{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T16:00:21Z","timestamp":1759334421515,"version":"build-2065373602"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T00:00:00Z","timestamp":1752624000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T00:00:00Z","timestamp":1752624000000},"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":[[2025,7,16]]},"DOI":"10.1109\/qrs65678.2025.00029","type":"proceedings-article","created":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T17:51:28Z","timestamp":1759168288000},"page":"189-198","source":"Crossref","is-referenced-by-count":0,"title":["Towards Fault-Tolerant Deep Reinforcement Learning Systems: A Framework Based on N-Version Programming"],"prefix":"10.1109","author":[{"given":"Wenting","family":"Yang","sequence":"first","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhuan","family":"Fan","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohui","family":"Wan","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1016\/j.jss.2024.111963"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1016\/j.sysarc.2022.102701"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/TSE.2023.3269804"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1016\/j.jss.2024.112016"},{"key":"ref5","first-page":"23","article-title":"The methodology of n-version programming","volume":"3","author":"Avizienis","year":"1995","journal-title":"Software fault tolerance"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1038\/nature14539"},{"key":"ref7","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv preprint"},{"key":"ref8","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"International conference on machine learning","author":"Fujimoto"},{"key":"ref9","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"},{"key":"ref10","first-page":"5556","article-title":"Controlling overestimation bias with truncated mixture of continuous distributional quantile critics","volume-title":"International Conference on Machine Learning","author":"Kuznetsov"},{"key":"ref11","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.5220\/0010199005800588"},{"key":"ref13","article-title":"Ensembles for continuous actions in reinforcement learning","author":"Duell","year":"2013","journal-title":"ESANN"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/DSN-W.2019.00016"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/DSN-W58399.2023.00044"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/PRDC47002.2019.00058"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/DSC54232.2022.9888825"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1145\/3448891.3448936"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/QRS54544.2021.00118"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.3233\/JIFS-179677"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/TCAD.2021.3129114"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/ETS56758.2023.10174178"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/SOCC52499.2021.9739383"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.23919\/DATE56975.2023.10137033"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1145\/3533767.3534388"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1145\/3721978"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1016\/j.asoc.2021.107295"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1145\/3631970"}],"event":{"name":"2025 25th International Conference on Software Quality, Reliability and Security (QRS)","start":{"date-parts":[[2025,7,16]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,7,20]]}},"container-title":["2025 25th International Conference on Software Quality, Reliability and Security (QRS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11173421\/11173424\/11173277.pdf?arnumber=11173277","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T16:06:09Z","timestamp":1759248369000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11173277\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,16]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/qrs65678.2025.00029","relation":{},"subject":[],"published":{"date-parts":[[2025,7,16]]}}}