{"id":"https://openalex.org/W4283393398","doi":"https://doi.org/10.3233/jifs-210956","title":"A novel model-based reinforcement learning algorithm for solving the problem of unbalanced reward","display_name":"A novel model-based reinforcement learning algorithm for solving the problem of unbalanced reward","publication_year":2022,"publication_date":"2022-06-24","ids":{"openalex":"https://openalex.org/W4283393398","doi":"https://doi.org/10.3233/jifs-210956"},"language":"en","primary_location":{"id":"doi:10.3233/jifs-210956","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-210956","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Fuzzy Systems","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/A5101184091","display_name":"Yinlong Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I199305430","display_name":"Nantong University","ror":"https://ror.org/02afcvw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I199305430"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinlong Yuan","raw_affiliation_strings":["Department of College of Electrical Engineering, Nantong University, Nantong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of College of Electrical Engineering, Nantong University, Nantong, China","institution_ids":["https://openalex.org/I199305430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078273675","display_name":"Liang Hua","orcid":"https://orcid.org/0000-0002-7739-3733"},"institutions":[{"id":"https://openalex.org/I199305430","display_name":"Nantong University","ror":"https://ror.org/02afcvw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I199305430"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Hua","raw_affiliation_strings":["Department of College of Electrical Engineering, Nantong University, Nantong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of College of Electrical Engineering, Nantong University, Nantong, China","institution_ids":["https://openalex.org/I199305430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087680636","display_name":"Yun Cheng","orcid":"https://orcid.org/0000-0002-0421-1716"},"institutions":[{"id":"https://openalex.org/I199305430","display_name":"Nantong University","ror":"https://ror.org/02afcvw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I199305430"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Cheng","raw_affiliation_strings":["Department of College of Electrical Engineering, Nantong University, Nantong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of College of Electrical Engineering, Nantong University, Nantong, China","institution_ids":["https://openalex.org/I199305430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100782051","display_name":"Junhong Li","orcid":"https://orcid.org/0000-0002-4864-0897"},"institutions":[{"id":"https://openalex.org/I199305430","display_name":"Nantong University","ror":"https://ror.org/02afcvw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I199305430"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junhong Li","raw_affiliation_strings":["Department of College of Electrical Engineering, Nantong University, Nantong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of College of Electrical Engineering, Nantong University, Nantong, China","institution_ids":["https://openalex.org/I199305430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111100415","display_name":"Xiaohu Sang","orcid":null},"institutions":[{"id":"https://openalex.org/I199305430","display_name":"Nantong University","ror":"https://ror.org/02afcvw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I199305430"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohu Sang","raw_affiliation_strings":["Department of College of Electrical Engineering, Nantong University, Nantong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of College of Electrical Engineering, Nantong University, Nantong, China","institution_ids":["https://openalex.org/I199305430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434028","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0003-2343-084X"},"institutions":[{"id":"https://openalex.org/I199305430","display_name":"Nantong University","ror":"https://ror.org/02afcvw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I199305430"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["Department of College of Electrical Engineering, Nantong University, Nantong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of College of Electrical Engineering, Nantong University, Nantong, China","institution_ids":["https://openalex.org/I199305430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015297129","display_name":"Wei Wu","orcid":"https://orcid.org/0000-0002-8734-1582"},"institutions":[{"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":"Wu Wei","raw_affiliation_strings":["Department of College of Automation Science and Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of College of Automation Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5015297129"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":0.1388,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53270822,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"44","issue":"2","first_page":"3233","last_page":"3243"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9828000068664551,"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":0.9828000068664551,"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/T11674","display_name":"Sports Analytics and Performance","score":0.9301999807357788,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.933914303779602},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7731338739395142},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.49042388796806335},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4899665415287018},{"id":"https://openalex.org/keywords/treasure","display_name":"Treasure","score":0.4859684705734253},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.44195878505706787},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.43537843227386475},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4190469980239868},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3322480022907257},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13976743817329407}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.933914303779602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7731338739395142},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.49042388796806335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4899665415287018},{"id":"https://openalex.org/C2776084483","wikidata":"https://www.wikidata.org/wiki/Q272937","display_name":"Treasure","level":2,"score":0.4859684705734253},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44195878505706787},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.43537843227386475},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4190469980239868},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3322480022907257},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13976743817329407},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/jifs-210956","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-210956","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent & Fuzzy Systems","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":11,"referenced_works":["https://openalex.org/W2076063813","https://openalex.org/W2124175081","https://openalex.org/W2132411323","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2912748933","https://openalex.org/W2919115771","https://openalex.org/W3035894110","https://openalex.org/W3111064853","https://openalex.org/W3128086886","https://openalex.org/W6678114464"],"related_works":["https://openalex.org/W2923653485","https://openalex.org/W2957776456","https://openalex.org/W4319773215","https://openalex.org/W4224287422","https://openalex.org/W4361026739","https://openalex.org/W2952472710","https://openalex.org/W4255994452","https://openalex.org/W4206669594","https://openalex.org/W4319083788","https://openalex.org/W3022038857"],"abstract_inverted_index":{"Reward":[0],"signal":[1],"reinforcement":[2,46,59,123],"learning":[3,11,47,60,124],"algorithms":[4],"can":[5,108],"be":[6],"used":[7],"to":[8],"solve":[9,33],"sequential":[10],"problems.":[12],"However,":[13],"in":[14,29,38],"practice,":[15],"they":[16],"still":[17],"suffer":[18],"from":[19],"the":[20,50,62,72,79,82,87,90,105,110,119],"problem":[21],"of":[22,74,81,89,113,121],"reward":[23,36],"imbalance,":[24],"which":[25],"limits":[26],"their":[27],"use":[28],"many":[30],"contexts.":[31],"To":[32],"this":[34,39],"unbalanced":[35,114],"problem,":[37],"paper,":[40],"we":[41],"propose":[42],"a":[43,66,94,98],"novel":[44],"model-based":[45,58],"algorithm":[48,92,107],"called":[49],"expected":[51],"n-step":[52],"value":[53],"iteration":[54],"(EnVI).":[55],"Unlike":[56],"traditional":[57,122],"algorithms,":[61],"proposed":[63,91,106],"method":[64],"uses":[65],"new":[67],"return":[68],"function":[69],"that":[70,104],"changes":[71],"discount":[73],"future":[75],"rewards":[76,115],"while":[77],"reducing":[78],"influence":[80],"current":[83],"reward.":[84],"We":[85],"evaluated":[86],"performance":[88,120],"on":[93],"Treasure-Hunting":[95],"game":[96],"and":[97,116],"Hill-Walking":[99],"game.":[100],"The":[101],"results":[102],"demonstrate":[103],"reduce":[109],"negative":[111],"impact":[112],"greatly":[117],"improve":[118],"algorithms.":[125]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-23T06:36:01.041984","created_date":"2025-10-10T00:00:00"}