{"id":"https://openalex.org/W4317928369","doi":"https://doi.org/10.1007/978-3-031-24383-7_22","title":"Learning Dialogue Policy Efficiently Through Dyna Proximal Policy Optimization","display_name":"Learning Dialogue Policy Efficiently Through Dyna Proximal Policy Optimization","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4317928369","doi":"https://doi.org/10.1007/978-3-031-24383-7_22"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-24383-7_22","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-24383-7_22","pdf_url":null,"source":{"id":"https://openalex.org/S4393917809","display_name":"Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","issn_l":"1867-8211","issn":["1867-8211","1867-822X"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","raw_type":"book-chapter"},"type":"book-chapter","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/A5101193908","display_name":"Chen-Ping Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chenping Huang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101755033","display_name":"Bin Cao","orcid":"https://orcid.org/0000-0003-1062-6309"},"institutions":[{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Cao","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China","institution_ids":["https://openalex.org/I55712492"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101193908"],"corresponding_institution_ids":["https://openalex.org/I55712492"],"apc_list":null,"apc_paid":null,"fwci":0.3429,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.65976046,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"396","last_page":"414"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9993000030517578,"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/T12128","display_name":"AI in Service Interactions","score":0.9937000274658203,"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":0.74076247215271},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7401198744773865},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7363740801811218},{"id":"https://openalex.org/keywords/ticket","display_name":"Ticket","score":0.5729106068611145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5123728513717651},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.44681432843208313},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.42881354689598083},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3625975251197815},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.14732956886291504},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11943221092224121}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.74076247215271},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7401198744773865},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7363740801811218},{"id":"https://openalex.org/C2776540713","wikidata":"https://www.wikidata.org/wiki/Q7800647","display_name":"Ticket","level":2,"score":0.5729106068611145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5123728513717651},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.44681432843208313},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.42881354689598083},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3625975251197815},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.14732956886291504},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11943221092224121},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-24383-7_22","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-24383-7_22","pdf_url":null,"source":{"id":"https://openalex.org/S4393917809","display_name":"Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","issn_l":"1867-8211","issn":["1867-8211","1867-822X"],"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1491843047","https://openalex.org/W1518203739","https://openalex.org/W1948566616","https://openalex.org/W2062175565","https://openalex.org/W2145339207","https://openalex.org/W2604382266","https://openalex.org/W2798494119","https://openalex.org/W2889186204","https://openalex.org/W2949476504","https://openalex.org/W2951805158","https://openalex.org/W2962682659","https://openalex.org/W2963043030","https://openalex.org/W2963433587","https://openalex.org/W2963857397","https://openalex.org/W2971159908","https://openalex.org/W2979372603","https://openalex.org/W3013860672","https://openalex.org/W3034330559","https://openalex.org/W3034782127","https://openalex.org/W3035597485","https://openalex.org/W3037879762","https://openalex.org/W3102854726","https://openalex.org/W3163045655","https://openalex.org/W3174076858","https://openalex.org/W3175095351","https://openalex.org/W3177075735","https://openalex.org/W3200895474","https://openalex.org/W3212099586","https://openalex.org/W3214586773","https://openalex.org/W4290742115","https://openalex.org/W6600103761","https://openalex.org/W6814003322"],"related_works":["https://openalex.org/W132856376","https://openalex.org/W4288388931","https://openalex.org/W2892636954","https://openalex.org/W4206805925","https://openalex.org/W4375841483","https://openalex.org/W2022874741","https://openalex.org/W2364431604","https://openalex.org/W2018860124","https://openalex.org/W3112526189","https://openalex.org/W2572886659"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
