{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T08:49:18Z","timestamp":1767084558029,"version":"3.32.0"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"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":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10801464","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"603-610","source":"Crossref","is-referenced-by-count":3,"title":["Gradient-based Regularization for Action Smoothness in Robotic Control with Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"I","family":"Lee","sequence":"first","affiliation":[{"name":"National Yang Ming Chiao Tung University,Department of Computer Science,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hoang-Giang","family":"Cao","sequence":"additional","affiliation":[{"name":"Ming Chi University of Technology,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cong-Tinh","family":"Dao","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University,Department of Computer Science,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Cheng","family":"Chen","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University,Department of Computer Science,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"I-Chen","family":"Wu","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University,Department of Computer Science,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"MoJuCo - Gym Documentation","key":"ref1"},{"journal-title":"Distributed distributional deterministic policy gradients","year":"2018","author":"Barth-Maron","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342029"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.05.016"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16864"},{"key":"ref6","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"International Conference on Machine Learning","author":"Fujimoto"},{"key":"ref7","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proceedings of the 35th International Conference on Machine Learning","volume":"80","author":"Haarnoja"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2720851"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981812"},{"key":"ref10","article-title":"Flight Controller Synthesis Via Deep Reinforcement Learning","volume-title":"PhD thesis","author":"Koch","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561138"},{"journal-title":"Dota 2 with large scale deep reinforcement learning","year":"2019","author":"Berner","key":"ref13"},{"journal-title":"Lipschitz regularity of deep neural networks: analysis and efficient estimation","year":"2019","author":"Scaman","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref16","first-page":"32253","article-title":"LipsNet: A smooth and robust neural network with adaptive Lipschitz constant for high accuracy optimal control","volume-title":"Proceedings of the 40th International Conference on Machine Learning","volume":"202","author":"Song"},{"journal-title":"Deep-mind control suite","year":"2018","author":"Tassa","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref19","first-page":"29021","article-title":"Taac: Temporally abstract actor-critic for continuous control","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Yu"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2024,10,14]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10801464.pdf?arnumber=10801464","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:39:29Z","timestamp":1735198769000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10801464\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10801464","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}