{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T05:17:04Z","timestamp":1735276624477,"version":"3.32.0"},"reference-count":27,"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\/iros58592.2024.10801717","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"11969-11976","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Trajectory Database Learning for Nonlinear Control with Hybrid Gradient Optimization"],"prefix":"10.1109","author":[{"given":"Kuan-Yu","family":"Tseng","sequence":"first","affiliation":[{"name":"University of Illinois at Urbana–Champaign,Department of Mechanical Science and Engineering,Urbana,IL,USA,61801"}]},{"given":"Mengchao","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana–Champaign,Department of Mechanical Science and Engineering,Urbana,IL,USA,61801"}]},{"given":"Kris","family":"Hauser","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana-Champaign,Department of Computer Science,Urbana,IL,USA,61801"}]},{"given":"Geir E.","family":"Dullerud","sequence":"additional","affiliation":[{"name":"University of Illinois at Urbana–Champaign,Department of Mechanical Science and Engineering,Urbana,IL,USA,61801"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.32657\/10356\/90191"},{"key":"ref2","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"},{"year":"2017","author":"Schulman","article-title":"Proximal policy optimization algorithms","key":"ref3"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1002\/rob.21587"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/TCST.2019.2949757"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/MCS.2006.1636313"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.23919\/ACC53348.2022.9867601"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1007\/s42064-019-0051-3"},{"key":"ref9","volume-title":"Model predictive control: theory, computation, and design","volume":"2","author":"Rawlings","year":"2017"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/TCST.2019.2948135"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1007\/s10514-012-9283-2"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/TAC.2020.2986211"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1126\/scirobotics.aau5872"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/ICRA48506.2021.9562079"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/ICRA.2018.8460528"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/SSCI47803.2020.9308468"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/IROS.2017.8202133"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/ICRA48506.2021.9561982"},{"key":"ref19","first-page":"262","article-title":"Sim-to-real robot learning from pixels with progressive nets","volume-title":"Conference on robot learning","author":"Rusu"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.15607\/RSS.2017.XIII.048"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/ICRA.2019.8793789"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1073\/pnas.1611835114"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1561\/2200000019"},{"issue":"268","key":"ref24","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume-title":"Journal of Machine Learning Research","volume":"22","author":"Raffin","year":"2021"},{"year":"2023","author":"Towers","article-title":"Gymnasium","key":"ref25"},{"key":"ref26","first-page":"4045","article-title":"Time limits in reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Pardo"},{"key":"ref27","first-page":"1634","article-title":"Smooth exploration for robotic reinforcement learning","volume-title":"Conference on Robot Learning","author":"Raffin"}],"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\/10801717.pdf?arnumber=10801717","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:38:19Z","timestamp":1735198699000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10801717\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10801717","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}