{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T00:29:53Z","timestamp":1783643393877,"version":"3.55.0"},"reference-count":13,"publisher":"MIT Press - Journals","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Computation"],"published-print":{"date-parts":[[2004,3,1]]},"abstract":"<jats:p> There is a growing interest in using Kalman filter models in brain modeling. The question arises whether Kalman filter models can be used on-line not only for estimation but for control. The usual method of optimal control of Kalman filter makes use of off-line backward recursion, which is not satisfactory for this purpose. Here, it is shown that a slight modification of the linear-quadratic-gaussian Kalman filter model allows the on-line estimation of optimal control by using reinforcement learning and overcomes this difficulty. Moreover, the emerging learning rule for value estimation exhibits a Hebbian form, which is weighted by the error of the value estimation. <\/jats:p>","DOI":"10.1162\/089976604772744884","type":"journal-article","created":{"date-parts":[[2004,2,9]],"date-time":"2004-02-09T23:56:08Z","timestamp":1076370968000},"page":"491-499","source":"Crossref","is-referenced-by-count":11,"title":["Kalman Filter Control Embedded into the Reinforcement Learning Framework"],"prefix":"10.1162","volume":"16","author":[{"given":"Istv\u00e1n","family":"Szita","sequence":"first","affiliation":[{"name":"Department of Information Systems, E\u00f6tv\u00f6s Lor\u00e1nd University, P\u00e1zm\u00e1ny P\u00e9ter s\u00e9t\u00e1ny 1\/C, H-1117 Budapest, Hungary,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andr\u00e1s","family":"L\u0151rincz","sequence":"additional","affiliation":[{"name":"Department of Information Systems, E\u00f6tv\u00f6s Lor\u00e1nd University, P\u00e1zm\u00e1ny P\u00e9ter s\u00e9t\u00e1ny 1\/C, H-1117 Budapest, Hungary,"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","reference":[{"key":"p_5","doi-asserted-by":"publisher","DOI":"10.1038\/nature01171"},{"key":"p_7","doi-asserted-by":"publisher","DOI":"10.1038\/nn887"},{"key":"p_9","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(00)01859-3"},{"key":"p_12","doi-asserted-by":"publisher","DOI":"10.1023\/A:1020262214821"},{"key":"p_13","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065702001187"},{"key":"p_14","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.16-05-01936.1996"},{"key":"p_16","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.19-21-09497.1999"},{"key":"p_18","doi-asserted-by":"publisher","DOI":"10.1016\/S0042-6989(98)00279-X"},{"key":"p_19","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.4.721"},{"key":"p_20","doi-asserted-by":"publisher","DOI":"10.1038\/4580"},{"key":"p_21","doi-asserted-by":"publisher","DOI":"10.1126\/science.275.5306.1593"},{"key":"p_22","doi-asserted-by":"publisher","DOI":"10.1126\/science.271.5257.1870"},{"key":"p_25","doi-asserted-by":"publisher","DOI":"10.1038\/nn963"}],"updated-by":[{"DOI":"10.1162\/neco.2007.19.6.1681","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2007,6,1]],"date-time":"2007-06-01T00:00:00Z","timestamp":1180656000000}}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/089976604772744884","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:51:02Z","timestamp":1615585862000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/16\/3\/491-499\/6886"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2004,3,1]]},"references-count":13,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2004,3,1]]}},"alternative-id":["10.1162\/089976604772744884"],"URL":"https:\/\/doi.org\/10.1162\/089976604772744884","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2004,3,1]]}}}