{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T13:25:49Z","timestamp":1756992349075,"version":"3.28.0"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"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":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561223","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"5906-5913","source":"Crossref","is-referenced-by-count":9,"title":["Reinforced iLQR: A Sample-Efficient Robot Locomotion Learning"],"prefix":"10.1109","author":[{"given":"Tongyu","family":"Zong","sequence":"first","affiliation":[{"name":"New York University,Tandon School of Engineering,Electrical and Computer Engineering Department,Brooklyn,NY,USA,11201"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liyang","family":"Sun","sequence":"additional","affiliation":[{"name":"New York University,Tandon School of Engineering,Electrical and Computer Engineering Department,Brooklyn,NY,USA,11201"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Liu","sequence":"additional","affiliation":[{"name":"New York University,Tandon School of Engineering,Electrical and Computer Engineering Department,Brooklyn,NY,USA,11201"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"When to trust your model: Model-based policy optimization","year":"2019","author":"janner","key":"ref39"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2013.6614995"},{"key":"ref33","first-page":"2944","article-title":"Learning continuous control policies by stochastic value gradients","author":"heess","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989384"},{"key":"ref31","first-page":"49","article-title":"Guided cost learning: Deep inverse optimal control via policy optimization","author":"finn","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref30","first-page":"4008","article-title":"Guided policy search via approximate mirror descent","author":"montgomery","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref37","first-page":"1","article-title":"Data efficient reinforcement learning for legged robots","author":"yang","year":"2020","journal-title":"Conference on Robot Learning"},{"key":"ref36","first-page":"4754","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","author":"chua","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref34","article-title":"Robust constrained model predictive control","author":"richards","year":"2005","journal-title":"Ph D Dissertation"},{"article-title":"Model-ensemble trust-region policy optimization","year":"2018","author":"kurutach","key":"ref10"},{"key":"ref40","first-page":"840","article-title":"Information theoretic model predictive q-learning","author":"bhardwaj","year":"2020","journal-title":"Learning for Dynamics and Control"},{"article-title":"Algorithmic framework for model-based deep reinforcement learning with theoretical guarantees","year":"2018","author":"luo","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2005.1469949"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386025"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"73","DOI":"10.7551\/mitpress\/9481.003.0015","article-title":"Infinite-horizon model predictive control for periodic tasks with contacts","author":"erez","year":"2012","journal-title":"Robotics Science and Systems VII"},{"key":"ref16","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning"},{"article-title":"Emergence of locomotion behaviours in rich environments","year":"2017","author":"heess","key":"ref17"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref18"},{"article-title":"Addressing function approximation error in actor-critic methods","year":"2018","author":"fujimoto","key":"ref19"},{"key":"ref28","first-page":"1","article-title":"Guided policy search","author":"levine","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(01)00174-1"},{"key":"ref27","first-page":"1701","article-title":"Data-efficient reinforcement learning with probabilistic model predictive control","author":"kamthe","year":"2018","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"ref3","article-title":"Walking human trajectory models and their application to humanoid robot locomotion","author":"maroger","year":"2020","journal-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073602"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487175"},{"journal-title":"Model Predictive Control","year":"2013","author":"camacho","key":"ref5"},{"article-title":"Learning to walk via deep reinforcement learning","year":"2018","author":"haarnoja","key":"ref8"},{"key":"ref7","first-page":"1","article-title":"Terrain-adaptive loco-motion skills using deep reinforcement learning","volume":"35","author":"peng","year":"2016","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2017.2783371"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref9"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-015-9479-3"},{"article-title":"Variance reduction for policy gradient with action-dependent factorized baselines","year":"2018","author":"wu","key":"ref46"},{"article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","year":"2018","author":"haarnoja","key":"ref20"},{"article-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref45"},{"article-title":"Benchmarking model-based reinforcement learning","year":"2019","author":"langlois","key":"ref48"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"article-title":"Openai gym","year":"2016","author":"brockman","key":"ref47"},{"article-title":"Model-based reinforcement learning via meta-policy optimization","year":"2018","author":"clavera","key":"ref21"},{"article-title":"Plan online, learn offline: Efficient learning and exploration via model-based control","year":"2018","author":"lowrey","key":"ref42"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-200-7.50073-8"},{"key":"ref41","first-page":"703","article-title":"Combining model-based and model-free updates for trajectory-centric reinforcement learning","author":"chebotar","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.jprocont.2012.12.012"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.218"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794352"},{"key":"ref25","first-page":"465","article-title":"Pilco: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"Proceedings of the 28th International Conference on Machine Learning (ICML-11)"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2021,5,30]]},"location":"Xi'an, China","end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09561223.pdf?arnumber=9561223","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,11]],"date-time":"2023-11-11T11:35:11Z","timestamp":1699702511000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561223\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561223","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}