{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,29]],"date-time":"2025-03-29T16:17:25Z","timestamp":1743265045347,"version":"3.28.0"},"reference-count":15,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1109\/fuzz.2001.1009030","type":"proceedings-article","created":{"date-parts":[[2005,8,25]],"date-time":"2005-08-25T03:23:34Z","timestamp":1124940214000},"page":"618-621","source":"Crossref","is-referenced-by-count":6,"title":["On convergence of fuzzy reinforcement learning"],"prefix":"10.1109","volume":"3","author":[{"given":"H.R.","family":"Berenji","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"D.","family":"Vengerov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/FUZZY.1992.258720"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/0165-0114(88)90113-3"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.88.2.135"},{"key":"ref13","first-page":"1057","article-title":"Policy Gradient Methods for Reinforcement Learning with Function Approximation","volume":"12","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1985.6313399"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/FUZZY.1992.258721"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/0888-613X(92)90020-Z"},{"key":"ref3","article-title":"Reinforcement learning in POMDP's via direct gradient ascent","author":"baxter","year":"2000","journal-title":"Proceedings of the 17th International Conference on Machine Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/FUZZY.1999.793014"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/72.159061"},{"journal-title":"Neuro-Dynamic Proarammming","year":"1996","author":"bertsekas","key":"ref8"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/FUZZY.2000.839146"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"ref1","article-title":"Gradient descent for general reinforcement learning","volume":"11","author":"baird","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref9","article-title":"Actor-critic algorithms","volume":"12","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"}],"event":{"name":"10th Annual IEEE Conference on Fuzzy Systems","acronym":"FUZZY-01","location":"Melbourne, Vic., Australia"},"container-title":["10th IEEE International Conference on Fuzzy Systems. (Cat. No.01CH37297)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/7885\/21755\/01009030.pdf?arnumber=1009030","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,10]],"date-time":"2017-03-10T16:40:42Z","timestamp":1489164042000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/1009030\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/fuzz.2001.1009030","relation":{},"subject":[]}}