Q-learning used for control of AMB: reduced state definition.

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61388998%3A_____%2F02%3A51020020" target="_blank" >RIV/61388998:_____/02:51020020 - isvavai.cz</a>

Alternative codes found

RIV/00216305:26210/02:PU30863

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Q-learning used for control of AMB: reduced state definition.

Original language description

Previous work showed that stochastic strategy improved model free RL method known as Q-learning used on active magnetic bearing (AMB) model. So far the position, velocity and acceleration were used to describe the state of the system. This paper shows simplified version of controller which uses reduced state definition - position and velocity only. Furthermore the controlled initial conditions domain and its development during learning are shown.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

JD - Use of computers, robotics and its application

OECD FORD branch

—

Project

<a href="/en/project/GA101%2F00%2F1471" target="_blank" >GA101/00/1471: Stability and control of rotors on magnetic bearings</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year

2002

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Mendel 2002.

ISBN

80-214-2135-5

ISSN

—

e-ISSN

—

Number of pages

6

Pages from-to

1-6

Publisher name

VUT

Place of publication

Brno

Event location

Brno [CZ]

Event date

Jun 5, 2002

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—