Kalman filter control in the reinforcement learning framework

Simple item page
dc.creatorSzita, Istvan
dc.creatorLorincz, Andras
dc.date2003-01-09
dc.date.accessioned2026-07-07T03:19:20Z
dc.date.available2026-07-07T03:19:20Z
dc.descriptionThere is a growing interest in using Kalman-filter models in brain modelling. In turn, it is of considerable importance to make Kalman-filters amenable for reinforcement learning. In the usual formulation of optimal control it is computed off-line by solving a backward recursion. In this technical note we show that slight modification of the linear-quadratic-Gaussian Kalman-filter model allows the on-line estimation of optimal control and makes the bridge to reinforcement learning. Moreover, the learning rule for value estimation assumes a Hebbian form weighted by the error of the value estimation.
dc.description4 pages
dc.identifierhttps://arxiv.org/abs/cs/0301007
dc.identifierhttp://arxiv.org/abs/cs/0301007
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/31421
dc.subjectMachine Learning
dc.subjectArtificial Intelligence
dc.subjectI.2.6; I.2.8
dc.titleKalman filter control in the reinforcement learning framework
dc.typetext

Files

Collections

arXiv