{"id":"https://openalex.org/W4411203209","doi":"https://doi.org/10.1109/lcsys.2025.3578573","title":"Relative Entropy Regularized Reinforcement Learning for Efficient Encrypted Policy Synthesis","display_name":"Relative Entropy Regularized Reinforcement Learning for Efficient Encrypted Policy Synthesis","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4411203209","doi":"https://doi.org/10.1109/lcsys.2025.3578573"},"language":"en","primary_location":{"id":"doi:10.1109/lcsys.2025.3578573","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2025.3578573","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"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 Control Systems Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.12358","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jihoon Suh","orcid":"https://orcid.org/0000-0001-5003-4258"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jihoon Suh","raw_affiliation_strings":["School of Aeronautics and Astronautics, Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0001-5003-4258","affiliations":[{"raw_affiliation_string":"School of Aeronautics and Astronautics, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078952614","display_name":"Yeongjun Jang","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yeongjun Jang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, ASRI, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0009-0007-0784-0212","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, ASRI, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072453949","display_name":"Kaoru Teranishi","orcid":"https://orcid.org/0000-0001-6725-7773"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaoru Teranishi","raw_affiliation_strings":["School of Aeronautics and Astronautics, Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0001-6725-7773","affiliations":[{"raw_affiliation_string":"School of Aeronautics and Astronautics, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082230661","display_name":"Takashi Tanaka","orcid":"https://orcid.org/0000-0001-7424-0064"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takashi Tanaka","raw_affiliation_strings":["School of Aeronautics and Astronautics, Purdue University, West Lafayette, IN, USA"],"raw_orcid":"https://orcid.org/0000-0001-7424-0064","affiliations":[{"raw_affiliation_string":"School of Aeronautics and Astronautics, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2082,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83742526,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"9","issue":null,"first_page":"895","last_page":"900"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10237","display_name":"Cryptography and Data Security","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10237","display_name":"Cryptography and Data Security","score":0.9998999834060669,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9991000294685364,"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/T11424","display_name":"Security and Verification in Computing","score":0.9932000041007996,"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":0.7374527454376221},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.49746420979499817},{"id":"https://openalex.org/keywords/encryption","display_name":"Encryption","score":0.48043227195739746},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4229254126548767},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35891902446746826},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33617162704467773},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3235228657722473},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.24717465043067932},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.18684688210487366},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.13401317596435547}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7374527454376221},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.49746420979499817},{"id":"https://openalex.org/C148730421","wikidata":"https://www.wikidata.org/wiki/Q141090","display_name":"Encryption","level":2,"score":0.48043227195739746},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4229254126548767},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35891902446746826},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33617162704467773},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3235228657722473},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.24717465043067932},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.18684688210487366},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.13401317596435547}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lcsys.2025.3578573","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2025.3578573","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"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 Control Systems Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2506.12358","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.12358","pdf_url":"https://arxiv.org/pdf/2506.12358","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.12358","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.12358","pdf_url":"https://arxiv.org/pdf/2506.12358","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W104209573","https://openalex.org/W2071825329","https://openalex.org/W2093524643","https://openalex.org/W2290211681","https://openalex.org/W2502318419","https://openalex.org/W2768174108","https://openalex.org/W2774167780","https://openalex.org/W2794974431","https://openalex.org/W2963426216","https://openalex.org/W2989605743","https://openalex.org/W2996072473","https://openalex.org/W3010850047","https://openalex.org/W3040353046","https://openalex.org/W3183960220","https://openalex.org/W3184400911","https://openalex.org/W4214717370","https://openalex.org/W4229706427","https://openalex.org/W4233840023","https://openalex.org/W4285445889","https://openalex.org/W4289927864","https://openalex.org/W4307462889","https://openalex.org/W4378697376","https://openalex.org/W4388784481","https://openalex.org/W4407949713","https://openalex.org/W4411687825"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"We":[0,13],"propose":[1],"an":[2],"efficient":[3,37],"encrypted":[4,55,89],"policy":[5,46,56,90],"synthesis":[6,57],"to":[7],"develop":[8],"privacy-preserving":[9],"model-based":[10],"reinforcement":[11,19],"learning.":[12],"first":[14],"demonstrate":[15,78],"that":[16],"the":[17,61,79,82],"relative-entropy-regularized":[18],"learning":[20],"framework":[21,84],"offers":[22],"a":[23,34],"computationally":[24],"convenient":[25],"linear":[26],"and":[27,36,49,68],"\u201cmin-free\u201d":[28],"structure":[29],"for":[30,88],"value":[31],"iteration,":[32],"enabling":[33],"direct":[35],"integration":[38],"of":[39,63,81],"fully":[40],"homomorphic":[41],"encryption":[42],"with":[43],"bootstrapping":[44],"into":[45],"synthesis.":[47,91],"Convergence":[48],"error":[50],"bounds":[51],"are":[52],"analyzed":[53],"as":[54],"propagates":[58],"errors":[59,65],"under":[60],"presence":[62],"encryption-induced":[64],"including":[66],"quantization":[67],"bootstrapping.":[69],"Theoretical":[70],"analysis":[71],"is":[72],"validated":[73],"by":[74],"numerical":[75],"simulations.":[76],"Results":[77],"effectiveness":[80],"RERL":[83],"in":[85],"integrating":[86],"FHE":[87]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}
