{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T17:51:28Z","timestamp":1775325088857,"version":"3.50.1"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"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. Ind. Inf."],"published-print":{"date-parts":[[2019,8]]},"DOI":"10.1109\/tii.2019.2917520","type":"journal-article","created":{"date-parts":[[2019,5,17]],"date-time":"2019-05-17T20:11:01Z","timestamp":1558123861000},"page":"4442-4454","source":"Crossref","is-referenced-by-count":13,"title":["Modeling and Planning Under Uncertainty Using Deep Neural Networks"],"prefix":"10.1109","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8686-4752","authenticated-orcid":false,"given":"Daniel L.","family":"Marino","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1484-7678","authenticated-orcid":false,"given":"Milos","family":"Manic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","author":"petersen","year":"2008","journal-title":"The Matrix Cookbook"},{"key":"ref33","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","author":"pascanu","year":"0","journal-title":"Proc 30th Int Conf Mach Learn"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/5.58337"},{"key":"ref31","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Int Conf on Learning Representations"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2017.8280935"},{"key":"ref37","author":"coumans","year":"2016","journal-title":"Pybullet a python module for physics simulation for games robotics and machine learning"},{"key":"ref36","article-title":"Openai gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2754540"},{"key":"ref34","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"0","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref11","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":"ref12","article-title":"Emergence of locomotion behaviours in rich environments","author":"heess","year":"2017","journal-title":"arXiv 1707 02286"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2730846"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IECON.2016.7793413"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2017.2774777"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2683528"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2016.2627020"},{"key":"ref18","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"Int Conf on Learning Representations"},{"key":"ref19","first-page":"1","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref28","first-page":"1050","article-title":"Dropout as a Bayesian approximation: Representing model uncertainty in deep learning","author":"gal","year":"0","journal-title":"Proc 33nd Int Conf Mach Learn"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2765398"},{"key":"ref27","author":"murphy","year":"2012","journal-title":"Machine Learning A Probabilistic Perspective"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.218"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2016.2612646"},{"key":"ref29","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"0","journal-title":"Int Conf on Learning Representations"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2684820"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2725899"},{"key":"ref2","article-title":"Underactuated robotics: Algorithms for walking, running, swimming, flying, and manipulation","author":"tedrake","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/RWEEK.2017.8088655"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2009.V.003"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2712743"},{"key":"ref22","article-title":"Improving PILCO with Bayesian neural network dynamics models","author":"gal","year":"0","journal-title":"Proc Data-Efficient Machine Learning Workshop in ICML"},{"key":"ref21","first-page":"3680","article-title":"Variational Gaussian process state-space models","author":"frigola","year":"0","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref24","first-page":"1","article-title":"Learning scalable deep kernels with recurrent structure","volume":"18","author":"al-shedivat","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref23","article-title":"Uncertainty-aware reinforcement learning for collision avoidance","author":"kahn","year":"2017","journal-title":"arXiv 1702 01182"},{"key":"ref26","article-title":"Learning multimodal transition dynamics for model-based reinforcement learning","author":"moerland","year":"2017","journal-title":"arXiv 1705 00470"},{"key":"ref25","article-title":"Learning and policy search in stochastic dynamical systems with Bayesian neural networks","author":"depeweg","year":"0","journal-title":"Int Conf on Learning Representations"}],"container-title":["IEEE Transactions on Industrial Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9424\/8789761\/08717678.pdf?arnumber=8717678","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:42:54Z","timestamp":1657744974000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8717678\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":38,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tii.2019.2917520","relation":{},"ISSN":["1551-3203","1941-0050"],"issn-type":[{"value":"1551-3203","type":"print"},{"value":"1941-0050","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,8]]}}}