{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T18:26:40Z","timestamp":1770229600210,"version":"3.49.0"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62071416"],"award-info":[{"award-number":["62071416"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tsp.2022.3158737","type":"journal-article","created":{"date-parts":[[2022,3,15]],"date-time":"2022-03-15T19:40:28Z","timestamp":1647373228000},"page":"1609-1624","source":"Crossref","is-referenced-by-count":18,"title":["Successive Convex Approximation Based Off-Policy Optimization for Constrained Reinforcement Learning"],"prefix":"10.1109","volume":"70","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1895-1758","authenticated-orcid":false,"given":"Chang","family":"Tian","sequence":"first","affiliation":[{"name":"State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3943-5234","authenticated-orcid":false,"given":"An","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hang Zhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guan","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hang Zhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wu","family":"Luo","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.011.2000195"},{"issue":"42","key":"ref4","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":"ref5","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref6","article-title":"Benchmarking safe exploration in deep reinforcement learning","author":"Ray","year":"2019"},{"key":"ref7","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"Comput. Res. Repository"},{"key":"ref8","first-page":"1017","article-title":"P3o: Policy-on policy-off policy optimization","volume-title":"Proc. 35th Uncertainty Artif. Intell. Conf., ser. Proc. Mach. Learn. Res.","volume":"115","author":"Fakoor","year":"2020"},{"key":"ref9","first-page":"3849","article-title":"Interpolated policy gradient: Merging on-policy and off-policy gradient estimation for deep reinforcement learning","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Gu","year":"2017"},{"key":"ref10","article-title":"Generalized proximal policy optimization with sample reuse","volume":"34","author":"Queeney","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref11","article-title":"Black-box off-policy estimation for infinite-horizon reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Mousavi","year":"2020"},{"issue":"141","key":"ref12","first-page":"1","article-title":"Importance sampling techniques for policy optimization","volume":"21","author":"Metelli","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref13","article-title":"Off-policy policy gradient algorithms by constraining the state distribution shift","author":"Islam","year":"2019"},{"key":"ref14","article-title":"Algaedice: Policy gradient from arbitrary experience","author":"Nachum","year":"2019"},{"key":"ref15","first-page":"8378","article-title":"Natural policy gradient primal-dual method for constrained markov decision processes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ding","year":"2020"},{"key":"ref16","article-title":"Reward constrained policy optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tessler","year":"2019"},{"key":"ref17","first-page":"9133","article-title":"Responsive safety in reinforcement learning by PID lagrangian methods","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Stooke","year":"2020"},{"key":"ref18","article-title":"Provably efficient safe exploration via primal-dual policy optimization","author":"Ding","year":"2020","journal-title":"Comput. Res. Repository"},{"key":"ref19","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Achiam","year":"2017"},{"key":"ref20","first-page":"15338","article-title":"First order constrained optimization in policy space","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Zhang","year":"2020"},{"key":"ref21","article-title":"Projection-based constrained policy optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang","year":"2020"},{"key":"ref22","article-title":"Lyapunov-based safe policy optimization for continuous control","volume-title":"Proc. Int. Conf. Mach. Learn. Workshop Reinforcement Learn. Real Life","author":"Chow","year":"2019"},{"key":"ref23","first-page":"8502","article-title":"Constrained markov decision processes via backward value functions","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Satija","year":"2020"},{"key":"ref24","article-title":"Safe exploration in continuous action spaces","author":"Dalal","year":"2018","journal-title":"Comput. Res. Repository"},{"key":"ref25","first-page":"3127","article-title":"Convergent policy optimization for safe reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Yu","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2925601"},{"key":"ref27","first-page":"1627","article-title":"A convergent form of approximate policy iteration","volume-title":"Proc. 15th Int. Conf. Neural Inf. Process. Syst.","author":"Perkins","year":"2002"},{"key":"ref28","first-page":"8668","article-title":"Finite-sample analysis for sarsa with linear function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Zou","year":"2019"},{"key":"ref29","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2004.840638"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-053018-023825"},{"key":"ref32","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Sutton","year":"2000"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2993442"},{"key":"ref34","first-page":"834","article-title":"Improving stochastic policy gradients in continuous control with deep reinforcement learning using the beta distribution","volume-title":"Proc. 34th Int. Conf. Mach. Learn., ser. Proc. Mach. Learn. Res.","volume":"70","author":"Chou","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2717986"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/BF01581643"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1239\/jap\/1134587812"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/S0377-0427(00)00433-7"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/78\/9675017\/09735284.pdf?arnumber=9735284","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T23:07:29Z","timestamp":1705532849000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9735284\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/tsp.2022.3158737","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"value":"1053-587X","type":"print"},{"value":"1941-0476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}