{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T15:51:08Z","timestamp":1776441068580,"version":"3.51.2"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911NF-16-1-0390"],"award-info":[{"award-number":["W911NF-16-1-0390"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1426945"],"award-info":[{"award-number":["1426945"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute for Robotics and Intelligent Machines at Georgia Tech"},{"name":"A. S. Onassis Foundation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.1109\/tnnls.2017.2764499","type":"journal-article","created":{"date-parts":[[2018,3,5]],"date-time":"2018-03-05T19:13:46Z","timestamp":1520277226000},"page":"5459-5474","source":"Crossref","is-referenced-by-count":25,"title":["Efficient Reinforcement Learning via Probabilistic Trajectory Optimization"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3373-0769","authenticated-orcid":false,"given":"Yunpeng","family":"Pan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0930-3257","authenticated-orcid":false,"given":"George I.","family":"Boutselis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Evangelos A.","family":"Theodorou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/9.86943"},{"key":"ref38","author":"whittle","year":"1990","journal-title":"Risk-Sensitive Optimal Control"},{"key":"ref33","first-page":"545","article-title":"Stability of controllers for Gaussian process forward models","author":"vinogradska","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref32","first-page":"2314","article-title":"Sample efficient path integral control under uncertainty","author":"pan","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553403"},{"key":"ref30","article-title":"Gaussian process models for robust regression, classification, and reinforcement learning","author":"kuss","year":"2006"},{"key":"ref37","first-page":"35","article-title":"The cross-entropy method for optimization","volume":"31","author":"botev","year":"2013","journal-title":"Machine Learning Theory and Applications"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6943064"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385977"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1978.tb01643.x"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1202463"},{"key":"ref27","author":"williams","year":"2006","journal-title":"Gaussian Processes for Machine Learning"},{"key":"ref29","first-page":"545","article-title":"Gaussian process priors with uncertain inputs application to multiple-step ahead time series forecasting","author":"girard","year":"2003","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref2","first-page":"3137","article-title":"A generalized path integral control approach to reinforcement learning","volume":"11","author":"theodorou","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.02.003"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2012.2201261"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.218"},{"key":"ref21","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2319052"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2013.2258732"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2014.7010608"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2009.5354013"},{"key":"ref50","first-page":"473","article-title":"Motion planning under uncertainty using differential dynamic programming in belief space","author":"van den berg","year":"2011","journal-title":"Proc Int Symp Robot Res"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2003.1248926"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2017.7963531"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.2514\/6.2017-1525"},{"key":"ref56","first-page":"406","article-title":"PEGASUS: A policy search method for large MDPs and POMDPs","author":"ng","year":"2000","journal-title":"Proc 16th Conf Uncertainty Artif Intell"},{"key":"ref55","first-page":"2760","article-title":"Prediction under uncertainty in sparse spectrum Gaussian processes with applications to filtering and control","author":"pan","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref54","author":"pan","year":"2016","journal-title":"Adaptive probabilistic trajectory optimization via efficient approximate inference"},{"key":"ref53","first-page":"1865","article-title":"Sparse spectrum Gaussian process regression","volume":"11","author":"l\u00e1zaro-gredilla","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref52","first-page":"972","article-title":"Incremental local Gaussian regression","author":"meier","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2005.1469949"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2010.5530971"},{"key":"ref40","article-title":"Global convergence of differential dynamic programming and Newton’s method for discrete-time optimal control","author":"liao","year":"1996"},{"key":"ref12","first-page":"1465","article-title":"Receding horizon differential dynamic programming","author":"tassa","year":"2007","journal-title":"Proc NIPS"},{"key":"ref13","first-page":"1539","article-title":"Minimax differential dynamic programming: An application to robust biped walking","author":"morimoto","year":"2002","journal-title":"Proc NIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2015.XI.029"},{"key":"ref15","first-page":"1","article-title":"An application of reinforcement learning to aerobatic helicopter flight","volume":"19","author":"abbeel","year":"2007","journal-title":"Proc NIPS"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1007\/978-3-642-05181-4_4","article-title":"Adaptive optimal feedback control with learned internal dynamics models","author":"mitrovic","year":"2010","journal-title":"From Motor Learning to Interaction Learning in Robots"},{"key":"ref17","first-page":"1","article-title":"Gaussian processes in reinforcement learning","volume":"4","author":"rasmussen","year":"2004","journal-title":"Proc NIPS"},{"key":"ref18","first-page":"1193","article-title":"Local Gaussian process regression for real time online model learning","author":"nguyen-tuong","year":"2008","journal-title":"Proc NIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509858"},{"key":"ref4","first-page":"817","article-title":"Variational inference for policy search in changing situations","author":"neumann","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn (ICML)"},{"key":"ref3","first-page":"1","article-title":"Relative entropy policy search","author":"peters","year":"2010","journal-title":"Proc AAAI"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2300000021","article-title":"A survey on policy search for robotics","volume":"2","author":"deisenroth","year":"2013","journal-title":"Foundations and Trends in Robotics"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1997.606886"},{"key":"ref8","author":"barto","year":"2004","journal-title":"Handbook of Learning and Approximate Dynamic Programming"},{"key":"ref7","first-page":"15","volume":"7","author":"bertsekas","year":"1996","journal-title":"Neuro-Dynamic Programming"},{"key":"ref49","first-page":"1","article-title":"Gaussian process planning with Lipschitz continuous reward functions: Towards unifying Bayesian optimization, active learning, and beyond","author":"ling","year":"2016","journal-title":"Proc AAAI"},{"key":"ref9","author":"jacobson","year":"1970","journal-title":"Differential Dynamic Programming"},{"key":"ref46","first-page":"1257","article-title":"Sparse Gaussian processes using pseudo-inputs","volume":"18","author":"snelson","year":"2006","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1162\/089976602317250933"},{"key":"ref48","first-page":"739","article-title":"Nonmyopic \n$\\epsilon $\n-Bayes-optimal active learning of Gaussian processes","author":"hoang","year":"2014","journal-title":"Proc ICML"},{"key":"ref47","first-page":"1907","article-title":"Probabilistic differential dynamic programming","author":"pan","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912456319"},{"key":"ref41","author":"boutselis","year":"2017","journal-title":"Stochastic trajectory optimization for mechanical systems with parametric uncertainties"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1137\/0320018"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907001"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielaam\/5962385\/8495104\/8306829-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/8495104\/08306829.pdf?arnumber=8306829","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:53:09Z","timestamp":1649443989000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8306829\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":58,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2017.2764499","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,11]]}}}