{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:02:39Z","timestamp":1758268959541,"version":"3.28.0"},"reference-count":32,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/iros.2018.8594018","type":"proceedings-article","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T02:33:30Z","timestamp":1548297210000},"page":"2538-2544","source":"Crossref","is-referenced-by-count":7,"title":["Synthesizing Neural Network Controllers with Probabilistic Model-Based Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Juan Camilo","family":"Gamboa Higuera","sequence":"first","affiliation":[]},{"given":"David","family":"Meger","sequence":"additional","affiliation":[]},{"given":"Gregory","family":"Dudek","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref32","article-title":"Sparse spectrum gaussian process regression","author":"lazaro-gredilla","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"ref31","article-title":"Adam: A method for stochastic optimization","volume":"absi1412 6980","author":"kingma","year":"2014","journal-title":"CoRR"},{"key":"ref30","article-title":"On the difficulty of training recurrent neural networks","author":"pascanu","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"ref10","article-title":"Dynamics and trajectory optimization for a soft spatial fluidic elastomer manipulator","author":"marchese","year":"2015","journal-title":"International Journal of Robotics Research"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10339-011-0404-1"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-017-2053-3_3"},{"key":"ref13","article-title":"An application of reinforcement learning to aerobatic helicopter flight","author":"abbeel","year":"2006","journal-title":"Proceedings of Neural Information Processing Systems (NIPS)"},{"key":"ref14","first-page":"1071","article-title":"Learning neural network policies with guided policy search under unknown dynamics","author":"levine","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref15","article-title":"Continuous deep q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref16","article-title":"Learning continuous control policies by stochastic value gradients","author":"heess","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"Continuous control with deep reinforcement learning","volume":"abs 1509 2971","author":"lillicrap","year":"2015","journal-title":"CoRR"},{"key":"ref18","article-title":"MBMF: model-based priors for model-free reinforcement learning","volume":"absi1709 3153","author":"bansal","year":"2017","journal-title":"CoRR"},{"key":"ref19","article-title":"Probabilistic differential dynamic programming","author":"pan","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.45.11.1570"},{"key":"ref4","article-title":"Dropout: a simple way to prevent neural networks from overfitting","author":"srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref27","article-title":"Concrete dropout","author":"gal","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref3","article-title":"Improving PILCO with Bayesian neural network dynamics models","author":"gal","year":"2016","journal-title":"Data-Efficient Machine Learning workshop"},{"key":"ref6","article-title":"Structured bayesian pruning via log-normal multiplicative noise","author":"neklyudov","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref29","article-title":"Pegasus: A policy search method for large mdps and pomdps","author":"ng","year":"2000","journal-title":"Proceedings of the Sixteenth Conference on Uncertainty in Artificial Intelligence"},{"key":"ref5","article-title":"Dropout as a bayesian approximation: Representing model uncertainty in deep learning","author":"gal","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref8","article-title":"Iterative linear quadratic regulator design for nonlinear biological movement systems","author":"li","year":"2004","journal-title":"Proceedings of the 1st International Conference on Informatics in Control Automation and Robotics"},{"journal-title":"Differential Dynamic Programming","year":"1970","author":"jacobson","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139509"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907001"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.218"},{"key":"ref20","article-title":"GP-ILQG: data-driven robust optimal control for uncertain nonlinear dynamical systems","volume":"absi1705 5344","author":"lee","year":"2017","journal-title":"CoRR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1997.606886"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202137"},{"key":"ref24","article-title":"Weight uncertainty in neural network","author":"blundell","year":"2015","journal-title":"International Conference on Machine Learning"},{"journal-title":"Efficient Reinforcement Learning Using Gaussian Processes","year":"2010","author":"deisenroth","key":"ref23"},{"key":"ref26","article-title":"Variational dropout spar-sifies deep neural networks","author":"molchanov","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref25","article-title":"Variational dropout and the local reparameterization trick","author":"kingma","year":"2015","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2018,10,1]]},"location":"Madrid","end":{"date-parts":[[2018,10,5]]}},"container-title":["2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8574473\/8593358\/08594018.pdf?arnumber=8594018","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T04:17:12Z","timestamp":1598242632000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8594018\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/iros.2018.8594018","relation":{},"subject":[],"published":{"date-parts":[[2018,10]]}}}