{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T22:12:51Z","timestamp":1740175971265,"version":"3.37.3"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2018,4,1]],"date-time":"2018-04-01T00:00:00Z","timestamp":1522540800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1109\/lra.2018.2798279","type":"journal-article","created":{"date-parts":[[2018,1,25]],"date-time":"2018-01-25T19:16:41Z","timestamp":1516907801000},"page":"1330-1337","source":"Crossref","is-referenced-by-count":1,"title":["Approximate Value Iteration Based on Numerical Quadrature"],"prefix":"10.1109","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1942-2812","authenticated-orcid":false,"given":"Julia","family":"Vinogradska","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8604-8432","authenticated-orcid":false,"given":"Bastian","family":"Bischoff","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5266-8091","authenticated-orcid":false,"given":"Jan","family":"Peters","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993591"},{"key":"ref33","first-page":"529","article-title":"Gaussian process\n priors with uncertain inputs—Application to multiple-step ahead time series forecasting","author":"girard","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","first-page":"1340","article-title":"Value pursuit iteration","author":"farahmand","year":"0","journal-title":"Proc 25th Int Conf Neural Inf Process Syst"},{"key":"ref31","first-page":"1391","article-title":"Greedy algorithms for sparse reinforcement learning","author":"painter-wakefield","year":"0","journal-title":"Proc 29th Int Conf Mach Learn"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143901"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10444-004-1812-x"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.jeconom.2007.12.004"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.2298\/FIL1406281M"},{"journal-title":"Gaussian Processes for Machine Learning","year":"2005","author":"rasmussen","key":"ref34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993104"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"ref12","first-page":"1047","article-title":"Exploiting model uncertainty estimates for safe dynamic control\n learning","author":"schneider","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ECC.2016.7810630"},{"key":"ref14","first-page":"545","article-title":"Stability of controllers for gaussian process forward models","author":"vinogradska","year":"0","journal-title":"Proc 33nd Int Conf Mach Learn"},{"journal-title":"Neuro-Dynamic Programming","year":"1996","author":"bertsekas","key":"ref15"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref16"},{"key":"ref17","volume":"1","author":"bertsekas","year":"2005","journal-title":"Dynamic Programming and Optimal Control"},{"journal-title":"Multivariable Feedback Control Analysis and Design","year":"2005","author":"skogestad","key":"ref18"},{"journal-title":"Essentials of Robust Control","year":"1998","author":"zhou","key":"ref19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SysTol.2013.6693820"},{"key":"ref27","first-page":"317","article-title":"Neural fitted q iteration—First experiences with a data\n efficient neural reinforcement learning method","author":"riedmiller","year":"0","journal-title":"Proc 16th Eur Conf Mach Learn"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/Allerton.2013.6736564"},{"key":"ref6","first-page":"347","article-title":"Learning to control an octopus arm with gaussian process temporal difference methods","author":"engel","year":"2006","journal-title":"Proc"},{"key":"ref29","first-page":"1107","article-title":"Least-squares policy iteration","volume":"4","author":"lagoudakis","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10339-011-0404-1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1997.606886"},{"key":"ref7","first-page":"2214","article-title":"Gaussian process model based predictive\n control","volume":"3","author":"kocijan","year":"0","journal-title":"Proc IEEE Amer Control Conf"},{"key":"ref2","first-page":"1907","article-title":"Probabilistic differential dynamic programming","author":"pan","year":"0","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref9","first-page":"1","article-title":"Model-based reinforcement learning with an approximate, learned\n model","author":"kuvayev","year":"0","journal-title":"Proc 9th Yale Workshop on Adaptive and Learning Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.218"},{"journal-title":"Stable Adaptive Systems","year":"2012","author":"narendra","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.11.005"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1002\/0471459100"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152660"},{"key":"ref23","first-page":"751","article-title":"Gaussian processes in reinforcement learning","author":"rasmussen","year":"0","journal-title":"Proc Adv Neur Inf Process Syst"},{"key":"ref26","first-page":"209","article-title":"Learning control under uncertainty: A\n probabilistic value-iteration approach","author":"bischoff","year":"0","journal-title":"Proc Eur Symp Artif Neural Netw"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2008.12.019"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7083369\/8214927\/08269312.pdf?arnumber=8269312","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:17:05Z","timestamp":1642004225000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8269312\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4]]},"references-count":38,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/lra.2018.2798279","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"type":"electronic","value":"2377-3766"},{"type":"electronic","value":"2377-3774"}],"subject":[],"published":{"date-parts":[[2018,4]]}}}