{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T00:21:50Z","timestamp":1760574110608,"version":"build-2065373602"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T00:00:00Z","timestamp":1750723200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T00:00:00Z","timestamp":1750723200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,24]]},"DOI":"10.23919\/ecc65951.2025.11186950","type":"proceedings-article","created":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T17:38:09Z","timestamp":1760463489000},"page":"364-371","source":"Crossref","is-referenced-by-count":0,"title":["Policy Gradient-based Reinforcement Learning for LQG Control with Chance Constraints"],"prefix":"10.23919","author":[{"given":"Arunava","family":"Naha","sequence":"first","affiliation":[{"name":"Linköping University,Department of Electrical Engineering,Linköping,Sweden,58183"}]},{"given":"Subhrakanti","family":"Dey","sequence":"additional","affiliation":[{"name":"Uppsala University,Department of Electrical Engineering,Uppsala,Sweden,75103"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Dynamic Programming and Optimal Control","volume":"II","author":"Bertsekas","year":"2011"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.10.035"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2887054"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.10.096"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tac.2023.3294868"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/OJCSYS.2023.3291596"},{"article-title":"Global Convergence of Policy Gradient Methods for Output Feedback Linear Quadratic Control","year":"2022","author":"Zhao","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683474"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CDC42340.2020.9303967"},{"volume-title":"Reinforcement Learning and Optimal Control","year":"2019","author":"Bertsekas","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2018.09.005"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2023.3235967"},{"volume-title":"Reinforcement Learning, Second Edition: An Introduction","year":"2018","author":"Sutton","key":"ref13"},{"key":"ref14","first-page":"1467","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","volume-title":"International Conference on Machine Learning","author":"Fazel"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-042920-020021"},{"key":"ref16","article-title":"Provably Global Convergence of Actor-Critic: A Case for Linear Quadratic Regulator with Ergodic Cost","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Yang","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1137\/20M1347942"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2023.3234176"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2021.109689"},{"article-title":"Reinforcement learning based optimal control with a probabilistic risk constraint","year":"2023","author":"Naha","key":"ref20"},{"key":"ref21","article-title":"Towards Generalization and Simplicity in Continuous Control","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Rajeswaran","year":"2017"},{"key":"ref22","article-title":"A natural policy gradient","volume":"14","author":"Kakade","year":"2001","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"article-title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","year":"2018","author":"Schulman","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2023.3234176"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2009.2029300"},{"article-title":"Policy gradient-based model free optimal lqg control with a probabilistic risk constraint","volume-title":"Submitted to IEEE ECC 2025","author":"Naha","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1006\/jmaa.1994.1475"}],"event":{"name":"2025 European Control Conference (ECC)","start":{"date-parts":[[2025,6,24]]},"location":"Thessaloniki, Greece","end":{"date-parts":[[2025,6,27]]}},"container-title":["2025 European Control Conference (ECC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11186289\/11186290\/11186950.pdf?arnumber=11186950","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T06:16:01Z","timestamp":1760508961000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11186950\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,24]]},"references-count":28,"URL":"https:\/\/doi.org\/10.23919\/ecc65951.2025.11186950","relation":{},"subject":[],"published":{"date-parts":[[2025,6,24]]}}}