11.
|
Linseed oil was one of the most common natural organic additives used in ancient times. Nevertheless the mechanism and the technology, e.g. effects of different dosages, [...]
|
12.
|
The method of free hexagons belongs to discrete element methods. There are plenty of advantages in comparison with other numerical approaches: the hexagons can cover the [...]
|
13.
|
Motion planning is essential for mobile robot successful navigation. There are many algorithms for motion planning under various constraints. However, in some cases the h [...]
|
14.
|
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 [...]
|
15.
|
A database of carbon dioxide emissions intensity was compiled for environmental life-cycle assessment of construction activities. The database consists of three smaller d [...]
|
16.
|
Abstrakt: A great intention is lately focused on Reinforcement Learning (RL) methods. The article is focused on improving model free RL method known as Q-Iearning algorit [...]
|
17.
|
Modifications of reinforcement learning algorithm, so called continuous action reinforcement learning automaton (CARLA), are presented in this contribution. Automaton lea [...]
|
18.
|
Many structures encountered in civil, mechanical, naval or aerospace engineering can show properties of auto-parametric systems. The general mathematical structure of the [...]
|
19.
|
Algorithm of locally weighted regression is presented in this contribution. Local approximator repeatedly uses the locally linear model based on least square method. Simu [...]
|
20.
|
The pendulum damper modelled as a two degree of freedom strongly non-linear auto-parametric system is investigated using an approximate differential system. Uni-direction [...]
|
21.
|
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 [...]
|
22.
|
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 [...]
|
23.
|
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 [...]
|