Aut\u00f3noma de Tlaxcala","ror":"https://ror.org/021vseb03"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W156932648.pdf","grobid_xml":"https://content.openalex.org/works/W156932648.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W200223693","https://openalex.org/W1503789224","https://openalex.org/W1530049455","https://openalex.org/W1681299129","https://openalex.org/W2083205357","https://openalex.org/W2096145771","https://openalex.org/W2099118758","https://openalex.org/W2110705209","https://openalex.org/W2117448986","https://openalex.org/W2121863487","https://openalex.org/W2128965063","https://openalex.org/W2134051188"],"related_works":["https://openalex.org/W3005560120","https://openalex.org/W2909304650","https://openalex.org/W2332834113","https://openalex.org/W4225393484","https://openalex.org/W1882507001","https://openalex.org/W20361778","https://openalex.org/W130452346","https://openalex.org/W2374724032","https://openalex.org/W2990027495","https://openalex.org/W2381453893"],"abstract_inverted_index":{"Learning":[0],"dialogue":[1,66,120],"strategies":[2,67,76],"using":[3,43,56,75],"the":[4,53,82],"reinforcement":[5,117],"learning":[6,97],"framework":[7],"is":[8],"problematic":[9],"due":[10],"to":[11,28,63],"its":[12],"expensive":[13],"computational":[14],"cost.":[15],"In":[16],"this":[17],"paper":[18],"we":[19],"propose":[20],"an":[21],"algorithm":[22],"that":[23],"reduces":[24],"a":[25,57],"state-action":[26],"space":[27],"one":[29],"which":[30],"includes":[31],"only":[32],"valid":[33],"state-actions.":[34],"We":[35],"performed":[36],"experiments":[37],"on":[38,78],"full":[39,86],"and":[40,49,70,102,110],"reduced":[41,79],"spaces":[42,80],"three":[44],"systems":[45],"(with":[46],"5,":[47],"9":[48],"20":[50],"slots)":[51],"in":[52],"travel":[54],"domain":[55],"simulated":[58],"environment.":[59],"The":[60],"task":[61],"was":[62],"learn":[64],"multi-goal":[65],"optimizing":[68],"single":[69],"multiple":[71],"confirmations.":[72],"Average":[73],"results":[74],"learnt":[77],"reveal":[81],"following":[83],"benefits":[84],"against":[85],"spaces:":[87],"1)":[88],"less":[89,107],"computer":[90],"memory":[91],"(94":[92],"%":[93,99,106,112],"reduction),":[94],"2)":[95],"faster":[96,100],"(93":[98],"convergence)":[101],"better":[103],"performance":[104],"(8.4":[105],"time":[108],"steps":[109],"7.7":[111],"higher":[113],"reward).":[114],"Index":[115],"Terms:":[116],"learning,":[118],"spoken":[119],"systems.":[121],"1.":[122]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}