乐胖代购免代理版

{"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":{"is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-149","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/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"],"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"],"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"],"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"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.919,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.739381,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":88},"biblio":{"volume":null,"issue":null,"first_page":"paper 1282","last_page":"0"},"is_retracted":false,"is_paratext":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":0.9966,"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":0.9957,"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":[],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.93013585},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.74714077},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6729466},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.57921934},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5741679},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5533019},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5069499},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5003896},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.46765488},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.45071352},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4491248},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44625363},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.41677624},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.092277706},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09182936},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07989341},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-149","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/portal/en/publications/learning-multigoal-dialogue-strategies-using-reinforcement-learning-with-reduced-stateaction-spaces(b1b36e32-9e44-473c-a70b-d03e9c8f483f).html","pdf_url":"https://www.research.ed.ac.uk/files/27377487/rss_icslp2006.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":["University of Edinburgh"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://www.pure.ed.ac.uk/ws/files/27377487/rss_icslp2006.pdf","pdf_url":"https://www.pure.ed.ac.uk/ws/files/27377487/rss_icslp2006.pdf","source":{"id":"https://openalex.org/S4306400320","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":["University of Edinburgh"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/portal/en/publications/learning-multigoal-dialogue-strategies-using-reinforcement-learning-with-reduced-stateaction-spaces(b1b36e32-9e44-473c-a70b-d03e9c8f483f).html","pdf_url":"https://www.research.ed.ac.uk/files/27377487/rss_icslp2006.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":["University of Edinburgh"],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":12,"referenced_works":["https://openalex.org/W1503789224","https://openalex.org/W1530049455","https://openalex.org/W1681299129","https://openalex.org/W200223693","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/W4225393484","https://openalex.org/W3005560120","https://openalex.org/W2990027495","https://openalex.org/W2909304650","https://openalex.org/W2381453893","https://openalex.org/W2374724032","https://openalex.org/W2332834113","https://openalex.org/W20361778","https://openalex.org/W1882507001","https://openalex.org/W130452346"],"abstract_inverted_index":{"Learning":[0],"dialogue":[1,66,116],"strategies":[2,67,76],"using":[3,43,56,75],"the":[4,53,82],"reinforcement":[5,113],"learning":[6,96],"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":[40,49,70,100,107],"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":[89,104],"computer":[90],"memory":[91],"(94%":[92],"reduction),":[93],"2)":[94],"faster":[95,98],"(93%":[97],"convergence)":[99],"better":[101],"performance":[102],"(8.4%":[103],"time":[105],"steps":[106],"7.7%":[108],"higher":[109],"reward).":[110],"Index":[111],"Terms:":[112],"learning,":[114],"spoken":[115],"systems.":[117]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W156932648","counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2024-12-12T12:51:05.132415","created_date":"2016-06-24"}