{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T11:00:13Z","timestamp":1770462013432,"version":"3.49.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T00:00:00Z","timestamp":1670284800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T00:00:00Z","timestamp":1670284800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,12,6]]},"DOI":"10.1109\/cdc51059.2022.9992419","type":"proceedings-article","created":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T19:26:56Z","timestamp":1673378816000},"page":"4892-4897","source":"Crossref","is-referenced-by-count":1,"title":["Policy gradient primal-dual mirror descent for constrained MDPs with large state spaces"],"prefix":"10.1109","author":[{"given":"Dongsheng","family":"Ding","sequence":"first","affiliation":[{"name":"University of Southern California,Ming Hsieh Department of Electrical and Computer Engineering,Los Angeles,CA,90089"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mihailo R.","family":"Jovanovic","sequence":"additional","affiliation":[{"name":"University of Southern California,Ming Hsieh Department of Electrical and Computer Engineering,Los Angeles,CA,90089"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05961-4"},{"issue":"1","key":"ref3","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garc\u0131a","year":"2015","journal-title":"J. Mach. Learn. Res"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref5","article-title":"Reward constrained policy optimization","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Tessler"},{"key":"ref6","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proceedings of the International Conference on Machine Learning","volume":"70","author":"Achiam"},{"key":"ref7","first-page":"8378","article-title":"Natural policy gradient primal-dual method for constrained Markov decision processes","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Ding"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.23919\/ACC53348.2022.9867805"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.23919\/acc53348.2022.9867805"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tac.2022.3152724"},{"key":"ref11","first-page":"7553","article-title":"Constrained reinforcement learning has zero duality gap","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Paternain"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-022-01816-5"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1137\/21m1456789"},{"key":"ref14","article-title":"On the convergence rates of policy gradient methods","author":"Xiao","year":"2022"},{"key":"ref15","article-title":"Accelerated primal-dual policy optimization for safe reinforcement learning","author":"Liang","year":"2018"},{"key":"ref16","first-page":"9133","article-title":"Responsive safety in reinforcement learning by PID Lagrangian methods","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Stooke"},{"key":"ref17","first-page":"3121","article-title":"Convergent policy optimization for safe reinforcement learning","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Yu"},{"key":"ref18","article-title":"A primal-dual approach to constrained Markov decision processes","author":"Chen","year":"2021"},{"key":"ref19","first-page":"3304","article-title":"Provably efficient safe exploration via primal-dual policy optimization","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics","volume":"130","author":"Ding"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cdc51059.2022.9992837"},{"key":"ref21","first-page":"1887","article-title":"A dual approach to constrained Markov decision processes with entropy regularization","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics","author":"Ying"},{"key":"ref22","article-title":"Fast global convergence of policy optimization for constrained MDPs","author":"Liu","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20281"},{"issue":"98","key":"ref24","first-page":"1","article-title":"On the theory of policy gradient methods: Optimality, approximation, and distribution shift","volume":"22","author":"Agarwal","year":"2021","journal-title":"J. Mach. Learn. Res"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1137\/1027074"},{"key":"ref26","article-title":"CRPO: A new approach for safe reinforcement learning with convergence guarantee","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Xu"},{"key":"ref27","first-page":"243","article-title":"Safe reinforcement learning with linear function approximation","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Amani"},{"key":"ref28","first-page":"15666","article-title":"A simple reward-free approach to constrained reinforcement learning","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Miryoosefi"},{"key":"ref29","article-title":"Exploration-exploitation in constrained MDPs","author":"Efroni","year":"2020"},{"key":"ref30","first-page":"1283","article-title":"Provably efficient exploration in policy optimization","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Cai"},{"key":"ref31","first-page":"22931","article-title":"Policy optimization in adversarial MDPs: Improved exploration via dilated bonuses","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Luo"},{"key":"ref32","first-page":"5166","article-title":"Independent policy gradient for large-scale Markov potential games: Sharper rates, function approximation, and game-agnostic convergence","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Ding"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1137\/070704277"},{"key":"ref34","article-title":"Stochastic control foundations of autonomous behavior","volume-title":"Ph.D. dissertation","author":"Paternain","year":"2018"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2705559"}],"event":{"name":"2022 IEEE 61st Conference on Decision and Control (CDC)","location":"Cancun, Mexico","start":{"date-parts":[[2022,12,6]]},"end":{"date-parts":[[2022,12,9]]}},"container-title":["2022 IEEE 61st Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9992315\/9992317\/09992419.pdf?arnumber=9992419","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T12:11:51Z","timestamp":1706789511000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9992419\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/cdc51059.2022.9992419","relation":{},"subject":[],"published":{"date-parts":[[2022,12,6]]}}}