{"id":"https://openalex.org/W4281900906","doi":"https://doi.org/10.1145/3489048.3522648","title":"Differentially Private Reinforcement Learning with Linear Function Approximation","display_name":"Differentially Private Reinforcement Learning with Linear Function Approximation","publication_year":2022,"publication_date":"2022-06-02","ids":{"openalex":"https://openalex.org/W4281900906","doi":"https://doi.org/10.1145/3489048.3522648"},"language":"en","primary_location":{"id":"doi:10.1145/3489048.3522648","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3489048.3522648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Abstract Proceedings of the 2022 ACM SIGMETRICS/IFIP PERFORMANCE Joint International Conference on Measurement and Modeling of Computer Systems","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/A5067378652","display_name":"Xingyu Zhou","orcid":"https://orcid.org/0000-0002-1771-8831"},"institutions":[{"id":"https://openalex.org/I185443292","display_name":"Wayne State University","ror":"https://ror.org/01070mq45","country_code":"US","type":"education","lineage":["https://openalex.org/I185443292"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xingyu Zhou","raw_affiliation_strings":["Wayne State University, Detroit, MI, USA"],"affiliations":[{"raw_affiliation_string":"Wayne State University, Detroit, MI, USA","institution_ids":["https://openalex.org/I185443292"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5067378652"],"corresponding_institution_ids":["https://openalex.org/I185443292"],"apc_list":null,"apc_paid":null,"fwci":0.5305,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70047809,"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":"77","last_page":"78"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9995999932289124,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9995999932289124,"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/T13553","display_name":"Age of Information Optimization","score":0.9979000091552734,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9869999885559082,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.943813681602478},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8890612721443176},{"id":"https://openalex.org/keywords/differential-privacy","display_name":"Differential privacy","score":0.8399602174758911},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7947608828544617},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7025442123413086},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.6314604878425598},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5317659974098206},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4707779586315155},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4449627995491028},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3862874507904053},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35568180680274963},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.340182900428772},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22127360105514526},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20367956161499023},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16652873158454895}],"concepts":[{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.943813681602478},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8890612721443176},{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.8399602174758911},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7947608828544617},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7025442123413086},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.6314604878425598},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5317659974098206},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4707779586315155},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4449627995491028},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3862874507904053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35568180680274963},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.340182900428772},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22127360105514526},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20367956161499023},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16652873158454895},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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:10.1145/3489048.3522648","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3489048.3522648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Abstract Proceedings of the 2022 ACM SIGMETRICS/IFIP PERFORMANCE Joint International Conference on Measurement and Modeling of Computer Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2342662072","https://openalex.org/W2492794003","https://openalex.org/W2560862806","https://openalex.org/W2883364792","https://openalex.org/W2952235417","https://openalex.org/W2963595477","https://openalex.org/W2994818021","https://openalex.org/W3044994114","https://openalex.org/W6638018090"],"related_works":["https://openalex.org/W4287863949","https://openalex.org/W4287102143","https://openalex.org/W1850488217","https://openalex.org/W2945119207","https://openalex.org/W3182614517","https://openalex.org/W2152670157","https://openalex.org/W2970347269","https://openalex.org/W2101748387","https://openalex.org/W2808418668","https://openalex.org/W1574958246"],"abstract_inverted_index":{"Motivated":[0],"by":[1],"the":[2,34,56,84,92,131,137,147,152],"wide":[3],"adoption":[4],"of":[5,36,86,136,139,149],"reinforcement":[6,199],"learning":[7,61,172],"(RL)":[8],"in":[9,27,62,158,173],"real-world":[10],"personalized":[11,161],"services,":[12],"where":[13,91],"users'":[14,99],"sensitive":[15,100],"and":[16,67,114,118,141],"private":[17,43,105,198],"information":[18],"needs":[19],"to":[20,41],"be":[21],"protected,":[22],"we":[23,54,71],"study":[24],"regret":[25,124,132],"minimization":[26],"finite-horizon":[28],"Markov":[29],"decision":[30],"processes":[31],"(MDPs)":[32],"under":[33,83,177],"constraints":[35],"differential":[37,88],"privacy":[38,89,128,156],"(DP).":[39],"Compared":[40],"existing":[42],"RL":[44,93,106],"algorithms":[45,107,153],"that":[46,108,120],"work":[47],"only":[48,182],"on":[49,111],"tabular":[50],"finite-state,":[51],"finite-actions":[52],"MDPs,":[53],"take":[55],"first":[57],"step":[58],"towards":[59],"privacy-preserving":[60],"MDPs":[63,73,176],"with":[64,74,146],"large":[65],"state":[66],"action":[68],"spaces.":[69],"Specifically,":[70],"consider":[72],"linear":[75,80,174],"function":[76],"approximation":[77],"(in":[78],"particular":[79],"mixture":[81,175],"MDPs)":[82],"notion":[85],"joint":[87],"(JDP),":[90],"agent":[94],"is":[95],"responsible":[96],"for":[97,155,171,186,196],"protecting":[98],"data.":[101],"We":[102],"design":[103],"two":[104],"are":[109,134,165],"based":[110],"value":[112],"iteration":[113],"policy":[115],"optimization,":[116],"respectively,":[117],"show":[119],"they":[121],"enjoy":[122],"sub-linear":[123],"performance":[125],"while":[126],"guaranteeing":[127],"protection.":[129],"Moreover,":[130],"bounds":[133],"independent":[135],"number":[138,148],"states,":[140],"scale":[142],"at":[143],"most":[144],"logarithmically":[145],"actions,":[150],"making":[151],"suitable":[154],"protection":[157],"nowadays":[159],"large-scale":[160],"services.":[162],"Our":[163],"results":[164,185],"achieved":[166],"via":[167],"a":[168,193],"general":[169,197],"procedure":[170],"changing":[178],"regularizers,":[179],"which":[180],"not":[181],"generalizes":[183],"previous":[184],"non-private":[187],"learning,":[188],"but":[189],"also":[190],"serves":[191],"as":[192],"building":[194],"block":[195],"learning.":[200]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}