{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T10:04:32Z","timestamp":1772791472856,"version":"3.50.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2011,2,1]],"date-time":"2011-02-01T00:00:00Z","timestamp":1296518400000},"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 Trans. Fuzzy Syst."],"published-print":{"date-parts":[[2011,2]]},"DOI":"10.1109\/tfuzz.2010.2081994","type":"journal-article","created":{"date-parts":[[2010,10,1]],"date-time":"2010-10-01T19:03:35Z","timestamp":1285959815000},"page":"51-64","source":"Crossref","is-referenced-by-count":31,"title":["Systems Control With Generalized Probabilistic Fuzzy-Reinforcement Learning"],"prefix":"10.1109","volume":"19","author":[{"given":"William M.","family":"Hinojosa","sequence":"first","affiliation":[]},{"given":"Samia","family":"Nefti","sequence":"additional","affiliation":[]},{"given":"Uzay","family":"Kaymak","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","author":"thrun","year":"0"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/0165-0114(94)00195-D"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/12.106218"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/91.273126"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2005.06.002"},{"key":"ref35","article-title":"vdcbpi: an approximate scalable algorithm for large pomdps","author":"poupart","year":"2004","journal-title":"Advances Neural Inform Process Syst"},{"key":"ref34","article-title":"point-based value iteration: an any time algorithm for pomdps","author":"pineau","year":"2003","journal-title":"Int Joint Conf Artif Intell"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/5326.704563"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S0165-0114(02)00299-3"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/72.501728"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1002\/isaf.293"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2007.03.012"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/70.68080"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2003.811201"},{"key":"ref17","article-title":"a new radial basis probabilistic neural network model","author":"deshuang","year":"1996","journal-title":"Int Conf Signal Processing"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.2307\/1269908"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/91.273123"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/37.24809"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-200-7.50097-0"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"ref27","article-title":"Tracking control of a peddulum-driven cart–pole underactuated system","author":"yu","year":"2007","journal-title":"IEEE Int Conf Syst Man Cybern"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1002\/int.4550060105"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/72.159061"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/FUZZY.1996.553542"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/0165-0114(94)00216-T"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/FUZZY.1993.327458"},{"key":"ref2","author":"bellman","year":"1957","journal-title":"Dynamic Programming"},{"key":"ref9","first-page":"54","article-title":"reinforcement learning for fuzzy control with linguistic states","volume":"2","author":"zarandi","year":"2008","journal-title":"J Uncertain Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijar.2003.08.007"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/91.493913"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/FUZZ.2002.1006639"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2005.859326"},{"key":"ref24","author":"baird","year":"1999","journal-title":"Reinforcement learning through gradient descent"},{"key":"ref23","article-title":"Testing stochastic processes through reinforcement learning","author":"laviolette","year":"2006","journal-title":"presented at the Workshop Testing Deployable Learn Decision Syst"},{"key":"ref26","first-page":"968","article-title":"gradient descent for general reinforcement learning","author":"baird","year":"1999","journal-title":"Proc Adv Neural Inf Process Syst II"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553501"}],"container-title":["IEEE Transactions on Fuzzy Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/91\/5705623\/05590288.pdf?arnumber=5590288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,11]],"date-time":"2021-10-11T00:47:40Z","timestamp":1633913260000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5590288\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,2]]},"references-count":36,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tfuzz.2010.2081994","relation":{},"ISSN":["1063-6706","1941-0034"],"issn-type":[{"value":"1063-6706","type":"print"},{"value":"1941-0034","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011,2]]}}}