{"id":"https://openalex.org/W7128500771","doi":"https://doi.org/10.1109/mic.2026.3662365","title":"Balancing Safety and Learning in the Internet of Things: A Risk-Aware Reinforcement Learning Approach","display_name":"Balancing Safety and Learning in the Internet of Things: A Risk-Aware Reinforcement Learning Approach","publication_year":2026,"publication_date":"2026-02-10","ids":{"openalex":"https://openalex.org/W7128500771","doi":"https://doi.org/10.1109/mic.2026.3662365"},"language":null,"primary_location":{"id":"doi:10.1109/mic.2026.3662365","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mic.2026.3662365","pdf_url":null,"source":{"id":"https://openalex.org/S205899252","display_name":"IEEE Internet Computing","issn_l":"1089-7801","issn":["1089-7801","1941-0131"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Internet Computing","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/A5053374035","display_name":"Congwei Zhang","orcid":"https://orcid.org/0000-0002-5317-9599"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Congwei Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0002-5317-9599","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024560479","display_name":"Guangpeng Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangpeng Qi","raw_affiliation_strings":["Inspur Yunzhou Industrial Internet Co., Ltd., Jinan, China"],"raw_orcid":"https://orcid.org/0009-0006-4733-8975","affiliations":[{"raw_affiliation_string":"Inspur Yunzhou Industrial Internet Co., Ltd., Jinan, China","institution_ids":["https://openalex.org/I4210144143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040831375","display_name":"Zhen Ma","orcid":"https://orcid.org/0009-0004-8732-8988"},"institutions":[{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Ma","raw_affiliation_strings":["Inspur Yunzhou Industrial Internet Co., Ltd., Jinan, China"],"raw_orcid":"https://orcid.org/0009-0006-9414-5586","affiliations":[{"raw_affiliation_string":"Inspur Yunzhou Industrial Internet Co., Ltd., Jinan, China","institution_ids":["https://openalex.org/I4210144143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125563129","display_name":"Long Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Ma","raw_affiliation_strings":["Inspur Yunzhou Industrial Internet Co., Ltd., Jinan, China"],"raw_orcid":"https://orcid.org/0009-0001-1078-7324","affiliations":[{"raw_affiliation_string":"Inspur Yunzhou Industrial Internet Co., Ltd., Jinan, China","institution_ids":["https://openalex.org/I4210144143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085325753","display_name":"Xuejian Chi","orcid":"https://orcid.org/0000-0001-6635-0482"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuejian Chi","raw_affiliation_strings":["School of Computer Science and Technology, Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0001-6635-0482","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073149771","display_name":"Huiqun Li","orcid":null},"institutions":[{"id":"https://openalex.org/I108688024","display_name":"Qingdao University","ror":"https://ror.org/021cj6z65","country_code":"CN","type":"education","lineage":["https://openalex.org/I108688024"]},{"id":"https://openalex.org/I146773158","display_name":"Qingdao Agricultural University","ror":"https://ror.org/051qwcj72","country_code":"CN","type":"education","lineage":["https://openalex.org/I146773158"]},{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huiqun Li","raw_affiliation_strings":["School of Mathematics, Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0009-0009-5714-464X","affiliations":[{"raw_affiliation_string":"School of Mathematics, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I108688024","https://openalex.org/I146773158","https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125513351","display_name":"Dongxiao Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongxiao Yu","raw_affiliation_strings":["School of Computer Science and Technology, Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0001-6835-5981","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125501716","display_name":"Xiuzhen Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiuzhen Cheng","raw_affiliation_strings":["School of Computer Science and Technology, Shandong University, Qingdao, China"],"raw_orcid":"https://orcid.org/0000-0001-5912-4647","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I80143920"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11996174,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":"2","first_page":"56","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.2386000007390976,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.2386000007390976,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.10189999639987946,"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/T10714","display_name":"Software-Defined Networks and 5G","score":0.07440000027418137,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8400999903678894},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6377000212669373},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5379999876022339},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.4120999872684479},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4090999960899353},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.40149998664855957},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.39739999175071716},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.37860000133514404}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8400999903678894},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7997000217437744},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6377000212669373},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5379999876022339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47600001096725464},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44179999828338623},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.4120999872684479},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4090999960899353},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.40149998664855957},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.39739999175071716},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3675000071525574},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.26989999413490295},{"id":"https://openalex.org/C81860439","wikidata":"https://www.wikidata.org/wiki/Q251212","display_name":"Internet of Things","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C52970973","wikidata":"https://www.wikidata.org/wiki/Q2497134","display_name":"Adaptive system","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mic.2026.3662365","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mic.2026.3662365","pdf_url":null,"source":{"id":"https://openalex.org/S205899252","display_name":"IEEE Internet Computing","issn_l":"1089-7801","issn":["1089-7801","1941-0131"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Internet Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6279090046882629}],"awards":[{"id":"https://openalex.org/G4323041288","display_name":null,"funder_award_id":"U23A20302","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7759355382","display_name":null,"funder_award_id":"62572280","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8517415502","display_name":null,"funder_award_id":"U24A20244","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"enables":[3],"Internet":[4],"of":[5],"Things":[6],"(IoT)":[7],"systems":[8],"to":[9,11,67,83],"adapt":[10],"dynamic":[12],"environments,":[13],"but":[14,33],"ensuring":[15],"safety":[16,28],"during":[17],"learning":[18,24,35,57],"is":[19],"challenging.":[20],"Fallback-based":[21],"safe":[22,46],"reinforcement":[23],"(SafeRL)":[25],"methods":[26],"guarantee":[27],"by":[29,107,111,117,125],"overriding":[30],"unsafe":[31],"actions,":[32],"hinder":[34],"in":[36,132],"high-risk":[37,70],"yet":[38],"informative":[39],"states":[40],"and":[41,72,87,121,130],"may":[42],"disrupt":[43],"previously":[44,95],"learned":[45],"behaviors.":[47],"We":[48],"propose":[49],"RA-SafeRL,":[50],"a":[51,63],"Risk-Aware":[52],"SafeRL":[53,106],"framework":[54],"that":[55],"improves":[56],"without":[58],"compromising":[59],"safety.":[60],"RA-SafeRL":[61,103],"uses":[62],"digital":[64],"twin":[65],"environment":[66],"safely":[68],"explore":[69],"actions":[71],"learn":[73],"from":[74],"them,":[75],"applies":[76],"adaptive":[77],"fallback":[78,89,115],"penalties":[79],"reflecting":[80],"action":[81],"severity":[82],"distinguish":[84],"risk":[85],"levels,":[86],"reuses":[88],"trajectories":[90],"via":[91],"off-policy":[92],"learning,":[93],"converting":[94],"discarded":[96],"data":[97],"into":[98],"useful":[99],"signals.":[100],"Experiments":[101],"show":[102],"outperforms":[104],"baseline":[105],"improving":[108],"task":[109],"performance":[110],"over":[112],"30%,":[113],"reducing":[114],"frequency":[116],"more":[118],"than":[119],"10%,":[120],"shortening":[122],"recovery":[123],"time":[124],"38%,":[126],"enhancing":[127],"safety,":[128],"efficiency,":[129],"robustness":[131],"safety-critical":[133],"IoT":[134],"applications.":[135]},"counts_by_year":[],"updated_date":"2026-05-26T06:15:08.310788","created_date":"2026-02-11T00:00:00"}