{"id":"https://openalex.org/W4210882709","doi":"https://doi.org/10.1109/tifs.2022.3149396","title":"Safe Exploration in Wireless Security: A Safe Reinforcement Learning Algorithm With Hierarchical Structure","display_name":"Safe Exploration in Wireless Security: A Safe Reinforcement Learning Algorithm With Hierarchical Structure","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4210882709","doi":"https://doi.org/10.1109/tifs.2022.3149396"},"language":"en","primary_location":{"id":"doi:10.1109/tifs.2022.3149396","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2022.3149396","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Information Forensics and Security","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/A5091024726","display_name":"Xiaozhen Lu","orcid":"https://orcid.org/0000-0001-8247-0353"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaozhen Lu","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China","Department of Information and Communication Engineering, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, China","institution_ids":["https://openalex.org/I9842412"]},{"raw_affiliation_string":"Department of Information and Communication Engineering, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068976123","display_name":"Liang Xiao","orcid":"https://orcid.org/0000-0003-2402-611X"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Xiao","raw_affiliation_strings":["Department of Information and Communication Engineering, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Department of Information and Communication Engineering, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003967935","display_name":"Guohang Niu","orcid":"https://orcid.org/0000-0001-9883-9936"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guohang Niu","raw_affiliation_strings":["Department of Information and Communication Engineering, Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Department of Information and Communication Engineering, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024401174","display_name":"Xiangyang Ji","orcid":"https://orcid.org/0000-0002-7333-9975"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyang Ji","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100391116","display_name":"Qian Wang","orcid":"https://orcid.org/0000-0002-8967-8525"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Wang","raw_affiliation_strings":["School of Cyber Science and Engineering, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5091024726"],"corresponding_institution_ids":["https://openalex.org/I191208505","https://openalex.org/I9842412"],"apc_list":null,"apc_paid":null,"fwci":38.8576,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":{"value":0.99723466,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"17","issue":null,"first_page":"732","last_page":"743"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11133","display_name":"UAV Applications and Optimization","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11133","display_name":"UAV Applications and Optimization","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9896000027656555,"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/T10917","display_name":"Smart Grid Security and Resilience","score":0.979200005531311,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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":0.8622171878814697},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8558977246284485},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.643815815448761},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5408957004547119},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5207583904266357},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4924262464046478},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.44607076048851013},{"id":"https://openalex.org/keywords/wireless-network","display_name":"Wireless network","score":0.44109833240509033},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.38120517134666443},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3452067971229553},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12371835112571716}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8622171878814697},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8558977246284485},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.643815815448761},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5408957004547119},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5207583904266357},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4924262464046478},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.44607076048851013},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.44109833240509033},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.38120517134666443},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3452067971229553},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12371835112571716}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tifs.2022.3149396","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2022.3149396","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Information Forensics and Security","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G2404993877","display_name":null,"funder_award_id":"U20B2049","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2874061861","display_name":null,"funder_award_id":"61971366","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7203450436","display_name":null,"funder_award_id":"U21A20444","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7711705859","display_name":null,"funder_award_id":"61822207","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8611733963","display_name":null,"funder_award_id":"2042021gf0006","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W41554520","https://openalex.org/W1592847719","https://openalex.org/W1845972764","https://openalex.org/W1932847118","https://openalex.org/W2121517924","https://openalex.org/W2145339207","https://openalex.org/W2486702221","https://openalex.org/W2776055286","https://openalex.org/W2782363571","https://openalex.org/W2790737916","https://openalex.org/W2891654323","https://openalex.org/W2899071560","https://openalex.org/W2939467494","https://openalex.org/W2949267040","https://openalex.org/W2962792006","https://openalex.org/W2969388461","https://openalex.org/W2978360652","https://openalex.org/W3004819373","https://openalex.org/W3006762012","https://openalex.org/W3040914594","https://openalex.org/W3101813280","https://openalex.org/W3103493968","https://openalex.org/W3127329908","https://openalex.org/W4246078117","https://openalex.org/W6631190155","https://openalex.org/W6684921986","https://openalex.org/W6685726866","https://openalex.org/W6703271639","https://openalex.org/W6734215269","https://openalex.org/W6751725685","https://openalex.org/W6752089545","https://openalex.org/W6752725515","https://openalex.org/W6764346552","https://openalex.org/W6767486501"],"related_works":["https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W3087814763","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W4376605461","https://openalex.org/W4400868993","https://openalex.org/W2361647908","https://openalex.org/W2952356279"],"abstract_inverted_index":{"Most":[0],"safe":[1,46,133,209],"reinforcement":[2],"learning":[3,27,76,80,112,149,153,191],"(RL)":[4],"algorithms":[5,211],"depend":[6],"on":[7,93],"the":[8,26,33,69,79,85,89,99,102,107,148,152,165,173,177,180,190,194,199,215,225,232,244,249,254,258],"accurate":[9],"reward":[10,168,255],"that":[11,29,97,110,155,238],"is":[12],"rarely":[13],"available":[14],"in":[15,120,141,214],"wireless":[16,121],"security":[17,95,118,122],"applications":[18],"and":[19,66,135,176,187,228,252],"suffer":[20],"from":[21,35],"severe":[22,116],"performance":[23],"degradation":[24],"for":[25,151],"agents":[28,154],"have":[30],"to":[31,56,77,145,197,223,231],"choose":[32],"policy":[34,52,59,200],"a":[36,45,51,94,131,204],"large":[37],"action":[38,70],"set.":[39,71],"In":[40],"this":[41,82],"paper,":[42],"we":[43],"propose":[44,130],"RL":[47,134,210],"algorithm,":[48],"which":[49],"uses":[50],"priority-based":[53],"hierarchical":[54],"structure":[55],"divide":[57],"each":[58,142,170],"into":[60],"sub-policies":[61,109],"with":[62,257],"different":[63],"selection":[64,144],"priorities":[65],"thus":[67],"compresses":[68],"By":[72],"applying":[73],"inter-agent":[74],"transfer":[75],"initialize":[78],"parameters,":[81],"algorithm":[83],"accelerates":[84],"initial":[86],"exploration":[87,201],"of":[88,169,193,218],"optimal":[90],"policy.":[91],"Based":[92],"criterion":[96],"evaluates":[98,164,179],"risk":[100,182],"value,":[101],"sub-policy":[103,143,171],"distribution":[104],"formulation":[105],"avoids":[106],"dangerous":[108],"cause":[111],"failure":[113],"such":[114],"as":[115],"network":[117],"problems":[119],"applications,":[123],"e.g.,":[124],"Internet":[125],"services":[126],"interruption.":[127],"We":[128],"also":[129],"deep":[132,138],"design":[136],"four":[137,157],"neural":[139,159],"networks":[140,160],"further":[146],"improve":[147,198,243],"efficiency":[150],"support":[156],"convolutional":[158],"(CNNs):":[161],"The":[162,184],"Q-network":[163],"long-term":[166,181],"expected":[167],"under":[172],"current":[174],"state,":[175],"E-network":[178],"value.":[183],"target":[185],"Q":[186],"E-networks":[188],"update":[189],"parameters":[192],"corresponding":[195],"CNN":[196],"stability.":[202],"As":[203],"case":[205],"study,":[206],"our":[207,239],"proposed":[208,240],"are":[212],"implemented":[213],"anti-jamming":[216],"communication":[217,246],"unmanned":[219],"aerial":[220],"vehicles":[221],"(UAVs)":[222],"select":[224],"frequency":[226],"channel":[227],"transmit":[229],"power":[230],"ground":[233],"node.":[234],"Experimental":[235],"results":[236],"show":[237],"schemes":[241],"significantly":[242],"UAV":[245,250],"performance,":[247],"save":[248],"energy":[251],"increase":[253],"compared":[256],"benchmark":[259],"against":[260],"jamming.":[261]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":6}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}