{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:17:47Z","timestamp":1792790267562,"version":"4.5.0"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"ARL DCIST CRA","award":["W911NF-17-2-0181"],"award-info":[{"award-number":["W911NF-17-2-0181"]}]},{"name":"Intel Science and Technology Center for Wireless Autonomous Systems"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Contr."],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1109\/tac.2022.3152724","type":"journal-article","created":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T15:18:07Z","timestamp":1645543087000},"page":"1321-1336","source":"Crossref","is-referenced-by-count":72,"title":["Safe Policies for Reinforcement Learning via Primal-Dual Methods"],"prefix":"10.1109","volume":"68","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6310-6345","authenticated-orcid":false,"given":"Santiago","family":"Paternain","sequence":"first","affiliation":[{"name":"Electrical Computer and Systems Engineering, Renssealaer Polytechnic Institute, Troy, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9001-3379","authenticated-orcid":false,"given":"Miguel","family":"Calvo-Fullana","sequence":"additional","affiliation":[{"name":"Department of Aeronautics and Astronautics, Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7731-6650","authenticated-orcid":false,"given":"Luiz F. O.","family":"Chamon","sequence":"additional","affiliation":[{"name":"University of California, Berkeley, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4230-9906","authenticated-orcid":false,"given":"Alejandro","family":"Ribeiro","sequence":"additional","affiliation":[{"name":"Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-75536-6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1985.1087247"},{"key":"ref3","volume-title":"Dynamics Program and Markov Processes","author":"Howard","year":"1964"},{"key":"ref4","volume-title":"Neuro-Dynamic Program.","volume":"5","author":"Bertsekas","year":"1996"},{"key":"ref5","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"issue":"3\/4","key":"ref6","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1023\/A:1022676722315","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Mach. Learn."},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref8","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutton","year":"2000"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50021-0"},{"issue":"2-3","key":"ref10","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1023\/A:1017940631555","article-title":"Risk-sensitive reinforcement learning","volume":"49","author":"Mihatsch","year":"2002","journal-title":"Mach. Learn."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1666"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_63"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.camwa.2005.11.013"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1080.0685"},{"key":"ref15","first-page":"1651","article-title":"Policy gradients with variance related risk criteria","volume-title":"Proc. 29th Int. Conf. Mach. Learn.","author":"Tamar","year":"2012"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45435-7_25"},{"issue":"167","key":"ref17","first-page":"1","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"Chow","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref18","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Achiam","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3182\/20070822-3-za-2920.00076"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/0196-8858(90)90017-S"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(99)00214-9"},{"key":"ref22","volume-title":"Nonlinear Systems","volume":"3","author":"Khalil","year":"2002"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029423"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.18.7.356"},{"key":"ref25","article-title":"Reward constrained policy optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tessler","year":"2018"},{"key":"ref26","article-title":"AI safety gridworlds","author":"Leike","year":"2017"},{"key":"ref27","article-title":"Simple random search provides a competitive approach to reinforcement learning","author":"Mania","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref29","first-page":"7553","article-title":"Constrained reinforcement learning has zero duality gap","volume-title":"Proc. 33rd Conf. Neural Inf. Process. Syst.","author":"Paternain","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1115\/1.2896456"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(95)00089-6"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029499"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-019-09426-y"},{"issue":"1","key":"ref34","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garca","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(98)00153-8"},{"key":"ref36","first-page":"1451","article-title":"Safe exploration in Markov decision processes","volume-title":"Proc. 29th Int. Conf. Mach. Learn.","author":"Moldovan","year":"2012"},{"key":"ref37","first-page":"4312","article-title":"Safe exploration in finite Markov decision processes with Gaussian processes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Turchetta","year":"2016"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2018.8619572"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.3029317"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-3264-1"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2627401"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2750109"},{"key":"ref43","first-page":"8378","article-title":"Natural policy gradient primal-dual method for constrained Markov decision processes","volume":"33","author":"Ding","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511779398"},{"key":"ref45","first-page":"1008","article-title":"Actor-critic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Konda","year":"2000"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_72229"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90003-8"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/BF02551274"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90020-8"},{"key":"ref50","first-page":"6231","article-title":"The expressive power of neural networks: A view from the width","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu","year":"2017"},{"key":"ref51","first-page":"6169","article-title":"Resnet with one-neuron hidden layers is a universal approximator","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin","year":"2018"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.2.246"},{"key":"ref53","first-page":"773","article-title":"On the relation between universality, characteristic kernels and RKHS embedding of measures","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Sriperumbudur","year":"2010"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/BF00353877"},{"key":"ref55","volume-title":"Studies in Linear and Nonlinear Progress","author":"Arrow","year":"1958"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-009-9522-7"},{"key":"ref57","volume-title":"Nonlinear Prog","author":"Bertsekas","year":"1999"},{"key":"ref58","volume-title":"Convex Optim. Algorithms","author":"Bertsekas","year":"2015"},{"key":"ref59","first-page":"64","article-title":"Optimality and approximation with policy gradient methods in Markov decision processes","volume-title":"Proc. Conf. Learn. Theory","author":"Agarwal","year":"2000"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2018.8431049"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-012-9989-5"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"}],"container-title":["IEEE Transactions on Automatic Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9\/10056266\/09718160.pdf?arnumber=9718160","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T18:26:01Z","timestamp":1705515961000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9718160\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3]]},"references-count":62,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tac.2022.3152724","relation":{},"ISSN":["0018-9286","1558-2523","2334-3303"],"issn-type":[{"value":"0018-9286","type":"print"},{"value":"1558-2523","type":"electronic"},{"value":"2334-3303","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3]]}}}