{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T22:54:38Z","timestamp":1768344878032,"version":"3.49.0"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,31]],"date-time":"2022-10-31T00:00:00Z","timestamp":1667174400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,31]],"date-time":"2022-10-31T00:00:00Z","timestamp":1667174400000},"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":["CAREER 1752362,CPS 2136324,TRIPODS 1934979"],"award-info":[{"award-number":["CAREER 1752362,CPS 2136324,TRIPODS 1934979"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,10,31]]},"DOI":"10.1109\/ieeeconf56349.2022.10052060","type":"proceedings-article","created":{"date-parts":[[2023,3,7]],"date-time":"2023-03-07T18:41:29Z","timestamp":1678214489000},"page":"1362-1366","source":"Crossref","is-referenced-by-count":3,"title":["Constrained Reinforcement Learning via Dissipative Saddle Flow Dynamics"],"prefix":"10.1109","author":[{"given":"Tianqi","family":"Zheng","sequence":"first","affiliation":[{"name":"Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA,21218"}]},{"given":"Pengcheng","family":"You","sequence":"additional","affiliation":[{"name":"Peking University,Dept. of Industrial Engineering and Management,Beijing,China"}]},{"given":"Enrique","family":"Mallada","sequence":"additional","affiliation":[{"name":"Johns Hopkins University,Department of Electrical and Computer Engineering,Baltimore,MD,USA,21218"}]}],"member":"263","reference":[{"key":"ref1","first-page":"325","article-title":"A geometric approach to multi-criterion reinforcement learning","volume":"5","author":"Mannor","year":"2004","journal-title":"The Journal of Machine Learning Research"},{"key":"ref2","first-page":"22","article-title":"Constrained policy optimization","volume-title":"International conference on machine learning. PMLR","author":"Achiam","year":"2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref4","article-title":"Constrained reinforcement learning has zero duality gap","volume":"32","author":"Paternain","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref5","article-title":"Rein-forcement learning with almost sure constraints","author":"Castellano","year":"2021","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"A primal-dual approach to constrained markov decision processes","author":"Chen","year":"2021","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20281"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tac.2023.3319070"},{"key":"ref9","first-page":"17183","article-title":"Learning policies with zero or bounded constraint violation for constrained mdps","volume":"34","author":"Liu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref10","first-page":"8378","article-title":"Natural policy gradient primal-dual method for constrained markov decision processes","volume":"33","author":"Ding","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9483346"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2015.10.006"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF56349.2022.10052060"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4684-9352-8"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2019.1000"}],"event":{"name":"2022 56th Asilomar Conference on Signals, Systems, and Computers","location":"Pacific Grove, CA, USA","start":{"date-parts":[[2022,10,31]]},"end":{"date-parts":[[2022,11,2]]}},"container-title":["2022 56th Asilomar Conference on Signals, Systems, and Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10051833\/10051818\/10052060.pdf?arnumber=10052060","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T18:39:59Z","timestamp":1707849599000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10052060\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,31]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/ieeeconf56349.2022.10052060","relation":{},"subject":[],"published":{"date-parts":[[2022,10,31]]}}}