{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:18:13Z","timestamp":1730229493877,"version":"3.28.0"},"reference-count":19,"publisher":"Nanyang Technological Univ","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1109\/icarcv.2002.1235026","type":"proceedings-article","created":{"date-parts":[[2004,1,23]],"date-time":"2004-01-23T23:33:03Z","timestamp":1074900783000},"page":"1670-1675","source":"Crossref","is-referenced-by-count":0,"title":["Machine control using radial basis value functions and inverse state projection"],"prefix":"10.1109","volume":"3","author":[{"given":"S.","family":"Buck","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"F.","family":"Stulp","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M.","family":"Beetz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"T.","family":"Schmitt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Reinforcement Learning Aircraft","author":"perez-uribe","year":"1997","journal-title":"Au-tolander Logic Systems Laboratory Swiss Federal Insuuue or Technology-Lausanne"},{"journal-title":"A theory of networks for approrimulion and'learning AI)Memo No 11 10 MIT AI Laborauory","year":"1989","author":"poggio","key":"ref11"},{"key":"ref12","article-title":"Radial basis functions for multivariale inlerpolalion","author":"powell","year":"1985","journal-title":"A review Proc of the conference on algo for the approximation of functions and data"},{"key":"ref13","article-title":"A direct adaptive method for faster backpropagalion leaming: the Rprop algorithm","author":"riedmiller","year":"1993","journal-title":"Proceedings of the ICNN"},{"key":"ref14","first-page":"903","article-title":"Praclical Reinforcemenl Learning in Continuous Spaces","author":"smart","year":"2000","journal-title":"Proc Seventh Int Conf Machine Learning"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref15"},{"key":"ref16","article-title":"Continuous Valued Q-learning Method Able to Incrementally Re-fmeSlate Space","author":"takeda","year":"2001","journal-title":"Proc IEEE Int Conf Intell Robot Syst"},{"key":"ref17","first-page":"255","article-title":"Issues in Using Function Approximation for Reinforcement Learning","author":"thrun","year":"1993","journal-title":"Proceedings of the Connectionist Models Summer School"},{"key":"ref18","first-page":"279","volume":"8","author":"watkins","year":"1992","journal-title":"Q-learning Mach Learn"},{"key":"ref19","first-page":"67","author":"werbos","year":"1990","journal-title":"A menu of designs for reinforccment learning over time In Neural Jet-works for Control"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015961"},{"journal-title":"Approximaling the Value Function for Continuous Space Reinforcement Learning in Robol Control Submitted to IEEE\/RSJ IROS","year":"2002","author":"buck","key":"ref3"},{"journal-title":"Introduction to the Theory of Neural Computing","year":"1991","author":"hertz","key":"ref6"},{"key":"ref5","article-title":"Real-lime reinfocemenl leaming in continuous domains","author":"forbes","year":"2000","journal-title":"AAAI Spring Symposium on Real-Time Autonomous Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.281"},{"key":"ref7","article-title":"Module Based Reinforcemenl Learning for a Real Robot","author":"kalmar","year":"1998","journal-title":"Proceedings of the 6th European Workshop on Learning Robots Lecture Notes in AI"},{"key":"ref2","article-title":"Generalizalion in Reinforcement Learning: Safely approximating the value function","author":"boyan","year":"1995","journal-title":"Advances in Neural Information Processing Systems 7 (SIPS)"},{"journal-title":"Neuro-Dynamic Programming","year":"1996","author":"bertsekas","key":"ref1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993591"}],"event":{"name":"ICARV 2002: The Seventh International Conference on Control, Automation, Robotics and Vision","acronym":"ICARCV-02","location":"Singapore"},"container-title":["7th International Conference on Control, Automation, Robotics and Vision, 2002. ICARCV 2002."],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/8741\/27684\/01235026.pdf?arnumber=1235026","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,13]],"date-time":"2017-03-13T13:23:25Z","timestamp":1489411405000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/1235026\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icarcv.2002.1235026","relation":{},"subject":[]}}