{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T15:45:47Z","timestamp":1766159147798,"version":"3.28.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,3,22]],"date-time":"2023-03-22T00:00:00Z","timestamp":1679443200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,22]],"date-time":"2023-03-22T00:00:00Z","timestamp":1679443200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,3,22]]},"DOI":"10.1109\/ciss56502.2023.10089763","type":"proceedings-article","created":{"date-parts":[[2023,4,10]],"date-time":"2023-04-10T18:58:36Z","timestamp":1681153116000},"page":"1-6","source":"Crossref","is-referenced-by-count":6,"title":["Policy Gradients for Probabilistic Constrained Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Weiqin","family":"Chen","sequence":"first","affiliation":[{"name":"Rensselaer Polytechnic Institute,Department of Electrical, Computer, and Systems Engineering,Troy,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dharmashankar","family":"Subramanian","sequence":"additional","affiliation":[{"name":"IBM T. J. Watson Research Center,Yorktown Heights,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Santiago","family":"Paternain","sequence":"additional","affiliation":[{"name":"Rensselaer Polytechnic Institute,Department of Electrical, Computer, and Systems Engineering,Troy,NY,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"issue":"1","key":"ref3","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref4","first-page":"1329","article-title":"Bench-marking deep reinforcement learning for continuous control","volume-title":"International conference on machine learning","author":"Duan","year":"2016"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref6","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"Sutton","year":"1999","journal-title":"Advances in neural information processing systems"},{"issue":"1","key":"ref7","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garcia","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460655"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_63"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.camwa.2005.11.013"},{"issue":"1","key":"ref11","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":"ref12","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.18.7.356"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1527\/tjsai.16.353"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1666"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2004.08.007"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-012-9989-5"},{"key":"ref18","article-title":"Accelerated primal-dual policy optimization for safe reinforcement learning","author":"Liang","year":"2018","journal-title":"arXiv preprint"},{"key":"ref19","first-page":"22","article-title":"Constrained policy optimization","volume-title":"International conference on machine learning","author":"Achiam","year":"2017"},{"key":"ref20","article-title":"Reward constrained policy optimization","author":"Tessler","year":"2018","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Projection-based constrained policy optimization","author":"Yang","year":"2020","journal-title":"arXiv preprint"},{"key":"ref22","first-page":"15338","article-title":"First order constrained optimization in policy space","volume":"33","author":"Zhang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5932"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/520"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref26","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv preprint"},{"key":"ref27","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"International conference on machine learning","author":"Schulman","year":"2015"},{"key":"ref28","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref29","first-page":"559","article-title":"Reinforcement learning with almost sure constraints","volume-title":"Learning for Dynamics and Control Conference","author":"Castellano","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tac.2022.3152724"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IV48863.2021.9575205"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/BF01442131"},{"key":"ref34","volume-title":"Studies in linear and non-linear programming","volume":"2","author":"Arrow","year":"1958"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1057\/palgrave.jors.2600425"}],"event":{"name":"2023 57th Annual Conference on Information Sciences and Systems (CISS)","start":{"date-parts":[[2023,3,22]]},"location":"Baltimore, MD, USA","end":{"date-parts":[[2023,3,24]]}},"container-title":["2023 57th Annual Conference on Information Sciences and Systems (CISS)"],"original-title":[],"link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/xplorestaging.ieee.org\/ielx7\/10089615\/10089616\/10089763.pdf?arnumber=10089763","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,3]],"date-time":"2024-03-03T11:13:22Z","timestamp":1709464402000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/ieeexplore.ieee.org\/document\/10089763\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,22]]},"references-count":35,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/ciss56502.2023.10089763","relation":{},"subject":[],"published":{"date-parts":[[2023,3,22]]}}}