000004021 001__ 4021
000004021 005__ 20141118153338.0
000004021 04107 $$acze
000004021 046__ $$k2004-05-10
000004021 100__ $$aBřezina, T.
000004021 24500 $$aUse of continuous action reinforcement learning automata for asynchronous electromotor control

000004021 24630 $$n10.$$pEngineering Mechanics 2004
000004021 260__ $$bInstitute of Thermomechanics AS CR, v.v.i., Prague
000004021 506__ $$arestricted
000004021 520__ $$2eng$$aRelatively unknown reinforcement learning algorithm, so called continuous action reinforcement learning automaton, is presented in this contribution. Automaton learning algorithm is based on rewarding, that gradually evolves set of probability densities. This set is consequently used for action set determination. Simulation study describing learning and behavior of asynchronous electromotor control is further presented. Standard PSD controller is used whose parameter values represent actions of three independent automata. The aim of online learning process is to minimize mean square of control error. Here described learning algorithm is simple to implement, robust to high level of noise.

000004021 540__ $$aText je chráněný podle autorského zákona č. 121/2000 Sb.
000004021 653__ $$a

000004021 7112_ $$aEngineering Mechanics 2004$$cSvratka (CZ)$$d2004-05-10 / 2004-05-13$$gEM2004
000004021 720__ $$aBřezina, T.$$iTurek, M.
000004021 8560_ $$ffischerc@itam.cas.cz
000004021 8564_ $$s476440$$uhttps://invenio.itam.cas.cz/record/4021/files/T-Brezina-Tomas.pdf$$y
             Original version of the author's contribution as presented on CD, .
            
000004021 962__ $$r4009
000004021 980__ $$aPAPER