{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T16:18:27Z","timestamp":1729613907915,"version":"3.28.0"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,14]],"date-time":"2021-12-14T00:00:00Z","timestamp":1639440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,14]]},"DOI":"10.1109\/cdc45484.2021.9683559","type":"proceedings-article","created":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T20:50:18Z","timestamp":1643748618000},"page":"49-56","source":"Crossref","is-referenced-by-count":2,"title":["Adversarial Attacks on Computation of the Modified Policy Iteration Method"],"prefix":"10.1109","author":[{"given":"Ali","family":"Yekkehkhany","sequence":"first","affiliation":[{"name":"University of California,Department of Industrial Engineering and Operations Research,Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Feng","sequence":"additional","affiliation":[{"name":"University of California,Department of Industrial Engineering and Operations Research,Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Javad","family":"Lavaei","sequence":"additional","affiliation":[{"name":"University of California,Department of Industrial Engineering and Operations Research,Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"year":"2017","author":"dimitri","journal-title":"Dynamic Programming and Optimal Control","key":"ref39"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.1109\/JPROC.2019.2918437"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/MNET.2018.1700202"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1109\/MC.2017.9"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1109\/IVS.2018.8500450"},{"key":"ref30","first-page":"2817","article-title":"Robust adversarial reinforcement learning","author":"pinto","year":"2017","journal-title":"International Conference on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.1007\/978-3-030-41110-7_6"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1109\/HPEC.2019.8916519"},{"doi-asserted-by":"publisher","key":"ref35","DOI":"10.1007\/978-3-030-65310-1_6"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1109\/COMST.2017.2682318"},{"key":"ref28","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2015","journal-title":"International Conference on Learning Representations"},{"year":"2017","author":"pattanaik","article-title":"Robust deep reinforcement learning with adversarial attacks","key":"ref27"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11687","article-title":"Alternating optimisation and quadrature for robust control","volume":"32","author":"paul","year":"2018","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1115\/1.4043115"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.24963\/ijcai.2020\/633"},{"year":"2018","author":"jun","article-title":"Adversarial attacks on stochastic bandits","key":"ref22"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/TNSE.2020.3018871"},{"key":"ref24","first-page":"201","article-title":"Online data poisoning attacks","author":"zhang","year":"2020","journal-title":"Learning for Dynamics and Control"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/TCNS.2020.3028035"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1109\/IROS.2017.8206245"},{"key":"ref25","first-page":"991","article-title":"Stochastic linear bandits robust to adversarial attacks","author":"bogunovic","year":"2021","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"doi-asserted-by":"publisher","key":"ref50","DOI":"10.4064\/fm-3-1-133-181"},{"year":"2014","author":"puterman","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming","key":"ref51"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/TSG.2016.2628522"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/HASE.2017.30"},{"doi-asserted-by":"publisher","key":"ref40","DOI":"10.1007\/978-1-4471-5022-0"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/ICRA.2019.8794293"},{"key":"ref13","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"},{"year":"2020","author":"javanmard","article-title":"Precise statistical analysis of classification accuracies for adversarial training","key":"ref14"},{"key":"ref15","article-title":"Safe exploration in Markov decision processes","author":"moldovan","year":"2017","journal-title":"International Conference on Machine Learning"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/ICRA.2017.7989190"},{"year":"2017","author":"fu","article-title":"Learning robust rewards with adversarial inverse reinforcement learning","key":"ref17"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.24963\/ijcai.2017\/525"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.5220\/0006197105590566"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1038\/s41591-018-0310-5"},{"key":"ref3","article-title":"Markov decision processes and its applications in healthcare","author":"patrick","year":"2011","journal-title":"Handbookof Healthcare Delivery Systems"},{"key":"ref6","article-title":"Modern perspectives on reinforcement learning in finance","volume":"1","author":"kolm","year":"2020","journal-title":"Machine Learning for Finance"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1007\/978-3-642-18324-9"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1145\/2882969"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/ACCESS.2020.3045114"},{"year":"2020","author":"feng","article-title":"A hitting time analysis of non-convex optimization with time-varying revelations","key":"ref49"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1201\/9781351006620"},{"doi-asserted-by":"publisher","key":"ref46","DOI":"10.1287\/moor.1060.0188"},{"doi-asserted-by":"publisher","key":"ref45","DOI":"10.1007\/BF00114724"},{"year":"2020","author":"yekkehkhany","article-title":"A hitting time analysis for stochastic time-varying functions with applications to adversarial attacks on computation of Markov decision processes","key":"ref48"},{"key":"ref47","volume":"39","author":"busoniu","year":"2010","journal-title":"Reinforcement Learning and Dynamic Programming Using Function Approximators"},{"doi-asserted-by":"publisher","key":"ref42","DOI":"10.1109\/TCIAIG.2012.2186810"},{"key":"ref41","first-page":"72","article-title":"Efficient selectivity and backup operators in montecarlo tree search","author":"coulom","year":"2006","journal-title":"International conference on computers and games"},{"key":"ref44","article-title":"Learning and value function approximation in complex decision processes","author":"van roy","year":"1998","journal-title":"Ph D Dissertation"},{"doi-asserted-by":"publisher","key":"ref43","DOI":"10.1287\/educ.2017.0166"}],"event":{"name":"2021 60th IEEE Conference on Decision and Control (CDC)","start":{"date-parts":[[2021,12,14]]},"location":"Austin, TX, USA","end":{"date-parts":[[2021,12,17]]}},"container-title":["2021 60th IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9682670\/9682776\/09683559.pdf?arnumber=9683559","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,17]],"date-time":"2024-09-17T19:06:04Z","timestamp":1726599964000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9683559\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,14]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/cdc45484.2021.9683559","relation":{},"subject":[],"published":{"date-parts":[[2021,12,14]]}}}