{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:15:07Z","timestamp":1771956907020,"version":"3.50.1"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,10,24]]},"DOI":"10.1109\/iros45743.2020.9340823","type":"proceedings-article","created":{"date-parts":[[2021,3,15]],"date-time":"2021-03-15T14:49:56Z","timestamp":1615819796000},"page":"7629-7636","source":"Crossref","is-referenced-by-count":27,"title":["Learning High-Level Policies for Model Predictive Control"],"prefix":"10.1109","author":[{"given":"Yunlong","family":"Song","sequence":"first","affiliation":[]},{"given":"Davide","family":"Scaramuzza","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2720851"},{"key":"ref11","first-page":"1861","article-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","volume":"80","author":"haarnoja","year":"0"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487277"},{"key":"ref13","first-page":"1","article-title":"Guided Policy Search","volume":"28","author":"levine","year":"0"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487175"},{"key":"ref15","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793631"},{"key":"ref17","first-page":"133","article-title":"Aggressive Deep Driving: Combining Convolutional Neural Networks and Model Predictive Control","volume":"78","author":"drews","year":"0"},{"key":"ref18","article-title":"BADGR: An Autonomous Self-Supervised Learning-Based Navigation System","author":"kahn","year":"2020","journal-title":"arXiv preprint arXiv 2002 05155"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2942989"},{"key":"ref28","article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","author":"abadi","year":"2015"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"3463","DOI":"10.1016\/j.ifacol.2017.08.849","article-title":"Linear vs nonlinear MPC for trajectory tracking applied to rotary wing micro aerial vehicles","volume":"50","author":"kamel","year":"2017","journal-title":"IFAC-PapersOnLine"},{"key":"ref27","article-title":"CasADi: a software framework for nonlinear optimization and optimal control","volume":"11","author":"andersson","year":"2018","journal-title":"Mathematical Programming Computation"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593739"},{"key":"ref6","first-page":"849","article-title":"Policy search for motor primitives in robotics","author":"kober","year":"2009","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989202"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2300000021","article-title":"A survey on policy search for robotics","volume":"2","author":"deisenroth","year":"2013","journal-title":"Foundations and Trends in Robotics"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273590"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2014.10.128"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref1","author":"rawlings","year":"2009","journal-title":"Model Predictive Control Theory and Design"},{"key":"ref20","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref22","first-page":"1","article-title":"Hierarchical Relative Entropy Policy Search","volume":"17","author":"daniel","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"ref21","article-title":"Path integral policy improvement with covariance matrix adaptation","author":"stulp","year":"2012","journal-title":"arXiv preprint arXiv 1206 4621"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5980409"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553512"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487274"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2479878"}],"event":{"name":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Las Vegas, NV, USA","start":{"date-parts":[[2020,10,24]]},"end":{"date-parts":[[2021,1,24]]}},"container-title":["2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9340668\/9340635\/09340823.pdf?arnumber=9340823","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:57:23Z","timestamp":1656453443000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9340823\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,24]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/iros45743.2020.9340823","relation":{},"subject":[],"published":{"date-parts":[[2020,10,24]]}}}