{"id":"https://openalex.org/W2911176533","doi":"https://doi.org/10.1142/s0218001419510054","title":"Variational Bayesian Exploration-Based Active Sarsa Algorithm","display_name":"Variational Bayesian Exploration-Based Active Sarsa Algorithm","publication_year":2019,"publication_date":"2019-01-11","ids":{"openalex":"https://openalex.org/W2911176533","doi":"https://doi.org/10.1142/s0218001419510054","mag":"2911176533"},"language":"en","primary_location":{"id":"doi:10.1142/s0218001419510054","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001419510054","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial 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/A5101997111","display_name":"Qiming Fu","orcid":"https://orcid.org/0000-0002-8720-9071"},"institutions":[{"id":"https://openalex.org/I308837","display_name":"Suzhou University of Science and Technology","ror":"https://ror.org/04en8wb91","country_code":"CN","type":"education","lineage":["https://openalex.org/I308837"]},{"id":"https://openalex.org/I4210110458","display_name":"Institute of Electronics","ror":"https://ror.org/01z143507","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210110458"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiming Fu","raw_affiliation_strings":["Institute of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","Jiangsu Key Laboratory of Intelligent Building Energy Efficiency, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","Suzhou Key Laboratory of Mobile Networking and Applied Technologies, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China"],"raw_orcid":"https://orcid.org/0000-0002-8720-9071","affiliations":[{"raw_affiliation_string":"Institute of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","institution_ids":["https://openalex.org/I308837","https://openalex.org/I4210110458"]},{"raw_affiliation_string":"Jiangsu Key Laboratory of Intelligent Building Energy Efficiency, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","institution_ids":["https://openalex.org/I308837"]},{"raw_affiliation_string":"Suzhou Key Laboratory of Mobile Networking and Applied Technologies, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","institution_ids":["https://openalex.org/I308837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081285185","display_name":"Zhengxia Yang","orcid":"https://orcid.org/0000-0003-2522-808X"},"institutions":[{"id":"https://openalex.org/I308837","display_name":"Suzhou University of Science and Technology","ror":"https://ror.org/04en8wb91","country_code":"CN","type":"education","lineage":["https://openalex.org/I308837"]},{"id":"https://openalex.org/I4210110458","display_name":"Institute of Electronics","ror":"https://ror.org/01z143507","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210110458"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengxia Yang","raw_affiliation_strings":["Institute of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","Jiangsu Key Laboratory of Intelligent Building Energy Efficiency, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","Suzhou Key Laboratory of Mobile Networking and Applied Technologies, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","institution_ids":["https://openalex.org/I308837","https://openalex.org/I4210110458"]},{"raw_affiliation_string":"Jiangsu Key Laboratory of Intelligent Building Energy Efficiency, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","institution_ids":["https://openalex.org/I308837"]},{"raw_affiliation_string":"Suzhou Key Laboratory of Mobile Networking and Applied Technologies, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","institution_ids":["https://openalex.org/I308837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009920251","display_name":"You Lu","orcid":"https://orcid.org/0000-0002-0930-2764"},"institutions":[{"id":"https://openalex.org/I308837","display_name":"Suzhou University of Science and Technology","ror":"https://ror.org/04en8wb91","country_code":"CN","type":"education","lineage":["https://openalex.org/I308837"]},{"id":"https://openalex.org/I4210110458","display_name":"Institute of Electronics","ror":"https://ror.org/01z143507","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210110458"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"You Lu","raw_affiliation_strings":["Institute of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","Jiangsu Key Laboratory of Intelligent Building Energy Efficiency, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","Suzhou Key Laboratory of Mobile Networking and Applied Technologies, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","institution_ids":["https://openalex.org/I308837","https://openalex.org/I4210110458"]},{"raw_affiliation_string":"Jiangsu Key Laboratory of Intelligent Building Energy Efficiency, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","institution_ids":["https://openalex.org/I308837"]},{"raw_affiliation_string":"Suzhou Key Laboratory of Mobile Networking and Applied Technologies, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","institution_ids":["https://openalex.org/I308837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076525932","display_name":"Hongjie Wu","orcid":"https://orcid.org/0000-0001-5921-8707"},"institutions":[{"id":"https://openalex.org/I308837","display_name":"Suzhou University of Science and Technology","ror":"https://ror.org/04en8wb91","country_code":"CN","type":"education","lineage":["https://openalex.org/I308837"]},{"id":"https://openalex.org/I4210110458","display_name":"Institute of Electronics","ror":"https://ror.org/01z143507","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210110458"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongjie Wu","raw_affiliation_strings":["Institute of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","Jiangsu Key Laboratory of Intelligent Building Energy Efficiency, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","Suzhou Key Laboratory of Mobile Networking and Applied Technologies, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","institution_ids":["https://openalex.org/I308837","https://openalex.org/I4210110458"]},{"raw_affiliation_string":"Jiangsu Key Laboratory of Intelligent Building Energy Efficiency, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","institution_ids":["https://openalex.org/I308837"]},{"raw_affiliation_string":"Suzhou Key Laboratory of Mobile Networking and Applied Technologies, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","institution_ids":["https://openalex.org/I308837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086390256","display_name":"Fuyuan Hu","orcid":"https://orcid.org/0000-0002-6818-2221"},"institutions":[{"id":"https://openalex.org/I308837","display_name":"Suzhou University of Science and Technology","ror":"https://ror.org/04en8wb91","country_code":"CN","type":"education","lineage":["https://openalex.org/I308837"]},{"id":"https://openalex.org/I4210110458","display_name":"Institute of Electronics","ror":"https://ror.org/01z143507","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210110458"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuyuan Hu","raw_affiliation_strings":["Institute of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","Jiangsu Key Laboratory of Intelligent Building Energy Efficiency, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","Suzhou Key Laboratory of Mobile Networking and Applied Technologies, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","institution_ids":["https://openalex.org/I308837","https://openalex.org/I4210110458"]},{"raw_affiliation_string":"Jiangsu Key Laboratory of Intelligent Building Energy Efficiency, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","institution_ids":["https://openalex.org/I308837"]},{"raw_affiliation_string":"Suzhou Key Laboratory of Mobile Networking and Applied Technologies, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","institution_ids":["https://openalex.org/I308837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100437534","display_name":"Jianping Chen","orcid":"https://orcid.org/0000-0002-2109-5761"},"institutions":[{"id":"https://openalex.org/I308837","display_name":"Suzhou University of Science and Technology","ror":"https://ror.org/04en8wb91","country_code":"CN","type":"education","lineage":["https://openalex.org/I308837"]},{"id":"https://openalex.org/I4210110458","display_name":"Institute of Electronics","ror":"https://ror.org/01z143507","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210110458"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianping Chen","raw_affiliation_strings":["Institute of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","Jiangsu Key Laboratory of Intelligent Building Energy Efficiency, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","Suzhou Key Laboratory of Mobile Networking and Applied Technologies, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Electronics and Information Engineering, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","institution_ids":["https://openalex.org/I308837","https://openalex.org/I4210110458"]},{"raw_affiliation_string":"Jiangsu Key Laboratory of Intelligent Building Energy Efficiency, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","institution_ids":["https://openalex.org/I308837"]},{"raw_affiliation_string":"Suzhou Key Laboratory of Mobile Networking and Applied Technologies, Suzhou University of Science and Technology, Suzhou, Jiangsu 215009, P. R. China","institution_ids":["https://openalex.org/I308837"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100437534"],"corresponding_institution_ids":["https://openalex.org/I308837","https://openalex.org/I4210110458"],"apc_list":null,"apc_paid":null,"fwci":0.1451,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5496542,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"33","issue":"10","first_page":"1951005","last_page":"1951005"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9951000213623047,"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/algorithm","display_name":"Algorithm","score":0.696832001209259},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6250394582748413},{"id":"https://openalex.org/keywords/wake-sleep-algorithm","display_name":"Wake-sleep algorithm","score":0.5111034512519836},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.49061551690101624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.478506475687027},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4650617241859436},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.45284026861190796},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.45071399211883545},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36899125576019287},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3299449682235718},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25594383478164673},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.16705870628356934},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.13344624638557434},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.10101500153541565}],"concepts":[{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.696832001209259},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6250394582748413},{"id":"https://openalex.org/C17061570","wikidata":"https://www.wikidata.org/wiki/Q7960888","display_name":"Wake-sleep algorithm","level":4,"score":0.5111034512519836},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.49061551690101624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.478506475687027},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4650617241859436},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.45284026861190796},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.45071399211883545},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36899125576019287},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3299449682235718},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25594383478164673},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.16705870628356934},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.13344624638557434},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.10101500153541565},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C117765406","wikidata":"https://www.wikidata.org/wiki/Q5362437","display_name":"Generalization error","level":3,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218001419510054","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218001419510054","pdf_url":null,"source":{"id":"https://openalex.org/S41486457","display_name":"International Journal of Pattern Recognition and Artificial Intelligence","issn_l":"0218-0014","issn":["0218-0014","1793-6381"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Pattern Recognition and Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1550989509","https://openalex.org/W2058735307","https://openalex.org/W2059836092","https://openalex.org/W2070615940","https://openalex.org/W2075022034","https://openalex.org/W2083417417","https://openalex.org/W2115979064","https://openalex.org/W2117212296","https://openalex.org/W2130935956","https://openalex.org/W2266236329","https://openalex.org/W2666874989","https://openalex.org/W2708325519","https://openalex.org/W2768605762","https://openalex.org/W2770676902","https://openalex.org/W2895133117","https://openalex.org/W2998989984","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W4255837520","https://openalex.org/W2387011115","https://openalex.org/W4234808182","https://openalex.org/W4255628145","https://openalex.org/W2382043075","https://openalex.org/W2809151339","https://openalex.org/W2216913934","https://openalex.org/W2360673138","https://openalex.org/W2809370583","https://openalex.org/W2033738158"],"abstract_inverted_index":{"We":[0],"proposed":[1,104],"an":[2,45,50],"improved":[3],"variational":[4,31],"Bayesian":[5,32,125],"exploration-based":[6],"active":[7],"Sarsa":[8,115,126],"(VBE-ASAR)":[9],"algorithm,":[10,116,119],"which":[11,41],"tries":[12],"to":[13,36,48,65,74,84,106],"balance":[14],"the":[15,23,28,38,60,67,76,86,92,96,103,107,114,117,120,124,133],"exploration":[16,46,68],"and":[17,20,95,111,123],"exploitation":[18],"dilemma,":[19],"speeds":[21],"up":[22],"convergence":[24],"rate.":[25,140],"First,":[26],"in":[27,63],"learning":[29,61,71,139],"process,":[30,62],"method":[33],"is":[34,42,72,82],"adopted":[35],"measure":[37,85],"information":[39],"gain,":[40],"used":[43,73],"as":[44],"factor":[47],"construct":[49],"internal":[51],"reward":[52],"function":[53],"for":[54],"heuristic":[55],"exploration.":[56],"In":[57],"addition,":[58],"before":[59],"order":[64],"improve":[66],"performance,":[69],"transfer":[70],"initialize":[75],"value":[77],"function,":[78],"where":[79],"Bisimulation":[80],"metric":[81],"introduced":[83],"distance":[87],"between":[88],"two":[89],"states":[90],"from":[91],"source":[93],"MDP":[94],"target":[97],"MDP,":[98],"respectively.":[99],"Finally,":[100],"we":[101],"apply":[102],"algorithm":[105,122,135],"cliff":[108],"walking":[109],"problem,":[110],"compare":[112],"with":[113],"Q-Learning":[118],"VFT-Sarsa":[121],"(BS)":[127],"algorithm.":[128],"Experimental":[129],"results":[130],"show":[131],"that":[132],"VBE-ASAR":[134],"has":[136],"a":[137],"faster":[138]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
