{"id":"https://openalex.org/W7123347689","doi":"https://doi.org/10.1109/cdc57313.2025.11312251","title":"Synthesis of Joint Current-state Opacity Supervisory Policies by Deep Reinforcement Learning","display_name":"Synthesis of Joint Current-state Opacity Supervisory Policies by Deep Reinforcement Learning","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7123347689","doi":"https://doi.org/10.1109/cdc57313.2025.11312251"},"language":null,"primary_location":{"id":"doi:10.1109/cdc57313.2025.11312251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5030101102","display_name":"Li Huang","orcid":"https://orcid.org/0000-0003-0741-4903"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Huang","raw_affiliation_strings":["Guangxi Normal University,Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education,Guilin,China,541004"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi Normal University,Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education,Guilin,China,541004","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wanling Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanling Huang","raw_affiliation_strings":["Guangxi Normal University,Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education,Guilin,China,541004"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi Normal University,Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education,Guilin,China,541004","institution_ids":["https://openalex.org/I29739308"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100381131","display_name":"Huimin Zhang","orcid":"https://orcid.org/0000-0002-7343-5641"},"institutions":[{"id":"https://openalex.org/I29739308","display_name":"Guangxi Normal University","ror":"https://ror.org/02frt9q65","country_code":"CN","type":"education","lineage":["https://openalex.org/I29739308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huimin Zhang","raw_affiliation_strings":["Guangxi Normal University,Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education,Guilin,China,541004"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangxi Normal University,Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education,Guilin,China,541004","institution_ids":["https://openalex.org/I29739308"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I29739308"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1235","last_page":"1240"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11125","display_name":"Petri Nets in System Modeling","score":0.311599999666214,"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/T11125","display_name":"Petri Nets in System Modeling","score":0.311599999666214,"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/T10917","display_name":"Smart Grid Security and Resilience","score":0.21469999849796295,"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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.08810000121593475,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/supervisor","display_name":"Supervisor","score":0.819100022315979},{"id":"https://openalex.org/keywords/supervisory-control","display_name":"Supervisory control","score":0.7757999897003174},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6775000095367432},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6274999976158142},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5224000215530396},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4180000126361847}],"concepts":[{"id":"https://openalex.org/C2779110517","wikidata":"https://www.wikidata.org/wiki/Q1240788","display_name":"Supervisor","level":2,"score":0.819100022315979},{"id":"https://openalex.org/C92991967","wikidata":"https://www.wikidata.org/wiki/Q7644329","display_name":"Supervisory control","level":3,"score":0.7757999897003174},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6775000095367432},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6274999976158142},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6057999730110168},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5224000215530396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4537999927997589},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4180000126361847},{"id":"https://openalex.org/C71745522","wikidata":"https://www.wikidata.org/wiki/Q2476929","display_name":"Confidentiality","level":2,"score":0.4043000042438507},{"id":"https://openalex.org/C2775960376","wikidata":"https://www.wikidata.org/wiki/Q1435859","display_name":"Grippers","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.38679999113082886},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3765000104904175},{"id":"https://openalex.org/C60056205","wikidata":"https://www.wikidata.org/wiki/Q691914","display_name":"Opacity","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2703999876976013},{"id":"https://openalex.org/C2910417920","wikidata":"https://www.wikidata.org/wiki/Q4116434","display_name":"Patient privacy","level":3,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc57313.2025.11312251","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312251","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,22,35,68,85,88],"advancement":[2],"of":[3,21,37,87],"communication":[4],"and":[5,78],"network":[6],"technologies,":[7],"multiple":[8,46],"intruders":[9],"can":[10],"collaborate":[11],"to":[12,27,66],"infer":[13],"a":[14,25,51,74],"system\u2019s":[15],"confidential":[16],"information.":[17],"Without":[18],"formal":[19],"models":[20],"system,":[23],"synthesizing":[24,57],"supervisor":[26],"enforce":[28],"opacity":[29,41],"becomes":[30],"particularly":[31],"challenging.":[32],"To":[33],"address":[34],"problem":[36],"ensuring":[38],"joint":[39],"current-state":[40],"under":[42],"cooperative":[43],"attacks":[44],"by":[45],"intruders,":[47],"this":[48],"paper":[49],"proposes":[50],"deep":[52,62],"reinforcement":[53],"learning-based":[54],"algorithm":[55],"for":[56],"supervisory":[58],"control":[59,67],"policies.":[60],"A":[61],"Q-network":[63],"is":[64],"trained":[65],"system.":[69],"Experimental":[70],"evaluations":[71],"conducted":[72],"on":[73],"flexible":[75],"manufacturing":[76],"system":[77,83],"an":[79],"automated":[80],"guided":[81],"vehicle":[82],"demonstrate":[84],"effectiveness":[86],"proposed":[89],"approach.":[90]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-14T00:00:00"}