{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:39:23Z","timestamp":1781797163370,"version":"3.54.5"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T00:00:00Z","timestamp":1670284800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T00:00:00Z","timestamp":1670284800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,12,6]]},"DOI":"10.1109\/cdc51059.2022.9992410","type":"proceedings-article","created":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T19:26:56Z","timestamp":1673378816000},"page":"4706-4713","source":"Crossref","is-referenced-by-count":2,"title":["Privacy-Preserving Reinforcement Learning Beyond Expectation"],"prefix":"10.1109","author":[{"given":"Arezoo","family":"Rajabi","sequence":"first","affiliation":[{"name":"University of Washington,Network Security Lab,Department of Electrical and Computer Engineering,Seattle,WA,USA,98195"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bhaskar","family":"Ramasubramanian","sequence":"additional","affiliation":[{"name":"Western Washington University,Electrical and Computer Engineering,Bellingham,WA,USA,98225"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdullah","family":"Al Maruf","sequence":"additional","affiliation":[{"name":"University of Washington,Network Security Lab,Department of Electrical and Computer Engineering,Seattle,WA,USA,98195"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Radha","family":"Poovendran","sequence":"additional","affiliation":[{"name":"University of Washington,Network Security Lab,Department of Electrical and Computer Engineering,Seattle,WA,USA,98195"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref2","volume-title":"Dynamic Programming and Optimal Control","volume":"1","author":"Bertsekas","year":"2017"},{"key":"ref3","volume-title":"Markov decision processes: Discrete stochastic dynamic programming","author":"Puterman","year":"2014"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-011-5235-x"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2904897"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2016.xii.029"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2018.2881359"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2019.01.003"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2744769.2747927"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2018.10.003"},{"key":"ref13","first-page":"1512","article-title":"FRESH: Interactive reward shaping in high-dimensional state spaces using human feedback","volume-title":"International Conference on Autonomous Agents and MultiAgent Systems","author":"Xiao"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.2307\/1914185"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/S0022-2496(02)00015-9"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1257\/jep.27.1.173"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/BF00122574"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683261"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1561\/0400000042"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2019.2951713"},{"key":"ref21","article-title":"Privacy-preserving Q-learning with functional noise in continuous spaces","volume":"32","author":"Wang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","first-page":"663","article-title":"Algorithms for inverse reinforcement learning","volume-title":"International Coference on Machine Learning","author":"Ng"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1137\/120899005"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00600"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.2307\/2975974"},{"key":"ref27","first-page":"1651","article-title":"Policy gradients with variance related risk criteria","volume-title":"International Coference on Machine Learning","author":"Tamar"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2013.06.019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.18.7.356"},{"key":"ref30","volume-title":"Risk-sensitive optimal control","author":"Whittle","year":"1990"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.2.294.324"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-4266(02)00271-6"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17393"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3131149"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9304056"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28619-4_10"},{"key":"ref37","first-page":"6070","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"Chow","year":"2017","journal-title":"The Journal of Machine Learning Research"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/indiancc.2019.8715578"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2822658"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2018.07.028"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2021.105009"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7798915"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3148710"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-060117-105018"},{"key":"ref45","article-title":"Asymmetric distances for approximate differential privacy","volume-title":"International Conference on Concurrency Theory","author":"Chistikov"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9304080"},{"key":"ref47","article-title":"Differentially private policy evaluation","volume-title":"International Conference on Machine Learning","author":"Balle"},{"key":"ref48","first-page":"9754","article-title":"Private reinforcement learning with PAC and regret guarantees","volume-title":"International Conference on Machine Learning","author":"Vietri"},{"key":"ref49","article-title":"Local differential privacy for regret minimization in reinforcement learning","volume":"34","author":"Garcelon","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9304015"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.2307\/2998573"},{"key":"ref52","volume-title":"Gaussian processes for machine learning","author":"Williams","year":"2006"},{"issue":"1","key":"ref53","first-page":"703","article-title":"Differential privacy for functions and functional data","volume":"14","author":"Hall","year":"2013","journal-title":"The Journal of Machine Learning Research"},{"key":"ref54","article-title":"Introduction to Gaussian processes","author":"Lalley","year":"2013"}],"event":{"name":"2022 IEEE 61st Conference on Decision and Control (CDC)","location":"Cancun, Mexico","start":{"date-parts":[[2022,12,6]]},"end":{"date-parts":[[2022,12,9]]}},"container-title":["2022 IEEE 61st Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9992315\/9992317\/09992410.pdf?arnumber=9992410","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T09:27:34Z","timestamp":1709371654000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9992410\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,6]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/cdc51059.2022.9992410","relation":{},"subject":[],"published":{"date-parts":[[2022,12,6]]}}}