{"id":"https://openalex.org/W4412886675","doi":"https://doi.org/10.18653/v1/2025.acl-long.171","title":"An Efficient Task-Oriented Dialogue Policy: Evolutionary Reinforcement Learning Injected by Elite Individuals","display_name":"An Efficient Task-Oriented Dialogue Policy: Evolutionary Reinforcement Learning Injected by Elite Individuals","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412886675","doi":"https://doi.org/10.18653/v1/2025.acl-long.171"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.171","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.171","pdf_url":"https://aclanthology.org/2025.acl-long.171.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.171.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103015387","display_name":"Yangyang Zhao","orcid":"https://orcid.org/0000-0003-1890-6508"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yangyang Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029380465","display_name":"Ben Niu","orcid":"https://orcid.org/0000-0002-3680-5594"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ben Niu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092102582","display_name":"L. Q. Qin","orcid":"https://orcid.org/0009-0005-1142-7397"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Libo Qin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5107808323","display_name":"Shihan Wang","orcid":"https://orcid.org/0000-0001-5971-7522"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shihan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3429","last_page":"3442"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12128","display_name":"AI in Service Interactions","score":0.6597999930381775,"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/T12128","display_name":"AI in Service Interactions","score":0.6597999930381775,"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/T12031","display_name":"Speech and dialogue systems","score":0.6579999923706055,"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":0.8423982858657837},{"id":"https://openalex.org/keywords/elite","display_name":"Elite","score":0.7988133430480957},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.717715322971344},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5714938640594482},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.49301621317863464},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4429889917373657},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.24371027946472168},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.1592867374420166},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.1479095220565796},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.10177114605903625},{"id":"https://openalex.org/keywords/management","display_name":"Management","score":0.08972877264022827}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8423982858657837},{"id":"https://openalex.org/C2775987171","wikidata":"https://www.wikidata.org/wiki/Q192797","display_name":"Elite","level":3,"score":0.7988133430480957},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.717715322971344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5714938640594482},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.49301621317863464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4429889917373657},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.24371027946472168},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.1592867374420166},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.1479095220565796},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.10177114605903625},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.08972877264022827},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.171","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.171","pdf_url":"https://aclanthology.org/2025.acl-long.171.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.171","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.171","pdf_url":"https://aclanthology.org/2025.acl-long.171.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322843","display_name":"Natural Science Foundation of\u00a0Hunan Province","ror":null},{"id":"https://openalex.org/F4320335581","display_name":"Young Scientists Fund","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412886675.pdf","grobid_xml":"https://content.openalex.org/works/W4412886675.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3173976592","https://openalex.org/W4386010110","https://openalex.org/W2322432826","https://openalex.org/W2047008865","https://openalex.org/W2943855857","https://openalex.org/W650538140","https://openalex.org/W1531633990","https://openalex.org/W1589465577","https://openalex.org/W2350164584","https://openalex.org/W3126144941"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"Learning":[2],"(DRL)":[3],"is":[4],"widely":[5],"used":[6],"in":[7,36,91,147],"task-oriented":[8,163],"dialogue":[9,13,92,164],"systems":[10],"to":[11,18,24,47,77,99,111],"optimize":[12],"policy,":[14],"but":[15],"it":[16],"struggles":[17],"balance":[19,80,134],"exploration":[20,82,136,149],"and":[21,30,83,137,160],"exploitation":[22],"due":[23],"the":[25,50,65,72,85,122,133,141,144],"high":[26],"dimensionality":[27],"of":[28,53,69,75,88,143,158],"state":[29],"action":[31],"spaces.This":[32],"challenge":[33],"often":[34],"results":[35],"local":[37,73],"optima":[38],"or":[39],"poor":[40],"convergence.Evolutionary":[41],"Algorithms":[42],"(EAs)":[43],"have":[44],"been":[45,152],"proven":[46],"effectively":[48],"explore":[49],"solution":[51],"space":[52],"neural":[54],"networks":[55],"by":[56,60,116],"maintaining":[57],"population":[58],"diversity.Inspired":[59],"this,":[61],"we":[62,103],"innovatively":[63],"combine":[64],"global":[66],"search":[67,114],"capabilities":[68],"EA":[70,159],"with":[71],"optimization":[74],"DRL":[76,161],"achieve":[78],"a":[79],"between":[81,135],"exploitation.Nevertheless,":[84],"inherent":[86],"flexibility":[87],"natural":[89],"language":[90],"tasks":[93],"complicates":[94],"this":[95],"direct":[96],"integration,":[97],"leading":[98],"prolonged":[100],"evolutionary":[101],"times.Thus,":[102],"further":[104],"propose":[105],"an":[106,155],"elite":[107],"individual":[108],"injection":[109],"mechanism":[110,146],"enhance":[112],"EA's":[113],"efficiency":[115],"adaptively":[117],"introducing":[118],"best-performing":[119],"individuals":[120],"into":[121],"population.Experiments":[123],"across":[124],"four":[125],"datasets":[126],"show":[127],"that":[128],"our":[129],"approach":[130],"significantly":[131],"improves":[132],"exploitation,":[138],"boosting":[139],"performance.Moreover,":[140],"effectiveness":[142],"EII":[145],"reducing":[148],"time":[150],"has":[151],"demonstrated,":[153],"achieving":[154],"efficient":[156],"integration":[157],"on":[162],"policy":[165],"tasks.":[166]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}