{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T07:17:52Z","timestamp":1774595872972,"version":"3.50.1"},"reference-count":12,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T00:00:00Z","timestamp":1761436800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T00:00:00Z","timestamp":1761436800000},"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":[[2025,10,26]]},"DOI":"10.1109\/ieeeconf67917.2025.11443777","type":"proceedings-article","created":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T19:47:37Z","timestamp":1774554457000},"page":"1408-1412","source":"Crossref","is-referenced-by-count":0,"title":["Safe Policy Learning in Online Reinforcement Learning Using Augmented PPO and CMDPs for Robot Navigation"],"prefix":"10.1109","author":[{"given":"Zhongna","family":"Zhou","sequence":"first","affiliation":[{"name":"University of Missouri,Electrical Engineering and Computer Science Department,Columbia,MO,USA,65211"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"K.C.","family":"Ho","sequence":"additional","affiliation":[{"name":"University of Missouri,Electrical Engineering and Computer Science Department,Columbia,MO,USA,65211"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhao","family":"Sun","sequence":"additional","affiliation":[{"name":"Hampton University,Electrical and Computer Engineering Department,Hampton,VA,USA,23669"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Trevor","family":"Tran","sequence":"additional","affiliation":[{"name":"Hampton University,Electrical and Computer Engineering Department,Hampton,VA,USA,23669"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Constrained Policy Optimization","author":"Achiam","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8796030"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2024.100945"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SII55687.2023.10039301"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i15.33767"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/iros60139.2025.11246167"},{"key":"ref7","article-title":"Offline primal-dual reinforcement learning for linear MDPs","volume-title":"Proc. Int. Conf. Artif. Intell. Stat. (AISTATS), Proc. Mach. Learn. Res","volume":"238","author":"Gabbianelli"},{"key":"ref8","article-title":"Provably efficient safe exploration via primal\u2013dual policy optimization","volume-title":"Proc. Int. Conf. Artif. Intell. Stat. (AISTATS), Proc. Mach. Learn. Res","volume":"130","author":"Ding"},{"key":"ref9","article-title":"Mirror descent policy optimization","author":"Tomar","year":"2021"},{"key":"ref10","article-title":"Mirror learning: A unifying framework of policy optimisation","author":"Kuba","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3043163"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"}],"event":{"name":"2025 59th Asilomar Conference on Signals, Systems, and Computers","location":"Pacific Grove, CA, USA","start":{"date-parts":[[2025,10,26]]},"end":{"date-parts":[[2025,10,29]]}},"container-title":["2025 59th Asilomar Conference on Signals, Systems, and Computers"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443114\/11443296\/11443777.pdf?arnumber=11443777","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T05:50:27Z","timestamp":1774590627000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443777\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,26]]},"references-count":12,"URL":"https:\/\/doi.org\/10.1109\/ieeeconf67917.2025.11443777","relation":{},"subject":[],"published":{"date-parts":[[2025,10,26]]}}}