{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T06:46:20Z","timestamp":1761806780139},"reference-count":31,"publisher":"Elsevier BV","issue":"3","license":[{"start":{"date-parts":[[1995,4,1]],"date-time":"1995-04-01T00:00:00Z","timestamp":796694400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[1995,4]]},"DOI":"10.1016\/0925-2312(94)00027-p","type":"journal-article","created":{"date-parts":[[2002,7,25]],"date-time":"2002-07-25T22:08:35Z","timestamp":1027634915000},"page":"275-297","source":"Crossref","is-referenced-by-count":59,"title":["A new approach to the design of reinforcement schemes for learning automata: Stochastic estimator learning algorithm"],"prefix":"10.1016","volume":"7","author":[{"given":"Athanasios V.","family":"Vasilakos","sequence":"first","affiliation":[]},{"given":"Georgios I.","family":"Papadimitriou","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/0925-2312(94)00027-P_BIB1","first-page":"24","article-title":"Discretized reward inaction learning automata","author":"Thathachar","year":"1979","journal-title":"J. Cybernet. Informat. Sci."},{"issue":"2","key":"10.1016\/0925-2312(94)00027-P_BIB2","first-page":"282","article-title":"Absorbing and ergodic discretized two-action learning automata","volume":"SMC-16","author":"Oommen","year":"1986","journal-title":"IEEE Trans. Systems Man Cybernet."},{"issue":"3","key":"10.1016\/0925-2312(94)00027-P_BIB3","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1109\/21.7494","article-title":"Epsilon-optimal discretized linear reward-penalty learning automata","volume":"SMC-18","author":"Oommen","year":"1988","journal-title":"IEEE Trans. Systems Man Cybernet."},{"key":"10.1016\/0925-2312(94)00027-P_BIB4","author":"Norman","year":"1972"},{"issue":"3\u20134","key":"10.1016\/0925-2312(94)00027-P_BIB5","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/0925-2312(92)90007-C","article-title":"Ergodic discretized estimator learning automata with high accuracy and high adaptation rate for nonstationary environments","volume":"4","author":"Vasilakos","year":"1992","journal-title":"Neurocomputing"},{"key":"10.1016\/0925-2312(94)00027-P_BIB6","series-title":"IEEE Int. Conf. Systems Man & Cyber","article-title":"New absorbing hierarchical discretized pursuit nonlinear learning automata with rapid convergence and high accuracy","author":"Vasilakos","year":"1991"},{"key":"10.1016\/0925-2312(94)00027-P_BIB7","series-title":"IEEE Int. Conf. on Systems, Man and Cybernetics","article-title":"A new nonlinear discretized learning automaton with rapid convergence and high accuracy","author":"Vasilakos","year":"1989"},{"key":"10.1016\/0925-2312(94)00027-P_BIB8","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1109\/TSMC.1973.5408585","article-title":"Stochastic automata models with applications to learning systems","author":"Viswanathan","year":"1973","journal-title":"IEEE Trans. Systems Man Cybernet."},{"issue":"2","key":"10.1016\/0925-2312(94)00027-P_BIB9","doi-asserted-by":"crossref","first-page":"388","DOI":"10.1109\/21.31041","article-title":"Relative reward strength algorithms for learning automata","volume":"SMC-19","author":"Simha","year":"1989","journal-title":"IEEE Trans. Systems Man Cybernet."},{"key":"10.1016\/0925-2312(94)00027-P_BIB10","series-title":"IEEE Int. Conf. Systems Man Cybernetics","article-title":"Epsilon-optimal discretized pursuit learning automata","author":"Oomen","year":"1989"},{"key":"10.1016\/0925-2312(94)00027-P_BIB11","first-page":"327","article-title":"On the behavior of stochastic automata with variable structure","volume":"24","author":"Varshavskii","year":"1963","journal-title":"Automat. Telemekh. (USSR)"},{"issue":"4","key":"10.1016\/0925-2312(94)00027-P_BIB12","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1109\/TSMC.1974.5408453","article-title":"Learning automata \u2014 A survey","volume":"SMC-4","author":"Narendra","year":"1974","journal-title":"IEEE Trans. Systems Man Cybernet."},{"key":"10.1016\/0925-2312(94)00027-P_BIB13","first-page":"53","article-title":"Learning automata: A critique","author":"Narendra","year":"1977","journal-title":"J. Cybernet. Informat. Sci."},{"issue":"1","key":"10.1016\/0925-2312(94)00027-P_BIB14","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1109\/TSMC.1985.6313407","article-title":"A class of rapidly converging algorithms for learning automata","volume":"SMC-15","author":"Thathachar","year":"1985","journal-title":"IEEE Trans. Systems Man Cybernet."},{"issue":"3","key":"10.1016\/0925-2312(94)00027-P_BIB15","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/0020-0255(85)90049-0","article-title":"Multiaction learning automata possessing ergodicity of the mean","volume":"35","author":"Oommen","year":"1985","journal-title":"Informat. Sci."},{"key":"10.1016\/0925-2312(94)00027-P_BIB16","author":"Allen","year":"1978"},{"key":"10.1016\/0925-2312(94)00027-P_BIB17","author":"Isaacson","year":"1976"},{"key":"10.1016\/0925-2312(94)00027-P_BIB18","first-page":"1345","article-title":"On the behavior of the finite automata in random media","volume":"22","author":"Tsetlin","year":"1961","journal-title":"Automat. Telemekh. (USSR)"},{"key":"10.1016\/0925-2312(94)00027-P_BIB19","author":"Tsetlin","year":"1973"},{"key":"10.1016\/0925-2312(94)00027-P_BIB20","first-page":"478","article-title":"Finite learning automata","volume":"10","author":"Tsypkin","year":"1972","journal-title":"Eng. Cybernet."},{"key":"10.1016\/0925-2312(94)00027-P_BIB21","author":"Lakshmivarahan","year":"1981"},{"key":"10.1016\/0925-2312(94)00027-P_BIB22","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1109\/TSSC.1968.300188","article-title":"On expediency and convergence in variable structure automata","volume":"SSC-4","author":"Chandrasekaran","year":"1968","journal-title":"IEEE Trans. Syst. Sci. Cybernet."},{"key":"10.1016\/0925-2312(94)00027-P_BIB23","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1109\/TAC.1973.1100406","article-title":"An optimal learning algotithm for S-model environments","author":"Mason","year":"1973","journal-title":"IEEE Trans. Automatic Control"},{"key":"10.1016\/0925-2312(94)00027-P_BIB24","author":"Chung","year":"1968"},{"key":"10.1016\/0925-2312(94)00027-P_BIB25","author":"Cramer","year":"1970"},{"issue":"6","key":"10.1016\/0925-2312(94)00027-P_BIB26","doi-asserted-by":"crossref","first-page":"1004","DOI":"10.1109\/TSMC.1987.6499311","article-title":"Nonstationary models of learning automata routing in data communication networks","volume":"SMC-17","author":"Nedzelnitski","year":"1987","journal-title":"IEEE Trans. Systems Man Cybernet."},{"key":"10.1016\/0925-2312(94)00027-P_BIB27","series-title":"Proc. 1990 ACM SIGMETRICS","article-title":"Adaptive window flow control and learning algorithms for adaptive routing in data networks","author":"Vasilakos","year":"1990"},{"key":"10.1016\/0925-2312(94)00027-P_BIB28","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1016\/0169-7552(91)90062-H","article-title":"Variable window flow control and ergodic discretized learning algorithms for adaptive routing in data networks","volume":"22","author":"Vasilakos","year":"1991","journal-title":"Comput. Networks ISDN Syst."},{"key":"10.1016\/0925-2312(94)00027-P_BIB29","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TSMC.1983.6313077","article-title":"Neuronlike elements that can solve difficult leatning control problems","volume":"SMC-13","author":"Barto","year":"1983","journal-title":"IEEE Trans. Systems Man Cybernet."},{"key":"10.1016\/0925-2312(94)00027-P_BIB30","first-page":"637","article-title":"A continuous input RAM-Based stochastic neural model","author":"Gorse","year":"1991","journal-title":"Neural Networks"},{"key":"10.1016\/0925-2312(94)00027-P_BIB31","series-title":"Proc. Int. Neural Net. Conf. '90","first-page":"860","article-title":"Reinforcement learning when results are delayed and interleaved in time","author":"Myers","year":"1991"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:092523129400027P?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:092523129400027P?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2019,4,14]],"date-time":"2019-04-14T20:54:55Z","timestamp":1555275295000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/092523129400027P"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1995,4]]},"references-count":31,"journal-issue":{"issue":"3","published-print":{"date-parts":[[1995,4]]}},"alternative-id":["092523129400027P"],"URL":"https:\/\/doi.org\/10.1016\/0925-2312(94)00027-p","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[1995,4]]}}}