{"id":"https://openalex.org/W4408202027","doi":"https://doi.org/10.1631/fitee.2400406","title":"Significance extraction based on data augmentation for reinforcement learning","display_name":"Significance extraction based on data augmentation for reinforcement learning","publication_year":2025,"publication_date":"2025-03-01","ids":{"openalex":"https://openalex.org/W4408202027","doi":"https://doi.org/10.1631/fitee.2400406"},"language":"en","primary_location":{"id":"doi:10.1631/fitee.2400406","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.2400406","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"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":"Frontiers of Information Technology & Electronic Engineering","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/A5050122489","display_name":"Yuxi Han","orcid":null},"institutions":[{"id":"https://openalex.org/I184681353","display_name":"Anhui University of Science and Technology","ror":"https://ror.org/00q9atg80","country_code":"CN","type":"education","lineage":["https://openalex.org/I184681353"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuxi Han","raw_affiliation_strings":["Faculty of Artificial Intelligence, Anhui University of Science and Technology, Huainan, 232000, China","Faculty of Artificial Intelligence, Anhui University of Science and Technology, Huainan, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Artificial Intelligence, Anhui University of Science and Technology, Huainan, 232000, China","institution_ids":["https://openalex.org/I184681353"]},{"raw_affiliation_string":"Faculty of Artificial Intelligence, Anhui University of Science and Technology, Huainan, China","institution_ids":["https://openalex.org/I184681353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070758349","display_name":"Dequan Li","orcid":"https://orcid.org/0000-0002-4329-864X"},"institutions":[{"id":"https://openalex.org/I184681353","display_name":"Anhui University of Science and Technology","ror":"https://ror.org/00q9atg80","country_code":"CN","type":"education","lineage":["https://openalex.org/I184681353"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dequan Li","raw_affiliation_strings":["Faculty of Artificial Intelligence, Anhui University of Science and Technology, Huainan, 232000, China","Faculty of Artificial Intelligence, Anhui University of Science and Technology, Huainan, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Artificial Intelligence, Anhui University of Science and Technology, Huainan, 232000, China","institution_ids":["https://openalex.org/I184681353"]},{"raw_affiliation_string":"Faculty of Artificial Intelligence, Anhui University of Science and Technology, Huainan, China","institution_ids":["https://openalex.org/I184681353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100397566","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-3510-6943"},"institutions":[{"id":"https://openalex.org/I184681353","display_name":"Anhui University of Science and Technology","ror":"https://ror.org/00q9atg80","country_code":"CN","type":"education","lineage":["https://openalex.org/I184681353"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["Faculty of Artificial Intelligence, Anhui University of Science and Technology, Huainan, 232000, China","Faculty of Artificial Intelligence, Anhui University of Science and Technology, Huainan, China"],"affiliations":[{"raw_affiliation_string":"Faculty of Artificial Intelligence, Anhui University of Science and Technology, Huainan, 232000, China","institution_ids":["https://openalex.org/I184681353"]},{"raw_affiliation_string":"Faculty of Artificial Intelligence, Anhui University of Science and Technology, Huainan, China","institution_ids":["https://openalex.org/I184681353"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050122489"],"corresponding_institution_ids":["https://openalex.org/I184681353"],"apc_list":null,"apc_paid":null,"fwci":2.4849,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.88531043,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"26","issue":"3","first_page":"385","last_page":"399"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9901999831199646,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.982699990272522,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6436817646026611},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.542321503162384},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5333628058433533},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.5283385515213013},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5103775858879089},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.436749666929245},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35771870613098145},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3049970269203186},{"id":"https://openalex.org/keywords/medline","display_name":"MEDLINE","score":0.09714585542678833},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.09621307253837585},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.08910787105560303},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.07879096269607544}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6436817646026611},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.542321503162384},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5333628058433533},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.5283385515213013},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5103775858879089},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.436749666929245},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35771870613098145},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3049970269203186},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.09714585542678833},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.09621307253837585},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.08910787105560303},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.07879096269607544},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1631/fitee.2400406","is_oa":false,"landing_page_url":"https://doi.org/10.1631/fitee.2400406","pdf_url":null,"source":{"id":"https://openalex.org/S4210189857","display_name":"Frontiers of Information Technology & Electronic Engineering","issn_l":"2095-9184","issn":["2095-9184","2095-9230"],"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":"Frontiers of Information Technology & Electronic Engineering","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":43,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2168359464","https://openalex.org/W2605102758","https://openalex.org/W2754517384","https://openalex.org/W2781585732","https://openalex.org/W2808849637","https://openalex.org/W2809668646","https://openalex.org/W2893662673","https://openalex.org/W2962887844","https://openalex.org/W2964198579","https://openalex.org/W2981030070","https://openalex.org/W3015437096","https://openalex.org/W3100789280","https://openalex.org/W3119908121","https://openalex.org/W3173518742","https://openalex.org/W3175182975","https://openalex.org/W3175558129","https://openalex.org/W3176485999","https://openalex.org/W3205321526","https://openalex.org/W3206739224","https://openalex.org/W4206513913","https://openalex.org/W4214717370","https://openalex.org/W4287309212","https://openalex.org/W4298857966","https://openalex.org/W4315487473","https://openalex.org/W4328007461","https://openalex.org/W4372279940","https://openalex.org/W4383176672","https://openalex.org/W4394906505","https://openalex.org/W4399115118","https://openalex.org/W6600127060","https://openalex.org/W6600281463","https://openalex.org/W6600302053","https://openalex.org/W6600874529","https://openalex.org/W6600985031","https://openalex.org/W6601630192","https://openalex.org/W6601926947","https://openalex.org/W6602215214","https://openalex.org/W6603732165","https://openalex.org/W6604268844","https://openalex.org/W6606494994","https://openalex.org/W6606882031","https://openalex.org/W6824051750"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1,163],"learning":[2,164],"has":[3],"shown":[4],"remarkable":[5],"capabilities":[6],"in":[7,19,25,40,55,166,173],"visual":[8],"tasks,":[9],"but":[10],"it":[11],"does":[12],"not":[13],"have":[14],"a":[15,41,72],"good":[16],"generalization":[17,139,172],"ability":[18],"the":[20,26,61,83,111,120,136,143],"context":[21],"of":[22,63,168],"interference":[23],"signals":[24,51],"input":[27],"images;":[28],"this":[29],"approach":[30],"is":[31,159],"therefore":[32],"hard":[33],"to":[34,37,47,85,118,122,161],"be":[35],"applied":[36],"trained":[38],"agents":[39,46],"new":[42],"environment.":[43],"To":[44],"enable":[45],"distinguish":[48],"between":[49],"noise":[50],"and":[52,60,91,104,108,127,142,154,171],"important":[53,96,125],"pixels":[54],"images,":[56],"data":[57],"augmentation":[58,79],"techniques":[59],"establishment":[62],"auxiliary":[64],"networks":[65],"are":[66],"proven":[67],"effective":[68],"solutions.":[69],"We":[70,131],"introduce":[71],"novel":[73],"algorithm,":[74],"namely,":[75],"saliency-extracted":[76],"Q-value":[77],"by":[78],"(SEQA),":[80],"which":[81],"encourages":[82],"agent":[84,121],"explore":[86],"unknown":[87],"states":[88],"more":[89],"comprehensively":[90],"focus":[92,123],"its":[93],"attention":[94],"on":[95,124,135],"information.":[97],"Specifically,":[98],"SEQA":[99],"masks":[100],"out":[101],"interfering":[102],"features":[103,107,126],"extracts":[105],"salient":[106],"then":[109],"updates":[110],"mask":[112],"decoder":[113],"network":[114],"with":[115],"critic":[116],"losses":[117],"encourage":[119],"make":[128],"correct":[129],"decisions.":[130],"evaluate":[132],"our":[133,148,157],"algorithm":[134,149,158],"DeepMind":[137],"Control":[138],"benchmark":[140],"(DMControl-GB),":[141],"experimental":[144],"results":[145],"show":[146],"that":[147],"greatly":[150],"improves":[151],"training":[152],"efficiency":[153,170],"stability.":[155],"Meanwhile,":[156],"superior":[160],"state-of-the-art":[162],"methods":[165],"terms":[167],"sample":[169],"most":[174],"DMControl-GB":[175],"tasks.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}