Control of Dynamics Systems Based on Q-learning
The purpose of the paper is to present an algorithm for solving nonlinear systems control problem based on Q-learning,which is a model-free approach belonging to the adaptive critic family of designs and its advantage over other algorithms of thisfamily is that it does not need a model of the system...
Main Authors: | Anna Filasova, Juraj Klacik, Jan Kasprisin |
---|---|
Format: | Article |
Language: | English |
Published: |
VSB-Technical University of Ostrava
2004-01-01
|
Series: | Advances in Electrical and Electronic Engineering |
Subjects: | |
Online Access: | http://advances.utc.sk/index.php/AEEE/article/view/286 |
Similar Items
-
Q-Learning Based Content Placement Method for Dynamic Cloud Content Delivery Networks
by: Yujie Liu, et al.
Published: (2019-01-01) -
Maximum Power Point Tracking of Photovoltaic System Based on Reinforcement Learning
by: Kuan-Yu Chou, et al.
Published: (2019-11-01) -
Reinforcement Learning Control with Approximation of Time-Dependent Agent Dynamics
by: Kirkpatrick, Kenton
Published: (2013) -
Deep Q-Learning: Theoretical Insights from an Asymptotic Analysis
by: Hullermeier, E., et al.
Published: (2022) -
Improved Q-Learning Algorithm Based on Approximate State Matching in Agricultural Plant Protection Environment
by: Fengjie Sun, et al.
Published: (2021-06-01)