{"id":"https://openalex.org/W7161248187","doi":"https://doi.org/10.1016/j.neunet.2026.109110","title":"Collective reflection-based multi-agent reinforcement learning framework for task-oriented dialogue policy learning","display_name":"Collective reflection-based multi-agent reinforcement learning framework for task-oriented dialogue policy learning","publication_year":2026,"publication_date":"2026-05-15","ids":{"openalex":"https://openalex.org/W7161248187","doi":"https://doi.org/10.1016/j.neunet.2026.109110","pmid":"https://pubmed.ncbi.nlm.nih.gov/42176665"},"language":"en","primary_location":{"id":"doi:10.1016/j.neunet.2026.109110","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.neunet.2026.109110","pdf_url":null,"source":{"id":"https://openalex.org/S123019304","display_name":"Neural Networks","issn_l":"0893-6080","issn":["0893-6080","1879-2782"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Networks","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5136226877","display_name":"Kai Xu","orcid":"https://orcid.org/0009-0004-5116-3739"},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]},{"id":"https://openalex.org/I4210122543","display_name":"Guangdong Polytechnic Normal University","ror":"https://ror.org/02pcb5m77","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210122543"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Xu","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Intellectual Property and Big Data, Guangdong Polytechnic Normal University, Guangzhou, 510665, Guangdong, China; School of Software Engineering, South China University of Technology, Guangzhou, 510641, Guangdong, China. Electronic address: sekxu@mail.scut.edu.cn"],"raw_orcid":"https://orcid.org/0009-0004-5116-3739","affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Intellectual Property and Big Data, Guangdong Polytechnic Normal University, Guangzhou, 510665, Guangdong, China; School of Software Engineering, South China University of Technology, Guangzhou, 510641, Guangdong, China. Electronic address: sekxu@mail.scut.edu.cn","institution_ids":["https://openalex.org/I4210122543","https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136244562","display_name":"Zhenyu Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]},{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhenyu Wang","raw_affiliation_strings":["School of Software Engineering, South China University of Technology, Guangzhou, 510641, Guangdong, China. Electronic address: wangzy@scut.edu.cn"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou, 510641, Guangdong, China. Electronic address: wangzy@scut.edu.cn","institution_ids":["https://openalex.org/I90610280","https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136198571","display_name":"Yangyang Zhao","orcid":"https://orcid.org/0000-0003-1890-6508"},"institutions":[{"id":"https://openalex.org/I56934997","display_name":"Changsha University of Science and Technology","ror":"https://ror.org/03yph8055","country_code":"CN","type":"education","lineage":["https://openalex.org/I56934997"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yangyang Zhao","raw_affiliation_strings":["Department of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha, 410000, HuNan, China. Electronic address: yyz@csust.edu.cn"],"raw_orcid":"https://orcid.org/0000-0003-1890-6508","affiliations":[{"raw_affiliation_string":"Department of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha, 410000, HuNan, China. Electronic address: yyz@csust.edu.cn","institution_ids":["https://openalex.org/I56934997"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017710092","display_name":"Bopeng Fang","orcid":"https://orcid.org/0000-0002-1054-3792"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bopeng Fang","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, 611731, Sichuan, China. Electronic address: bopengF@outlook.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, 611731, Sichuan, China. Electronic address: bopengF@outlook.com","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5136198571","https://openalex.org/A5136244562"],"corresponding_institution_ids":["https://openalex.org/I139024713","https://openalex.org/I56934997","https://openalex.org/I90610280"],"apc_list":{"value":3350,"currency":"USD","value_usd":3350},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74395183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"203","issue":null,"first_page":"109110","last_page":"109110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.2612999975681305,"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":0.2612999975681305,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.147599995136261,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.08070000261068344,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.6272000074386597},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.4722999930381775},{"id":"https://openalex.org/keywords/experiential-learning","display_name":"Experiential learning","score":0.30230000615119934},{"id":"https://openalex.org/keywords/collaborative-learning","display_name":"Collaborative learning","score":0.2939000129699707},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.2896000146865845}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6272000074386597},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5534999966621399},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.4722999930381775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4659999907016754},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3140999972820282},{"id":"https://openalex.org/C37228920","wikidata":"https://www.wikidata.org/wiki/Q1307600","display_name":"Experiential learning","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.29420000314712524},{"id":"https://openalex.org/C138020889","wikidata":"https://www.wikidata.org/wiki/Q2349659","display_name":"Collaborative learning","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2854999899864197},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.2653999924659729},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2603999972343445},{"id":"https://openalex.org/C51672120","wikidata":"https://www.wikidata.org/wiki/Q303446","display_name":"Cooperative learning","level":3,"score":0.2549000084400177}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.neunet.2026.109110","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.neunet.2026.109110","pdf_url":null,"source":{"id":"https://openalex.org/S123019304","display_name":"Neural Networks","issn_l":"0893-6080","issn":["0893-6080","1879-2782"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Networks","raw_type":"journal-article"},{"id":"pmid:42176665","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42176665","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural networks : the official journal of the International Neural Network Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320318653","display_name":"Guangdong Polytechnic Normal University","ror":"https://ror.org/02pcb5m77"},{"id":"https://openalex.org/F4320322843","display_name":"Natural Science Foundation of\u00a0Hunan Province","ror":null},{"id":"https://openalex.org/F4320324202","display_name":"Guangdong Science and Technology Department","ror":"https://ror.org/00tjzgn92"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2139898527","https://openalex.org/W2998458199","https://openalex.org/W3037211177","https://openalex.org/W3101282510","https://openalex.org/W4220747123","https://openalex.org/W4297227993","https://openalex.org/W4313703382","https://openalex.org/W4315473113","https://openalex.org/W4319335480","https://openalex.org/W4319878952","https://openalex.org/W4376851154","https://openalex.org/W4381186279","https://openalex.org/W4382203395","https://openalex.org/W4390753602","https://openalex.org/W4391305545","https://openalex.org/W4392946938","https://openalex.org/W4399282679","https://openalex.org/W4399346003"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-14T06:11:07.267592","created_date":"2026-05-16T00:00:00"}
