{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T14:03:36Z","timestamp":1756994616061,"version":"3.28.0"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9197058","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T21:25:46Z","timestamp":1600205146000},"page":"5094-5100","source":"Crossref","is-referenced-by-count":8,"title":["Local Policy Optimization for Trajectory-Centric Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Patrik","family":"Kolaric","sequence":"first","affiliation":[]},{"given":"Devesh K.","family":"Jha","sequence":"additional","affiliation":[]},{"given":"Arvind U.","family":"Raghunathan","sequence":"additional","affiliation":[]},{"given":"Frank L.","family":"Lewis","sequence":"additional","affiliation":[]},{"given":"Mouhacine","family":"Benosman","sequence":"additional","affiliation":[]},{"given":"Diego","family":"Romeres","sequence":"additional","affiliation":[]},{"given":"Daniel","family":"Nikovski","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794229"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910369189"},{"key":"ref12","first-page":"arxiv:1907.02057","article-title":"Benchmarking Model-Based Reinforcement Learning","author":"wang","year":"2019","journal-title":"ArXiv e-prints"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/BF00925746"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386025"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1561\/2200000016"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989384"},{"key":"ref17","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":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6631149"},{"key":"ref28","article-title":"Local trajectory stabilization for dexterous manipulation via piecewise affine approximations","author":"han","year":"2019","journal-title":"ArXiv e-prints"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2017.8285376"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref6","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)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2015.7172127"},{"key":"ref8","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":"ref7","first-page":"1","article-title":"Guided policy search","author":"levine","year":"0"},{"journal-title":"Optimal Adaptive Control and Differential Games by Reinforcement Learning Principles","year":"2013","author":"vrabie","key":"ref2"},{"key":"ref9","first-page":"63","article-title":"Gaussian processes in machine learning","author":"rasmussen","year":"2003","journal-title":"Machine Learning Summer School"},{"key":"ref1","volume":"1","author":"sutton","year":"2018","journal-title":"Reinforcement learning An introduction (2nd Edition)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8815325"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.23919\/ECC.2019.8795815"},{"key":"ref21","article-title":"Safe approximate dynamic programming via kernelized lipschitz estimation","author":"chakrabarty","year":"2019","journal-title":"arXiv preprint arXiv 1907 09977"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989202"},{"key":"ref23","first-page":"3137","article-title":"A generalized path integral control approach to reinforcement learning","volume":"11","author":"theodorou","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"ref26","volume":"ii","author":"facchinei","year":"2003","journal-title":"Finite-Dimensional Variational Inequalities and Complementarity Problems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/sj.jors.2600425"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2020,5,31]]},"location":"Paris, France","end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09197058.pdf?arnumber=9197058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T00:11:27Z","timestamp":1656375087000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9197058\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9197058","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}