{"id":"https://openalex.org/W4390724044","doi":"https://doi.org/10.1109/access.2024.3351696","title":"An Improved Reinforcement Learning Method Based on Unsupervised Learning","display_name":"An Improved Reinforcement Learning Method Based on Unsupervised Learning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4390724044","doi":"https://doi.org/10.1109/access.2024.3351696"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3351696","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3351696","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10385075.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10385075.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074453296","display_name":"Xin Chang","orcid":"https://orcid.org/0000-0002-4505-522X"},"institutions":[{"id":"https://openalex.org/I2800372957","display_name":"China Electronics Technology Group Corporation","ror":"https://ror.org/0098hst83","country_code":"CN","type":"company","lineage":["https://openalex.org/I2800372957"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xin Chang","raw_affiliation_strings":["The 54th Research Institute of China Electronics Technology Group Corporation (CETC54), Shijiazhuang, China"],"affiliations":[{"raw_affiliation_string":"The 54th Research Institute of China Electronics Technology Group Corporation (CETC54), Shijiazhuang, China","institution_ids":["https://openalex.org/I2800372957"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100771495","display_name":"Yanbin Li","orcid":"https://orcid.org/0000-0001-7151-9270"},"institutions":[{"id":"https://openalex.org/I2800372957","display_name":"China Electronics Technology Group Corporation","ror":"https://ror.org/0098hst83","country_code":"CN","type":"company","lineage":["https://openalex.org/I2800372957"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanbin Li","raw_affiliation_strings":["The 54th Research Institute of China Electronics Technology Group Corporation (CETC54), Shijiazhuang, China"],"affiliations":[{"raw_affiliation_string":"The 54th Research Institute of China Electronics Technology Group Corporation (CETC54), Shijiazhuang, China","institution_ids":["https://openalex.org/I2800372957"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069045557","display_name":"Guanjie Zhang","orcid":"https://orcid.org/0000-0001-6149-6490"},"institutions":[{"id":"https://openalex.org/I2800372957","display_name":"China Electronics Technology Group Corporation","ror":"https://ror.org/0098hst83","country_code":"CN","type":"company","lineage":["https://openalex.org/I2800372957"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanjie Zhang","raw_affiliation_strings":["The 54th Research Institute of China Electronics Technology Group Corporation (CETC54), Shijiazhuang, China"],"affiliations":[{"raw_affiliation_string":"The 54th Research Institute of China Electronics Technology Group Corporation (CETC54), Shijiazhuang, China","institution_ids":["https://openalex.org/I2800372957"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100599982","display_name":"Donghui Liu","orcid":"https://orcid.org/0009-0003-3387-0774"},"institutions":[{"id":"https://openalex.org/I90090648","display_name":"Shijiazhuang Tiedao University","ror":"https://ror.org/022e9e065","country_code":"CN","type":"education","lineage":["https://openalex.org/I90090648"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Donghui Liu","raw_affiliation_strings":["School of Management, Shijiazhuang Tiedao University, Shijiazhuang, China"],"affiliations":[{"raw_affiliation_string":"School of Management, Shijiazhuang Tiedao University, Shijiazhuang, China","institution_ids":["https://openalex.org/I90090648"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091095275","display_name":"Changjun Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I2800372957","display_name":"China Electronics Technology Group Corporation","ror":"https://ror.org/0098hst83","country_code":"CN","type":"company","lineage":["https://openalex.org/I2800372957"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changjun Fu","raw_affiliation_strings":["The 54th Research Institute of China Electronics Technology Group Corporation (CETC54), Shijiazhuang, China"],"affiliations":[{"raw_affiliation_string":"The 54th Research Institute of China Electronics Technology Group Corporation (CETC54), Shijiazhuang, China","institution_ids":["https://openalex.org/I2800372957"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5074453296"],"corresponding_institution_ids":["https://openalex.org/I2800372957"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.044,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.87639663,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"12","issue":null,"first_page":"12295","last_page":"12307"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9894999861717224,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9868000149726868,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8759869933128357},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7544031143188477},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7516942620277405},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.7016146183013916},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.6178828477859497},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6023619771003723},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5383924245834351},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5366672277450562},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5185676217079163},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.51609867811203},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.430184543132782},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.415600061416626},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36591506004333496},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11654642224311829}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8759869933128357},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7544031143188477},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7516942620277405},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.7016146183013916},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.6178828477859497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6023619771003723},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5383924245834351},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5366672277450562},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5185676217079163},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.51609867811203},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.430184543132782},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.415600061416626},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36591506004333496},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11654642224311829},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3351696","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3351696","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10385075.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a9088de74fe742018906b15da9ec3d83","is_oa":true,"landing_page_url":"https://doaj.org/article/a9088de74fe742018906b15da9ec3d83","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 12, Pp 12295-12307 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3351696","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3351696","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10385075.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4000000059604645,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G2104653401","display_name":null,"funder_award_id":"2021M","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G6362877599","display_name":null,"funder_award_id":"2021M693002","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390724044.pdf","grobid_xml":"https://content.openalex.org/works/W4390724044.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W595252221","https://openalex.org/W2004203064","https://openalex.org/W2096994080","https://openalex.org/W2145339207","https://openalex.org/W2160166502","https://openalex.org/W2226509531","https://openalex.org/W2336650964","https://openalex.org/W2403793778","https://openalex.org/W2509790245","https://openalex.org/W2514890051","https://openalex.org/W2736601468","https://openalex.org/W2765492968","https://openalex.org/W2781726626","https://openalex.org/W2884586244","https://openalex.org/W2891063394","https://openalex.org/W2898754723","https://openalex.org/W2904246096","https://openalex.org/W2949561945","https://openalex.org/W2951799221","https://openalex.org/W2963688947","https://openalex.org/W2963927126","https://openalex.org/W2982316857","https://openalex.org/W2991059173","https://openalex.org/W3011655242","https://openalex.org/W3130385304","https://openalex.org/W3207179386","https://openalex.org/W4214717370","https://openalex.org/W4289761856","https://openalex.org/W4290043195","https://openalex.org/W4298032596","https://openalex.org/W4306316942","https://openalex.org/W4319586228","https://openalex.org/W4321780094","https://openalex.org/W4353056919","https://openalex.org/W4360770829","https://openalex.org/W4394662461","https://openalex.org/W6676179485","https://openalex.org/W6685444567","https://openalex.org/W6703420464","https://openalex.org/W6734517396","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6748108687","https://openalex.org/W6753146606","https://openalex.org/W6757592117","https://openalex.org/W6775180354","https://openalex.org/W6863618527"],"related_works":["https://openalex.org/W1995622179","https://openalex.org/W1484111231","https://openalex.org/W4391160746","https://openalex.org/W1552543208","https://openalex.org/W2074396517","https://openalex.org/W2166963679","https://openalex.org/W2187269125","https://openalex.org/W1641615907","https://openalex.org/W3089231081","https://openalex.org/W2093956241"],"abstract_inverted_index":{"The":[0],"approach":[1],"of":[2,59,73,109,117,196],"directly":[3],"combining":[4],"clustering":[5,64,97],"method":[6,47],"and":[7,92,104,149,194],"reinforcement":[8,45,143],"learning":[9,46,51,144],"(RL)":[10],"will":[11],"lead":[12],"to":[13,67,100,145,200],"encounter":[14],"the":[15,26,70,74,77,84,88,96,110,124,132,138,160,175,197],"issue":[16],"where":[17],"states":[18],"may":[19],"have":[20],"different":[21],"state":[22,130],"transition":[23,116],"processes":[24],"under":[25],"same":[27],"action,":[28],"resulting":[29,133],"in":[30,204],"poor":[31],"policy":[32,202],"performance.":[33,173],"To":[34],"address":[35],"this":[36],"challenge":[37],"with":[38,54,154],"multi-dimensional":[39,81],"continuous":[40],"observation":[41,86,90,111,125],"data,":[42,87],"an":[43],"improved":[44,161,201],"based":[48],"on":[49,165],"unsupervised":[50,63],"is":[52,65],"proposed":[53,78],"a":[55,101,128],"novel":[56],"framework.":[57],"Instead":[58],"dimensionality":[60],"reduction":[61],"methods,":[62],"employed":[66],"indirectly":[68],"capture":[69],"underlying":[71],"structure":[72],"data.":[75],"First,":[76],"framework":[79,166,176],"incorporates":[80],"information,":[82,94],"including":[83],"current":[85],"next":[89],"data":[91,112,126],"reward":[93],"during":[95],"process,":[98],"leading":[99,199],"more":[102,147],"accurate":[103],"comprehensive":[105],"low-dimensional":[106,139],"discrete":[107,140],"representation":[108],"while":[113],"retaining":[114],"preserving":[115],"Markov":[118],"decision":[119],"process.":[120],"Second,":[121],"by":[122,182],"compressing":[123],"into":[127],"well-defined":[129],"space,":[131],"cluster":[134],"labels":[135],"serve":[136],"as":[137,180],"label-states":[141],"for":[142,191],"generate":[146],"effective":[148],"robust":[150],"policies.":[151],"Comparative":[152],"analysis":[153],"state-of-the-art":[155],"RL":[156,162],"methods":[157,163],"demonstrates":[158],"that":[159],"base":[164],"achieves":[167],"higher":[168],"rewards,":[169],"indicating":[170],"its":[171,183],"superior":[172],"Furthermore,":[174],"exhibits":[177],"computational":[178],"efficiency,":[179],"evidenced":[181],"reasonable":[184],"time":[185],"complexity.":[186],"This":[187],"structural":[188],"innovation":[189],"allows":[190],"better":[192],"exploration":[193],"exploitation":[195],"transition,":[198],"performance":[203],"engineering":[205],"applications.":[206]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}