{"id":"https://openalex.org/W4383108206","doi":"https://doi.org/10.1109/icra48891.2023.10160753","title":"Security-Aware Reinforcement Learning under Linear Temporal Logic Specifications","display_name":"Security-Aware Reinforcement Learning under Linear Temporal Logic Specifications","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383108206","doi":"https://doi.org/10.1109/icra48891.2023.10160753"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160753","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","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/A5068652180","display_name":"Bohan Cui","orcid":"https://orcid.org/0009-0003-8637-8548"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bohan Cui","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Automation,Shanghai,China,200240","Ministry of Education of China, Key Laboratory of System Control and Information Processing, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Automation,Shanghai,China,200240","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Ministry of Education of China, Key Laboratory of System Control and Information Processing, Shanghai, China","institution_ids":["https://openalex.org/I1327237609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102507939","display_name":"Keyi Zhu","orcid":"https://orcid.org/0000-0002-1002-1863"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keyi Zhu","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Automation,Shanghai,China,200240","Ministry of Education of China, Key Laboratory of System Control and Information Processing, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Automation,Shanghai,China,200240","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Ministry of Education of China, Key Laboratory of System Control and Information Processing, Shanghai, China","institution_ids":["https://openalex.org/I1327237609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041126305","display_name":"Shaoyuan Li","orcid":"https://orcid.org/0000-0003-3427-2912"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoyuan Li","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Automation,Shanghai,China,200240","Ministry of Education of China, Key Laboratory of System Control and Information Processing, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Automation,Shanghai,China,200240","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Ministry of Education of China, Key Laboratory of System Control and Information Processing, Shanghai, China","institution_ids":["https://openalex.org/I1327237609"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034304769","display_name":"Xiang Yin","orcid":"https://orcid.org/0000-0003-1944-1570"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Yin","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Automation,Shanghai,China,200240","Ministry of Education of China, Key Laboratory of System Control and Information Processing, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Automation,Shanghai,China,200240","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Ministry of Education of China, Key Laboratory of System Control and Information Processing, Shanghai, China","institution_ids":["https://openalex.org/I1327237609"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5068652180"],"corresponding_institution_ids":["https://openalex.org/I1327237609","https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.4142,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.84005431,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"12367","last_page":"12373"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.9905999898910522,"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":0.8372212648391724},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7259746789932251},{"id":"https://openalex.org/keywords/linear-temporal-logic","display_name":"Linear temporal logic","score":0.7049418687820435},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6849396228790283},{"id":"https://openalex.org/keywords/observer","display_name":"Observer (physics)","score":0.5341699719429016},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4860987663269043},{"id":"https://openalex.org/keywords/temporal-logic","display_name":"Temporal logic","score":0.48392897844314575},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.47136202454566956},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4512922763824463},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.42468178272247314},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4152737259864807},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.4112371802330017},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3931868076324463},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.35715097188949585},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2955798804759979},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17528480291366577},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16165894269943237},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08755072951316833}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8372212648391724},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7259746789932251},{"id":"https://openalex.org/C4777664","wikidata":"https://www.wikidata.org/wiki/Q1536492","display_name":"Linear temporal logic","level":2,"score":0.7049418687820435},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6849396228790283},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.5341699719429016},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4860987663269043},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.48392897844314575},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.47136202454566956},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4512922763824463},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.42468178272247314},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4152737259864807},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4112371802330017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3931868076324463},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.35715097188949585},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2955798804759979},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17528480291366577},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16165894269943237},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08755072951316833},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10160753","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G182815336","display_name":null,"funder_award_id":"2018AAA0101700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G4151334307","display_name":null,"funder_award_id":"62061136004,62173226,61803259","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1498432697","https://openalex.org/W2004398490","https://openalex.org/W2059470663","https://openalex.org/W2061598829","https://openalex.org/W2064886960","https://openalex.org/W2086081604","https://openalex.org/W2090930915","https://openalex.org/W2497816991","https://openalex.org/W2768035641","https://openalex.org/W2895196950","https://openalex.org/W2948652605","https://openalex.org/W2963575966","https://openalex.org/W2963604565","https://openalex.org/W2966735560","https://openalex.org/W2967236043","https://openalex.org/W3026873144","https://openalex.org/W3046090096","https://openalex.org/W3089490871","https://openalex.org/W3090827750","https://openalex.org/W3119785025","https://openalex.org/W3195968524","https://openalex.org/W4210609986","https://openalex.org/W4214717370","https://openalex.org/W4221021751","https://openalex.org/W4221161625","https://openalex.org/W6763565325","https://openalex.org/W6766521978"],"related_works":["https://openalex.org/W2124110813","https://openalex.org/W3021103820","https://openalex.org/W2763487042","https://openalex.org/W2031188261","https://openalex.org/W4232446061","https://openalex.org/W4285022830","https://openalex.org/W2020883449","https://openalex.org/W3035590440","https://openalex.org/W3205267199","https://openalex.org/W1996820391"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,108],"investigate":[4],"the":[5,34,39,48,51,57,65,73,91,99,103,114,118,125],"problem":[6,100],"of":[7,38,50,56,101,132],"reinforcement":[8,106],"learning":[9],"under":[10],"linear":[11],"temporal":[12],"logic":[13],"(LTL)":[14],"specifications":[15],"for":[16,70,105],"Markov":[17],"decision":[18],"processes":[19],"(MDPs)":[20],"with":[21],"security":[22,61],"constraints.":[23],"We":[24,45,123],"consider":[25],"an":[26,42,110],"outside":[27],"passive":[28],"intruder":[29],"(observer)":[30],"that":[31,47,64,72,89],"can":[32,67],"observe":[33],"external":[35],"output":[36,43],"behavior":[37],"system":[40,52],"through":[41],"projection.":[44],"assume":[46],"secret":[49,79],"is":[53,83],"a":[54,78,86,129],"subset":[55],"initial":[58],"states.":[59],"The":[60],"constraint":[62],"requires":[63],"observer":[66],"never":[68],"infer":[69],"sure":[71],"agent":[74],"was":[75],"initiated":[76],"from":[77],"state.":[80],"Our":[81],"objective":[82],"to":[84],"learn":[85],"control":[87],"policy":[88],"achieves":[90],"LTL":[92],"task":[93],"while":[94],"ensuring":[95],"security.":[96],"To":[97],"solve":[98],"shaping":[102],"reward":[104],"learning,":[107],"propose":[109],"approach":[111,127],"based":[112],"on":[113],"initial-state":[115],"estimator":[116],"and":[117],"limit":[119],"deterministic":[120],"B\u00fcchi":[121],"automata.":[122],"illustrate":[124],"proposed":[126],"by":[128],"case":[130],"study":[131],"mobile":[133],"robot":[134],"example.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
