{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T16:06:54Z","timestamp":1775146014458,"version":"3.50.1"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["ECCS-1554576"],"award-info":[{"award-number":["ECCS-1554576"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"U.S. Department of Energy, Office of Science, Advanced Scientific Computing Research","award":["DE-AC02-06CH11357"],"award-info":[{"award-number":["DE-AC02-06CH11357"]}]},{"name":"DOE Early Career Research Program Award"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tnnls.2023.3315598","type":"journal-article","created":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T17:44:19Z","timestamp":1696009459000},"page":"18914-18921","source":"Crossref","is-referenced-by-count":3,"title":["A Gradient-Aware Search Algorithm for Constrained Markov Decision Processes"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6730-7267","authenticated-orcid":false,"given":"Sami","family":"Khairy","sequence":"first","affiliation":[{"name":"Illinois Institute of Technology, Chicago, IL, USA"}]},{"given":"Prasanna","family":"Balaprakash","sequence":"additional","affiliation":[{"name":"Computing and Computational Sciences Directorate, Oak Ridge National Laboratory, Oak Ridge, TN, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8509-0452","authenticated-orcid":false,"given":"Lin X.","family":"Cai","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Illinois Institute of Technology, Chicago, IL, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3060187"},{"issue":"1","key":"ref3","first-page":"2","volume-title":"Benchmarking safe exploration in deep reinforcement learning","volume":"7","author":"Ray","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2392122"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2526615"},{"key":"ref6","first-page":"325","article-title":"A geometric approach to multi-criterion reinforcement learning","volume":"5","author":"Mannor","year":"2004","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"ref7","first-page":"3483","article-title":"Multi-objective reinforcement learning using sets of Pareto dominating policies","volume":"15","author":"Van Moffaert","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121546"},{"key":"ref10","first-page":"1326","article-title":"Stationary deterministic policies for constrained MDPs with multiple rewards, costs, and discount factors","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","volume":"19","author":"Dolgov"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2006.872754"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6377(00)00039-0"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2004.826725"},{"issue":"3","key":"ref14","first-page":"645","article-title":"Dynamic programming in constrained Markov decision processes","volume":"35","author":"Piunovskiy","year":"2006","journal-title":"Control Cybern."},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s00186-006-0133-x"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1666"},{"issue":"2","key":"ref17","first-page":"241","article-title":"Learning algorithms for discounted MDPS with constraints","volume":"21","author":"Geibel","year":"2012","journal-title":"Int. J. Math., Game Theory, Algebra"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2004.08.007"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2002.1184811"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2010.08.013"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-012-9989-5"},{"key":"ref22","article-title":"Reward constrained policy optimization","author":"Tessler","year":"2018","journal-title":"arXiv:1805.11074"},{"key":"ref23","article-title":"Accelerated primal-dual policy optimization for safe reinforcement learning","author":"Liang","year":"2018","journal-title":"arXiv:1802.06480"},{"key":"ref24","article-title":"Risk-sensitive reinforcement learning: A constrained optimization viewpoint","author":"Fu","year":"2018","journal-title":"arXiv:1810.09126"},{"key":"ref25","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Achiam"},{"key":"ref26","article-title":"Actor-critic algorithms for risk-sensitive reinforcement learning","author":"Prashanth","year":"2014","journal-title":"arXiv:1403.6530"},{"key":"ref27","article-title":"Safe policies for reinforcement learning via primal-dual methods","author":"Paternain","year":"2019","journal-title":"arXiv:1911.09101"},{"key":"ref28","article-title":"Provably efficient safe exploration via primal-dual policy optimization","author":"Ding","year":"2020","journal-title":"arXiv:2003.00534"},{"key":"ref29","volume-title":"Benchmarking Safe Exploration in Deep Reinforcement Learning","author":"Ray"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3018804"},{"key":"ref31","article-title":"On the complexity of solving Markov decision problems","author":"Littman","year":"2013","journal-title":"arXiv:1302.4971"},{"key":"ref32","first-page":"1522","article-title":"Risk-sensitive and robust decision-making: A CVAR optimization approach","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chow"},{"issue":"1","key":"ref33","first-page":"6070","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"Chow","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref34","article-title":"IPO: Interior-point policy optimization under constraints","author":"Liu","year":"2019","journal-title":"arXiv:1910.09615"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2018.12.013"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2018.2875524"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2016.2578312"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2900630"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1239\/jap\/1037816024"},{"key":"ref40","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/5962385\/10772360\/10267915-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10772360\/10267915.pdf?arnumber=10267915","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T19:10:41Z","timestamp":1733253041000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10267915\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":40,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3315598","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}