{"id":"https://openalex.org/W2145180135","doi":"https://doi.org/10.1109/asru.2009.5373260","title":"The exploration/exploitation trade-off in Reinforcement Learning for dialogue management","display_name":"The exploration/exploitation trade-off in Reinforcement Learning for dialogue management","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2145180135","doi":"https://doi.org/10.1109/asru.2009.5373260","mag":"2145180135"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2009.5373260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & 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/A5079060755","display_name":"Sebastian Varges","orcid":null},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Sebastian Varges","raw_affiliation_strings":["Department of Information Engineering and Computer Science, University of Trento, Trento, Italy","Department of Information Engineering and Computer Science, University of Trento, 38050 Povo di Trento, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering and Computer Science, University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]},{"raw_affiliation_string":"Department of Information Engineering and Computer Science, University of Trento, 38050 Povo di Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062879885","display_name":"Giuseppe Riccardi","orcid":"https://orcid.org/0000-0002-0739-8184"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giuseppe Riccardi","raw_affiliation_strings":["Department of Information Engineering and Computer Science, University of Trento, Trento, Italy","Department of Information Engineering and Computer Science, University of Trento, 38050 Povo di Trento, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering and Computer Science, University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]},{"raw_affiliation_string":"Department of Information Engineering and Computer Science, University of Trento, 38050 Povo di Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028178077","display_name":"Silvia Quarteroni","orcid":null},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Silvia Quarteroni","raw_affiliation_strings":["Department of Information Engineering and Computer Science, University of Trento, Trento, Italy","Department of Information Engineering and Computer Science, University of Trento, 38050 Povo di Trento, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering and Computer Science, University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]},{"raw_affiliation_string":"Department of Information Engineering and Computer Science, University of Trento, 38050 Povo di Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056095515","display_name":"\u0410. \u0412. \u0418\u0432\u0430\u043d\u043e\u0432","orcid":"https://orcid.org/0000-0002-6410-5237"},"institutions":[{"id":"https://openalex.org/I193223587","display_name":"University of Trento","ror":"https://ror.org/05trd4x28","country_code":"IT","type":"education","lineage":["https://openalex.org/I193223587"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alexei V. Ivanov","raw_affiliation_strings":["Department of Information Engineering and Computer Science, University of Trento, Trento, Italy","Department of Information Engineering and Computer Science, University of Trento, 38050 Povo di Trento, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering and Computer Science, University of Trento, Trento, Italy","institution_ids":["https://openalex.org/I193223587"]},{"raw_affiliation_string":"Department of Information Engineering and Computer Science, University of Trento, 38050 Povo di Trento, Italy","institution_ids":["https://openalex.org/I193223587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5079060755"],"corresponding_institution_ids":["https://openalex.org/I193223587"],"apc_list":null,"apc_paid":null,"fwci":1.3549,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.85612718,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"479","last_page":"484"},"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":0.9986000061035156,"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":0.998199999332428,"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":0.8963623642921448},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.717664897441864},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7065138220787048},{"id":"https://openalex.org/keywords/session","display_name":"Session (web analytics)","score":0.6964514851570129},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6823689341545105},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.5954268574714661},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5459328293800354},{"id":"https://openalex.org/keywords/reward-system","display_name":"Reward system","score":0.48469260334968567},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.4723963439464569},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4676354229450226},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4331137537956238},{"id":"https://openalex.org/keywords/trade-off","display_name":"Trade-off","score":0.43100571632385254},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4199036955833435},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.37512820959091187},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32131919264793396},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.28652864694595337},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.21454834938049316},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.18418645858764648},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.11273550987243652},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09790998697280884}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8963623642921448},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.717664897441864},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7065138220787048},{"id":"https://openalex.org/C2779182362","wikidata":"https://www.wikidata.org/wiki/Q17126187","display_name":"Session (web analytics)","level":2,"score":0.6964514851570129},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6823689341545105},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.5954268574714661},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5459328293800354},{"id":"https://openalex.org/C143661069","wikidata":"https://www.wikidata.org/wiki/Q670713","display_name":"Reward system","level":2,"score":0.48469260334968567},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.4723963439464569},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4676354229450226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4331137537956238},{"id":"https://openalex.org/C142985932","wikidata":"https://www.wikidata.org/wiki/Q638123","display_name":"Trade-off","level":2,"score":0.43100571632385254},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4199036955833435},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.37512820959091187},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32131919264793396},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.28652864694595337},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.21454834938049316},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.18418645858764648},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.11273550987243652},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09790998697280884},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/asru.2009.5373260","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373260","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.165.1495","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.165.1495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dit.unitn.it/~varges/asru2009/asru2009.pdf","raw_type":"text"},{"id":"pmh:oai:iris.unitn.it:11572/85329","is_oa":false,"landing_page_url":"http://hdl.handle.net/11572/85329","pdf_url":null,"source":{"id":"https://openalex.org/S4306401913","display_name":"Institutional Research Information System (Universit\u00e0 degli Studi di Trento)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I193223587","host_organization_name":"University of Trento","host_organization_lineage":["https://openalex.org/I193223587"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2010642616","https://openalex.org/W2106157256","https://openalex.org/W2111550420","https://openalex.org/W2115101920","https://openalex.org/W2121863487","https://openalex.org/W2132997613","https://openalex.org/W2137877387","https://openalex.org/W2148796308","https://openalex.org/W2155898337","https://openalex.org/W2168490009","https://openalex.org/W2172264025","https://openalex.org/W2408200822","https://openalex.org/W2438667436","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W4214717370","https://openalex.org/W6677341168","https://openalex.org/W6683094211","https://openalex.org/W6714440685"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1515117609","https://openalex.org/W1589140671","https://openalex.org/W4323315247","https://openalex.org/W2294884454","https://openalex.org/W3169161914","https://openalex.org/W4321379664","https://openalex.org/W2211790881"],"abstract_inverted_index":{"Conversational":[0],"systems":[1],"use":[2,76],"deterministic":[3],"rules":[4],"that":[5,109,115],"trigger":[6],"actions":[7],"such":[8],"as":[9,80],"requests":[10],"for":[11,28,39],"confirmation":[12],"or":[13],"clarification.":[14],"More":[15],"recently,":[16],"reinforcement":[17],"learning":[18,82],"and":[19,47,61,113],"(partially":[20],"observable)":[21],"Markov":[22],"decision":[23],"processes":[24],"have":[25],"been":[26],"proposed":[27],"this":[29,32],"task.":[30],"In":[31],"paper,":[33],"we":[34],"investigate":[35],"action":[36],"selection":[37],"strategies":[38],"dialogue":[40],"management,":[41],"in":[42,100],"particular":[43],"the":[44,54,65,70,86,90,117,120],"exploration/exploitation":[45],"trade-off":[46],"its":[48],"impact":[49],"on":[50],"final":[51,101,121],"reward":[52,56,63,67,87,102,112,118],"(i.e.":[53,64],"session":[55],"after":[57],"optimization":[58],"has":[59],"ended)":[60],"lifetime":[62,111],"overall":[66],"accumulated":[68],"over":[69],"learner's":[71],"lifetime).":[72],"We":[73],"propose":[74],"to":[75,84],"interleaved":[77],"exploitation":[78],"sessions":[79,105],"a":[81,96,107],"methodology":[83],"assess":[85],"obtained":[88],"from":[89],"current":[91],"policy.":[92,122],"The":[93],"experiments":[94],"show":[95],"statistically":[97],"significant":[98],"difference":[99],"of":[103,119],"exploitation-only":[104],"between":[106],"system":[108],"optimizes":[110],"one":[114],"maximizes":[116]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}