000004150 001__ 4150
000004150 005__ 20141118153333.0
000004150 04107 $$acze
000004150 046__ $$k2004-05-10
000004150 100__ $$aVěchet, S.
000004150 24500 $$aContinuous Q-learning application

000004150 24630 $$n10.$$pEngineering Mechanics 2004
000004150 260__ $$bInstitute of Thermomechanics AS CR, v.v.i., Prague
000004150 506__ $$arestricted
000004150 520__ $$2eng$$aStandard algorithm of Q-Learning is limited by discrete states and actions and Qfunction is u sually represented as discrete table. To avoid this obstacle and extend the use of Q-learning for continuous states and actions the algorithm must be modified and such modification is presented in the paper. Straightforward way is to replace discrete table with suitable approximator. A number of approximators can be used, with respect to memory and computational requirements the local approximator is particularly favorable. We have used Locally Weighted Regression (LWR) algorithm. The paper discusses advantages and disadvantages of modified algorithm demonstrated on simple control task.

000004150 540__ $$aText je chráněný podle autorského zákona č. 121/2000 Sb.
000004150 653__ $$a

000004150 7112_ $$aEngineering Mechanics 2004$$cSvratka (CZ)$$d2004-05-10 / 2004-05-13$$gEM2004
000004150 720__ $$aVěchet, S.$$iMiček, P.$$iKrejsa, J.
000004150 8560_ $$ffischerc@itam.cas.cz
000004150 8564_ $$s233267$$uhttps://invenio.itam.cas.cz/record/4150/files/T-Vechet-Stanislav.pdf$$y
             Original version of the author's contribution as presented on CD, .
            
000004150 962__ $$r4009
000004150 980__ $$aPAPER