{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T12:24:36Z","timestamp":1783427076471,"version":"3.54.6"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"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":["IEEE Trans. Robot."],"published-print":{"date-parts":[[2022,12]]},"DOI":"10.1109\/tro.2022.3184837","type":"journal-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T19:33:08Z","timestamp":1657654388000},"page":"3879-3898","source":"Crossref","is-referenced-by-count":27,"title":["Model-Based Policy Search Using Monte Carlo Gradient Estimation With Real Systems Application"],"prefix":"10.1109","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0866-2952","authenticated-orcid":false,"given":"Fabio","family":"Amadio","sequence":"first","affiliation":[{"name":"Deptartment of Information Engineering, University of Padova, Padova, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7656-7797","authenticated-orcid":false,"given":"Alberto","family":"Dalla Libera","sequence":"additional","affiliation":[{"name":"Deptartment of Information Engineering, University of Padova, Padova, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4221-2004","authenticated-orcid":false,"given":"Riccardo","family":"Antonello","sequence":"additional","affiliation":[{"name":"Deptartment of Information Engineering, University of Padova, Padova, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2919-645X","authenticated-orcid":false,"given":"Daniel","family":"Nikovski","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6506-5898","authenticated-orcid":false,"given":"Ruggero","family":"Carli","sequence":"additional","affiliation":[{"name":"Deptartment of Information Engineering, University of Padova, Padova, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8603-2438","authenticated-orcid":false,"given":"Diego","family":"Romeres","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","author":"neuh\u00e4user","year":"2011","journal-title":"Wilcoxon-Mann-Whitney test"},{"key":"ref38","article-title":"Automatic differentiation in PyTorch","author":"paszke","year":"0","journal-title":"Proc Neural Inf Process Syst Workshop Autodiff"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/089976602317250933"},{"key":"ref32","first-page":"1935","article-title":"A unifying view of sparse approximate Gaussian process regression","volume":"6","author":"candela","year":"2005","journal-title":"J Mach Learn Res"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.218"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.179"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2005.863042"},{"key":"ref36","first-page":"1050","article-title":"Dropout as a Bayesian approximation: Representing model uncertainty in deep learning","author":"gal","year":"0","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref35","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc 3rd Int Conf Learn Representations"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492900002804"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794229"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1038\/156388a0"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7798708"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509858"},{"key":"ref13","first-page":"34","article-title":"Improving PILCO with Bayesian neural network dynamics models","author":"gal","year":"0","journal-title":"Proc Data-Efficient Mach Learn Workshop"},{"key":"ref14","article-title":"Bayesian methods for adaptive models","author":"mackay","year":"1992"},{"key":"ref15","first-page":"4754","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","author":"chua","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139550"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202137"},{"key":"ref18","article-title":"Nonlinear modelling and control using gaussian processes","author":"mchutchon","year":"2015"},{"key":"ref19","first-page":"406","article-title":"PEGASUS: A policy search method for large MDPs and POMDPs","author":"ng","year":"0","journal-title":"Proc Conf Uncertainty of Artificial Intelligence"},{"key":"ref28","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"0","journal-title":"Proc 14th Int Conf Artif Intell Statist"},{"key":"ref4","first-page":"751","article-title":"Gaussian processes in reinforcement learning","author":"rasmussen","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.123.170602"},{"key":"ref3","author":"williams","year":"2006","journal-title":"Gaussian Processes for Machine Learning"},{"key":"ref6","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"0","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref29","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref5","first-page":"908","article-title":"Safe model-based reinforcement learning with stability guarantees","author":"berkenkamp","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385955"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2011.VII.008"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1997.606886"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2945240"},{"key":"ref1","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref46","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"garc?a","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref20","first-page":"4065","article-title":"PIPPS: Flexible model-based policy search robust to the curse of chaos","author":"parmas","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2977255"},{"key":"ref22","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","author":"rezende","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref21","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"0","journal-title":"Proc 2nd Int Conf Learn Representations"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1155\/2011\/528341"},{"key":"ref24","first-page":"177","article-title":"Large-scale machine learning with stochastic gradient descent","author":"bottou","year":"0","journal-title":"Proc COMPSTAT"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref23","author":"rumelhart","year":"1988","journal-title":"Learning Representations by Back-propagating Errors"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2019.2891222"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1908636117"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"}],"container-title":["IEEE Transactions on Robotics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8860\/9970416\/09827590.pdf?arnumber=9827590","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:34:28Z","timestamp":1672083268000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9827590\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12]]},"references-count":46,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tro.2022.3184837","relation":{},"ISSN":["1552-3098","1941-0468"],"issn-type":[{"value":"1552-3098","type":"print"},{"value":"1941-0468","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12]]}}}