000004085 001__ 4085
000004085 005__ 20141118153336.0
000004085 04107 $$acze
000004085 046__ $$k2004-05-10
000004085 100__ $$aMarada, T.
000004085 24500 $$aDetermination of Q-function optimum grid applied on asynchronous electric motor control task

000004085 24630 $$n10.$$pEngineering Mechanics 2004
000004085 260__ $$bInstitute of Thermomechanics AS CR, v.v.i., Prague
000004085 506__ $$arestricted
000004085 520__ $$2eng$$aAsynchronous electric motor control task can be successfully solved using reinforcement learning based method called Q-learning. The main problem to solve is the convergence speed. Two-phase Q-learning can be used to speed up the learning process. Efficient prelearning phase uses mathematical model and next phase using for tutorage real system. This method can increase learning speed significantly. When the table is used as Q-function approximation, the learning speed and precision of found controllers depend highly on the Q-function table grid properties. The paper is focused on finding the optimal division of grid.

000004085 540__ $$aText je chráněný podle autorského zákona č. 121/2000 Sb.
000004085 653__ $$aAsynchronní elektromotor, Q-učení, řízení

000004085 7112_ $$aEngineering Mechanics 2004$$cSvratka (CZ)$$d2004-05-10 / 2004-05-13$$gEM2004
000004085 720__ $$aMarada, T.$$iSingule, V.$$iBřezina, T.
000004085 8560_ $$ffischerc@itam.cas.cz
000004085 8564_ $$s269220$$uhttps://invenio.itam.cas.cz/record/4085/files/T-Marada-Tomas.pdf$$y
             Original version of the author's contribution as presented on CD, .
            
000004085 962__ $$r4009
000004085 980__ $$aPAPER