{"id":"https://openalex.org/W4404774330","doi":"https://doi.org/10.1007/s10489-024-05867-3","title":"Windows deep transformer Q-networks: an extended variance reduction architecture for partially observable reinforcement learning","display_name":"Windows deep transformer Q-networks: an extended variance reduction architecture for partially observable reinforcement learning","publication_year":2024,"publication_date":"2024-11-27","ids":{"openalex":"https://openalex.org/W4404774330","doi":"https://doi.org/10.1007/s10489-024-05867-3"},"language":"en","primary_location":{"id":"doi:10.1007/s10489-024-05867-3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-024-05867-3","pdf_url":null,"source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-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/A5115601609","display_name":"Zijian Wang","orcid":"https://orcid.org/0009-0008-0160-8014"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zijian Wang","raw_affiliation_strings":["Qingdao Institute of Software & College of Computer Science and Technology, China University of Petroleum (East China), Changjiang West Road, Qingdao, Shandong, 266580, China","Qingdao Institute of Software & College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qingdao Institute of Software & College of Computer Science and Technology, China University of Petroleum (East China), Changjiang West Road, Qingdao, Shandong, 266580, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210162190"]},{"raw_affiliation_string":"Qingdao Institute of Software & College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, China","institution_ids":["https://openalex.org/I4210162190"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102012404","display_name":"Bin Wang","orcid":"https://orcid.org/0000-0002-0092-3951"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bin Wang","raw_affiliation_strings":["Qingdao Institute of Software & College of Computer Science and Technology, China University of Petroleum (East China), Changjiang West Road, Qingdao, Shandong, 266580, China","Qingdao Institute of Software & College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0002-0092-3951","affiliations":[{"raw_affiliation_string":"Qingdao Institute of Software & College of Computer Science and Technology, China University of Petroleum (East China), Changjiang West Road, Qingdao, Shandong, 266580, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210162190"]},{"raw_affiliation_string":"Qingdao Institute of Software & College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, China","institution_ids":["https://openalex.org/I4210162190"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109702920","display_name":"Hongbo Dou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongbo Dou","raw_affiliation_strings":["Qingdao Institute of Software & College of Computer Science and Technology, China University of Petroleum (East China), Changjiang West Road, Qingdao, Shandong, 266580, China","Qingdao Institute of Software & College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qingdao Institute of Software & College of Computer Science and Technology, China University of Petroleum (East China), Changjiang West Road, Qingdao, Shandong, 266580, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210162190"]},{"raw_affiliation_string":"Qingdao Institute of Software & College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, China","institution_ids":["https://openalex.org/I4210162190"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045926855","display_name":"Zhongyuan Liu","orcid":"https://orcid.org/0000-0002-5600-8998"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhongyuan Liu","raw_affiliation_strings":["Qingdao Institute of Software & College of Computer Science and Technology, China University of Petroleum (East China), Changjiang West Road, Qingdao, Shandong, 266580, China","Qingdao Institute of Software & College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qingdao Institute of Software & College of Computer Science and Technology, China University of Petroleum (East China), Changjiang West Road, Qingdao, Shandong, 266580, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210162190"]},{"raw_affiliation_string":"Qingdao Institute of Software & College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, China","institution_ids":["https://openalex.org/I4210162190"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5045926855","https://openalex.org/A5102012404","https://openalex.org/A5109702920","https://openalex.org/A5115601609"],"corresponding_institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210162190"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":0.7203,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.76786925,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"55","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9886999726295471,"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/T10320","display_name":"Neural Networks and Applications","score":0.988099992275238,"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/computer-science","display_name":"Computer science","score":0.8391255140304565},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8101868033409119},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.8089354038238525},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7046440243721008},{"id":"https://openalex.org/keywords/variance-reduction","display_name":"Variance reduction","score":0.6707959175109863},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6544305086135864},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4863000810146332},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.48382821679115295},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4563191533088684},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4088992178440094},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.15159383416175842},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.13403940200805664},{"id":"https://openalex.org/keywords/composite-material","display_name":"Composite material","score":0.11449208855628967},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.07576549053192139},{"id":"https://openalex.org/keywords/accounting","display_name":"Accounting","score":0.06748279929161072},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.061071544885635376}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8391255140304565},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8101868033409119},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.8089354038238525},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7046440243721008},{"id":"https://openalex.org/C62644790","wikidata":"https://www.wikidata.org/wiki/Q3454689","display_name":"Variance reduction","level":3,"score":0.6707959175109863},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6544305086135864},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4863000810146332},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.48382821679115295},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4563191533088684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4088992178440094},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.15159383416175842},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.13403940200805664},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.11449208855628967},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.07576549053192139},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.06748279929161072},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.061071544885635376},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10489-024-05867-3","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-024-05867-3","pdf_url":null,"source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2612972167","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2798878556","https://openalex.org/W3136222254","https://openalex.org/W3144523431","https://openalex.org/W3177023080","https://openalex.org/W4206513913","https://openalex.org/W4210257517","https://openalex.org/W4225283319","https://openalex.org/W4294691690","https://openalex.org/W4306955484","https://openalex.org/W4309452521","https://openalex.org/W4385603717","https://openalex.org/W4390413862","https://openalex.org/W6600721014","https://openalex.org/W6600753396","https://openalex.org/W6602539713"],"related_works":["https://openalex.org/W1994680671","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2000283393","https://openalex.org/W2920061524","https://openalex.org/W2002320543","https://openalex.org/W2061947244","https://openalex.org/W2150232912","https://openalex.org/W1977959518","https://openalex.org/W2054940838"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
