{"id":"https://openalex.org/W2939467494","doi":"https://doi.org/10.1109/icassp.2019.8682983","title":"Reinforcement Learning with Safe Exploration for Network Security","display_name":"Reinforcement Learning with Safe Exploration for Network Security","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2939467494","doi":"https://doi.org/10.1109/icassp.2019.8682983","mag":"2939467494"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5051449524","display_name":"Canhuang Dai","orcid":null},"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":"Canhuang Dai","raw_affiliation_strings":["Dept. Communication Engineering, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. 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":["Dept. Communication Engineering, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. Communication Engineering, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102759541","display_name":"Xiaoyue Wan","orcid":"https://orcid.org/0000-0003-4808-7443"},"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":"Xiaoyue Wan","raw_affiliation_strings":["Dept. Communication Engineering, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. Communication Engineering, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100359135","display_name":"Ye Chen","orcid":"https://orcid.org/0000-0003-3383-9390"},"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":"Ye Chen","raw_affiliation_strings":["Dept. Communication Engineering, Xiamen University, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. Communication Engineering, Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3489,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.80799974,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3057","last_page":"3061"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10917","display_name":"Smart Grid Security and Resilience","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10917","display_name":"Smart Grid Security and Resilience","score":0.9993000030517578,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980999827384949,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9933000206947327,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8861697912216187},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7488456964492798},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5510787963867188},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4528369605541229},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.44178518652915955},{"id":"https://openalex.org/keywords/jamming","display_name":"Jamming","score":0.4322878420352936},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41805756092071533},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.415860652923584},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.3579862713813782}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8861697912216187},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7488456964492798},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5510787963867188},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4528369605541229},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.44178518652915955},{"id":"https://openalex.org/C2779079576","wikidata":"https://www.wikidata.org/wiki/Q17092823","display_name":"Jamming","level":2,"score":0.4322878420352936},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41805756092071533},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.415860652923584},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3579862713813782},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682983","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6000000238418579,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2101018825","https://openalex.org/W2145339207","https://openalex.org/W2151237105","https://openalex.org/W2166798247","https://openalex.org/W2324627801","https://openalex.org/W2427917354","https://openalex.org/W2605369401","https://openalex.org/W2611484353","https://openalex.org/W2618318883","https://openalex.org/W2782363571","https://openalex.org/W2805862167","https://openalex.org/W2962858248","https://openalex.org/W2963468788","https://openalex.org/W2963958573","https://openalex.org/W4294555834","https://openalex.org/W4297780563","https://openalex.org/W4298174377","https://openalex.org/W6682367392","https://openalex.org/W6684359289","https://openalex.org/W6685726866","https://openalex.org/W6717915398","https://openalex.org/W6736521721","https://openalex.org/W6737523040","https://openalex.org/W6738483526","https://openalex.org/W6750234710","https://openalex.org/W6751934456"],"related_works":["https://openalex.org/W4200319726","https://openalex.org/W2378211422","https://openalex.org/W1984793747","https://openalex.org/W4312547492","https://openalex.org/W3197729047","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W1624160917","https://openalex.org/W1987034598","https://openalex.org/W2130974462"],"abstract_inverted_index":{"Safe":[0],"reinforcement":[1,41,75,112],"learning":[2,42,50,76,100,104,113],"is":[3,59,117],"important":[4],"for":[5,102],"the":[6,14,53,63,85,92,95,99,103,110,120,128,133,137,141,146,152],"safety":[7,70,93],"critical":[8],"applications":[9],"especially":[10],"network":[11,28,82],"security,":[12],"as":[13,27,68],"exploration":[15,46,96,116],"of":[16,94,136],"some":[17],"dangerous":[18,65,148],"actions":[19],"can":[20,131],"result":[21],"in":[22,119],"huge":[23],"short-term":[24],"losses":[25],"such":[26],"failure":[29],"or":[30],"large":[31],"scale":[32],"privacy":[33],"leakage.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38],"propose":[39],"a":[40,69,79,107],"algorithm":[43],"with":[44,114,151],"safe":[45,73,115],"and":[47,88,97,139],"uses":[48,78],"transfer":[49],"to":[51,61,83,144],"reduce":[52,140],"initial":[54],"random":[55],"exploration.":[56],"A":[57,72],"blacklist":[58],"maintained":[60],"record":[62],"most":[64,147],"state-action":[66],"pairs":[67],"constraint.":[71],"deep":[74],"version":[77],"convolutional":[80],"neural":[81],"estimate":[84],"risk":[86],"levels":[87],"thus":[89],"further":[90],"improves":[91],"accelerates":[98],"speed":[101],"agent.":[105],"As":[106],"case":[108],"study,":[109],"proposed":[111,129],"applied":[118],"anti-jamming":[121],"robot":[122,138],"communications.":[123],"Experimental":[124],"results":[125],"show":[126],"that":[127],"algorithms":[130],"improve":[132],"jamming":[134],"resistance":[135],"outage":[142],"rate":[143],"enter":[145],"states":[149],"compared":[150],"benchmark":[153],"algorithms.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}