{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T18:12:30Z","timestamp":1757614350708,"version":"3.44.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,1]]},"DOI":"10.1109\/rcar65431.2025.11139393","type":"proceedings-article","created":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T18:16:38Z","timestamp":1757009798000},"page":"7-12","source":"Crossref","is-referenced-by-count":0,"title":["Improving Stability and Efficiency of Reinforcement Learning using Reward Functions based on Lyapunov Neural Networks"],"prefix":"10.1109","author":[{"given":"Mingyu","family":"Sun","sequence":"first","affiliation":[{"name":"Southern University of Science and Technology,College of Engineering,China"}]},{"given":"Chenyang","family":"Miao","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Shenzhen Institutes of Advanced Technology,China"}]},{"given":"Yidong","family":"Chen","sequence":"additional","affiliation":[{"name":"Shenzhen ZHAOWEI Machinery & Electronics Co., Ltd,China"}]},{"given":"Tianfu","family":"Sun","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Shenzhen Institutes of Advanced Technology,China"}]},{"given":"Yunduan","family":"Cui","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Shenzhen Institutes of Advanced Technology,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120495"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2901791"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2021.3087787"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2020.110618"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2025.134585"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16156"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICNP49622.2020.9259378"},{"article-title":"Concrete problems in ai safety","year":"2016","author":"Amodei","key":"ref9"},{"key":"ref10","first-page":"22","article-title":"Constrained policy optimization","volume-title":"International Conference on Machine Learning","author":"Achiam"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/37.506394"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-010-0393-3"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/make4010013"},{"key":"ref14","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":"ref15","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"International Conference on Machine Learning","author":"Fujimoto"},{"article-title":"Randomized ensembled double q-learning: Learning fast without a model","volume-title":"International Conference on Learning Representations","author":"Chen","key":"ref16"},{"article-title":"Dropout q-functions for doubly efficient reinforcement learning","volume-title":"International Conference on Learning Representations","author":"Hiraoka","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3457538"},{"issue":"Dec","key":"ref19","first-page":"803","article-title":"Lyapunov design for safe reinforcement learning","volume":"3","author":"Perkins","year":"2002","journal-title":"Journal of Machine Learning Research"},{"key":"ref20","article-title":"A lyapunov-based approach to safe reinforcement learning","volume":"31","author":"Chow","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","first-page":"466","article-title":"The lyapunov neural network: Adaptive stability certification for safe learning of dynamical systems","volume-title":"Conference on Robot Learning","author":"Richards"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2020.xvi.088"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981632"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662604"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO55434.2022.10011834"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3492174"},{"article-title":"Safety gymnasium: A unified safe reinforcement learning benchmark","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Ji","key":"ref27"},{"key":"ref28","first-page":"326","article-title":"Adaptive primal-dual method for safe reinforcement learning","volume-title":"Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems","author":"Chen"}],"event":{"name":"2025 IEEE International Conference on Real-time Computing and Robotics (RCAR)","start":{"date-parts":[[2025,6,1]]},"location":"Toyama, Japan","end":{"date-parts":[[2025,6,6]]}},"container-title":["2025 IEEE International Conference on Real-time Computing and Robotics (RCAR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11139128\/11139096\/11139393.pdf?arnumber=11139393","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T06:09:25Z","timestamp":1757052565000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11139393\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,1]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/rcar65431.2025.11139393","relation":{},"subject":[],"published":{"date-parts":[[2025,6,1]]}}}