{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T18:30:07Z","timestamp":1729621807341,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1109\/cdc.2017.8264294","type":"proceedings-article","created":{"date-parts":[[2018,1,23]],"date-time":"2018-01-23T15:30:57Z","timestamp":1516721457000},"page":"4309-4314","source":"Crossref","is-referenced-by-count":6,"title":["Stochastic feedback control of systems with unknown nonlinear dynamics"],"prefix":"10.1109","author":[{"given":"Dan","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammadhussein","family":"Rafieisakhaei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Suman","family":"Chakravorty","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Adaptive Optimal Control The Thinking Man s GPC","year":"1991","author":"bithmead","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2012.03.004"},{"key":"ref12","article-title":"Learning Complex Neural Network Policies with Trajectory Optimization","author":"levine","year":"2014","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref13","article-title":"Model Free Trajectory Optimization for Reinforcement Learning","author":"akrour","year":"2016","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2009.4927530"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1613\/jair.806","article-title":"Infinite Horizon Policy-Gradient Estimation","volume":"15","author":"baxter","year":"2001","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref16","article-title":"Policy Gradient Methods for Reinforcement Learning with Function Approximation","author":"sutton","year":"1999","journal-title":"Proc 1999 Neural Information Proc Sys"},{"journal-title":"Simulation-based optimization of Markov reward processes","year":"1999","author":"marbach","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.2514\/1.45722"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1115\/1.3640537"},{"journal-title":"Differential Dynamic Programming","year":"1970","author":"jacobsen","key":"ref4"},{"journal-title":"Applied Optimal Control Optimization Estimation and Control","year":"1975","author":"bryson","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2005.1469949"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2010.5530971"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989080"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1080\/00207170701364913"},{"key":"ref2","article-title":"Recent Results in the Approximation of Nonlinear Optimal Control Problems","author":"falcone","year":"2013","journal-title":"Large-Scale Scientific Computing"},{"journal-title":"Dynamic Programming and Optimal Control Two","year":"1995","author":"bertsekas","key":"ref1"},{"key":"ref9","article-title":"A Near-Optimal Separation Principle for Nonlinear Stochastic Systems Arising in Robotic Path Planning and Control","author":"rafieisakhaei","year":"2017","journal-title":"56th IEEE Conference on Decision and Control (CDC)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-3766-0"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-014-0818-1"}],"event":{"name":"2017 IEEE 56th Annual Conference on Decision and Control (CDC)","start":{"date-parts":[[2017,12,12]]},"location":"Melbourne, Australia","end":{"date-parts":[[2017,12,15]]}},"container-title":["2017 IEEE 56th Annual Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8253407\/8263624\/08264294.pdf?arnumber=8264294","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,9]],"date-time":"2019-10-09T14:31:30Z","timestamp":1570631490000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8264294\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/cdc.2017.8264294","relation":{},"subject":[],"published":{"date-parts":[[2017,12]]}}}