{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:44:25Z","timestamp":1782405865985,"version":"3.54.5"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T00:00:00Z","timestamp":1751932800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T00:00:00Z","timestamp":1751932800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000194","name":"U.S. Department of State","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000194","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,7,8]]},"DOI":"10.23919\/acc63710.2025.11107452","type":"proceedings-article","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:17:51Z","timestamp":1755800271000},"page":"180-187","source":"Crossref","is-referenced-by-count":1,"title":["Decomposing Control Lyapunov Functions for Efficient Reinforcement Learning"],"prefix":"10.23919","author":[{"given":"Antonio","family":"L\u00f3pez","sequence":"first","affiliation":[{"name":"University of Texas at Austin,Department of Aerospace Engineering and Engineering Mechanics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Fridovich-Keil","sequence":"additional","affiliation":[{"name":"University of Texas at Austin,Department of Aerospace Engineering and Engineering Mechanics"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asej.2020.11.005"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-08834-1"},{"key":"ref3","first-page":"4015","article-title":"On the importance of hyperparameter optimization for model-based reinforcement learning","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Zhang"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LCSYS.2022.3228728"},{"key":"ref5","article-title":"Data-efficient hierarchical reinforcement learning","volume":"31","author":"Nachum","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.011"},{"key":"ref7","first-page":"27395","article-title":"Policy finetuning: Bridging sample-efficient offline and online reinforcement learning","volume":"34","author":"Xie","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref8","author":"Franke","year":"2020","journal-title":"Sample-efficient automated deep reinforcement learning"},{"key":"ref9","article-title":"Model-based value expansion for efficient model-free reinforcement learning","volume-title":"Proceedings of the 35th International Conference on Machine Learning (ICML 2018)","author":"Feinberg"},{"key":"ref10","author":"Mukherjee","year":"2023","journal-title":"Bridging Physics-Informed Neural Networks with Reinforcement Learning: Hamilton-Jacobi-Bellman Proximal Policy Optimization (HJBPPO)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2025.112458"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.033"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2021.xvii.062"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794107"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.088"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967820"},{"key":"ref18","first-page":"803","article-title":"Lyapunov design for safe reinforcement learning","author":"Perkins","year":"2002","journal-title":"Journal of Machine Learning Research"},{"key":"ref19","first-page":"15931","article-title":"Learning to utilize shaping rewards: A new approach of reward shaping","volume":"33","author":"Hu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proceedings of the 16th International Conference on Machine Learning","author":"Ng"},{"key":"ref21","first-page":"433","article-title":"Dynamic potential-based reward shaping","volume-title":"Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems","author":"Devlin"},{"key":"ref22","author":"Grzes","year":"2017","journal-title":"Reward shaping in episodic reinforcement learning"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-015-9292-6"},{"key":"ref24","article-title":"Potential-based reward shaping for hierarchical reinforcement learning","volume-title":"Twenty-Fourth International Joint Conference on Artificial Intelligence","author":"Gao"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.218"},{"key":"ref26","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume":"31","author":"Chua","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8594018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-060117-104941"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8263977"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-31954-2_31"},{"key":"ref31","author":"Westenbroek","year":"2022","journal-title":"Lyapunov design for robust and efficient robotic reinforcement learning"},{"key":"ref32","author":"Haarnoja","year":"2018","journal-title":"Soft actor-critic algorithms and applications"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2797194"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref35","article-title":"Nonlinear Systems","author":"Khalil","year":"2002"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2015.7402390"},{"key":"ref37","author":"Brockman","year":"2016","journal-title":"Openai gym"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1997.606886"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21236\/ada572108"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9482751"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2025.01.005"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6911(89)90028-5"}],"event":{"name":"2025 American Control Conference (ACC)","location":"Denver, CO, USA","start":{"date-parts":[[2025,7,8]]},"end":{"date-parts":[[2025,7,10]]}},"container-title":["2025 American Control Conference (ACC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11107441\/11107442\/11107452.pdf?arnumber=11107452","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:24:18Z","timestamp":1755840258000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11107452\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,8]]},"references-count":42,"URL":"https:\/\/doi.org\/10.23919\/acc63710.2025.11107452","relation":{},"subject":[],"published":{"date-parts":[[2025,7,8]]}}}