1.
|
The retrofitting of heritage buildings represents a significant opportunity to reduce the carbon footprint of our built environment. Within the retrofit process, the desi [...]
|
2.
|
Locally Weighted Learning (LWR) is a class of approximations, based on a local model. In this paper we demonstrate using LWR together with Q-learning for control tasks. Q [...]
|
3.
|
Algorithm of locally weighted regression is presented in this contribution. Local approximator repeatedly uses the locally linear model based on least square method. Simu [...]
|
4.
|
Ventilation-control design was applied to a synchronous machine with a single exterior ventilation source. Control of this machine's ventilation, and thus its cooling as [...]
|
5.
|
In this paper, the properties of the current control loop of linear synchronous motors are described. There are shown root loci, time delay of a PWM and influence of the [...]
|
6.
|
Donát, M.
The electromechanical interaction in rotating electric machines induces additional forces between the rotor and the stator. A simple electromechanical computational model [...]
|
7.
|
Q-learning is the most popular and effective version of Reinforcement Learning algorithms. In this paper we discuss the possibility of control of a nonstationary system b [...]
|
8.
|
The paper presents an analysis of vibration of electromechanics system consisting of a 1DOF vibrating mechanical subsystem connected by means of spring and crank mechanis [...]
|
9.
| |
10.
|
Concrete is represented as a two-phase material in this paper. Behaviour of a crack with its tip on the interface between two different materials - hardened cement paste [...]
|
11.
|
Půst, L.
The more precise mathematical models of dynamic systems must contain also more exact description of sources of excitations. The paper deals with the analysis of electric [...]
|
12.
|
Marada, Tomáš
Abstrakt: Tento článek obsahuje numerické experimenty, popisujicí nastaveni parametrů Q-učeni pro řízeni asynchronniho elektromotoru. Citem je stanovit velikost a [...]
|
13.
|
Q-learning method proved to be usable in active magnetic bearing (AMB) control task, however the learning speed remains the main problem. Two-phase variant of the Q-learn [...]
|
14.
|
Modifications of reinforcement learning algorithm, so called continuous action reinforcement learning automaton (CARLA), are presented in this contribution. Automaton lea [...]
|
15.
|
Asynchronous electric motor control task can be successfully solved using reinforcement learning based method called Q-learning. The main problem to solve is the converge [...]
|