{"id":"https://openalex.org/W4315489188","doi":"https://doi.org/10.1109/cdc51059.2022.9992410","title":"Privacy-Preserving Reinforcement Learning Beyond Expectation","display_name":"Privacy-Preserving Reinforcement Learning Beyond Expectation","publication_year":2022,"publication_date":"2022-12-06","ids":{"openalex":"https://openalex.org/W4315489188","doi":"https://doi.org/10.1109/cdc51059.2022.9992410"},"language":"en","primary_location":{"id":"doi:10.1109/cdc51059.2022.9992410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc51059.2022.9992410","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 61st 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/A5072425371","display_name":"Arezoo Rajabi","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arezoo Rajabi","raw_affiliation_strings":["University of Washington,Network Security Lab,Department of Electrical and Computer Engineering,Seattle,WA,USA,98195"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington,Network Security Lab,Department of Electrical and Computer Engineering,Seattle,WA,USA,98195","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052064870","display_name":"Bhaskar Ramasubramanian","orcid":"https://orcid.org/0000-0002-2166-7838"},"institutions":[{"id":"https://openalex.org/I52669646","display_name":"Western Washington University","ror":"https://ror.org/05wn7r715","country_code":"US","type":"education","lineage":["https://openalex.org/I52669646"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhaskar Ramasubramanian","raw_affiliation_strings":["Western Washington University,Electrical and Computer Engineering,Bellingham,WA,USA,98225"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Western Washington University,Electrical and Computer Engineering,Bellingham,WA,USA,98225","institution_ids":["https://openalex.org/I52669646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091549518","display_name":"Abdullah Al Maruf","orcid":"https://orcid.org/0000-0001-5595-9647"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdullah Al Maruf","raw_affiliation_strings":["University of Washington,Network Security Lab,Department of Electrical and Computer Engineering,Seattle,WA,USA,98195"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington,Network Security Lab,Department of Electrical and Computer Engineering,Seattle,WA,USA,98195","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079723268","display_name":"Radha Poovendran","orcid":"https://orcid.org/0000-0003-0269-8097"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Radha Poovendran","raw_affiliation_strings":["University of Washington,Network Security Lab,Department of Electrical and Computer Engineering,Seattle,WA,USA,98195"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington,Network Security Lab,Department of Electrical and Computer Engineering,Seattle,WA,USA,98195","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4706","last_page":"4713"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.987500011920929,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.987500011920929,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10524","display_name":"Traffic control and management","score":0.9605000019073486,"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/T11942","display_name":"Transportation and Mobility Innovations","score":0.9546999931335449,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8573198318481445},{"id":"https://openalex.org/keywords/differential-privacy","display_name":"Differential privacy","score":0.8027549386024475},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7813180685043335},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5182394981384277},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4610077738761902},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4502803087234497},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.424642413854599},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.36144113540649414},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3485565781593323},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.13779112696647644}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8573198318481445},{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.8027549386024475},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7813180685043335},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5182394981384277},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4610077738761902},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4502803087234497},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.424642413854599},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36144113540649414},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3485565781593323},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.13779112696647644},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc51059.2022.9992410","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc51059.2022.9992410","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.800000011920929}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1589395967","https://openalex.org/W1825869920","https://openalex.org/W1999874108","https://openalex.org/W2017070213","https://openalex.org/W2038398071","https://openalex.org/W2041946752","https://openalex.org/W2088413745","https://openalex.org/W2093785384","https://openalex.org/W2098432798","https://openalex.org/W2099161251","https://openalex.org/W2107431923","https://openalex.org/W2139914196","https://openalex.org/W2145339207","https://openalex.org/W2162849300","https://openalex.org/W2169206416","https://openalex.org/W2257979135","https://openalex.org/W2411577903","https://openalex.org/W2570759866","https://openalex.org/W2784041991","https://openalex.org/W2796289712","https://openalex.org/W2887536917","https://openalex.org/W2897254705","https://openalex.org/W2901621510","https://openalex.org/W2905148377","https://openalex.org/W2909906617","https://openalex.org/W2952161445","https://openalex.org/W2962883549","https://openalex.org/W2965585060","https://openalex.org/W2970356364","https://openalex.org/W2994668099","https://openalex.org/W3011865677","https://openalex.org/W3021487874","https://openalex.org/W3104184956","https://openalex.org/W3111425826","https://openalex.org/W3118656864","https://openalex.org/W3119931447","https://openalex.org/W3120310250","https://openalex.org/W3122620151","https://openalex.org/W3124407081","https://openalex.org/W3157075202","https://openalex.org/W3162902207","https://openalex.org/W3215494060","https://openalex.org/W4205228770","https://openalex.org/W4210333964","https://openalex.org/W4210879306","https://openalex.org/W4211049957","https://openalex.org/W4236670843","https://openalex.org/W4298023569","https://openalex.org/W4327873626","https://openalex.org/W6683755438","https://openalex.org/W6687063787","https://openalex.org/W6697282503","https://openalex.org/W6767102351","https://openalex.org/W6767300576","https://openalex.org/W6772962736","https://openalex.org/W6781089347","https://openalex.org/W6802757742"],"related_works":["https://openalex.org/W3038283795","https://openalex.org/W2604501336","https://openalex.org/W2734500670","https://openalex.org/W2558166297","https://openalex.org/W2315671126","https://openalex.org/W798507144","https://openalex.org/W2964481303","https://openalex.org/W1751413323","https://openalex.org/W2571704763","https://openalex.org/W3206394311"],"abstract_inverted_index":{"Cyber":[0],"and":[1,69,72,130,172],"cyber-physical":[2],"systems":[3],"equipped":[4],"with":[5,15,30,186],"machine":[6],"learning":[7,96],"algorithms":[8],"such":[9,18],"as":[10],"autonomous":[11],"cars":[12],"share":[13],"environments":[14],"humans.":[16],"In":[17],"a":[19,65,74,94,123,127,153,157,169,189,197],"setting,":[20],"it":[21],"is":[22,56,149,178],"important":[23],"to":[24,47,57,67,76,113,118,121,180],"align":[25],"system":[26],"(or":[27],"agent)":[28],"behaviors":[29,49,182],"the":[31,41,91,100,103,134,141,175,193],"preferences":[32],"of":[33,62,93,136,188],"one":[34],"or":[35],"more":[36],"human":[37,190],"users.":[38],"We":[39,84,109],"consider":[40],"case":[42],"when":[43,143],"an":[44,51,111,115],"agent":[45,117,177],"has":[46],"learn":[48,119,181],"in":[50,126,192,196],"unknown":[52],"environment.":[53],"Our":[54],"goal":[55],"capture":[58],"two":[59],"defining":[60],"characteristics":[61],"humans:":[63],"i)":[64],"tendency":[66],"assess":[68],"quantify":[70],"risk,":[71],"ii)":[73],"desire":[75],"keep":[77],"decision":[78],"making":[79],"hidden":[80],"from":[81],"external":[82],"parties.":[83],"incorporate":[85],"cumulative":[86],"prospect":[87],"theory":[88],"(CPT)":[89],"into":[90],"objective":[92,125],"reinforcement":[95],"(RL)":[97],"problem":[98],"for":[99],"former.":[101],"For":[102],"latter,":[104],"we":[105,167],"use":[106],"differential":[107],"privacy.":[108],"design":[110],"algorithm":[112,142],"enable":[114],"RL":[116,176],"policies":[120],"maximize":[122],"CPT-based":[124],"privacy-preserving":[128,198],"manner":[129],"establish":[131],"guarantees":[132],"on":[133],"privacy":[135],"value":[137],"functions":[138],"learned":[139],"by":[140],"rewards":[144],"are":[145,184],"sufficiently":[146],"close.":[147],"This":[148],"accomplished":[150],"through":[151],"adding":[152],"calibrated":[154],"noise":[155],"using":[156],"Gaussian":[158],"process":[159],"mechanism":[160],"at":[161],"each":[162],"step.":[163],"Through":[164],"empirical":[165],"evaluations,":[166],"highlight":[168],"privacy-utility":[170],"tradeoff":[171],"demonstrate":[173],"that":[174,183,187],"able":[179],"aligned":[185],"user":[191],"same":[194],"environment":[195],"manner.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}