Detail publikace

Using Modified Q-learning With LWR for Inverted Pendulum Control

VĚCHET, S., KREJSA, J., BŘEZINA, T.

Originální název

Using Modified Q-learning With LWR for Inverted Pendulum Control

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

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-learning is the most effective and popular algorithm which belongs to the Reinforcement Learning algorithms group. This algorithm works with rewards and penalties. The most common representation of Q-function is the table. The table must be replaced by suitable approximator if use of continuous states is required. LWR is one of possible approximators. To get the first impression on application of LWR together with modified Q-learning for the control task a simple model of inverted pendulum was created and proposed method was applied on this model.

Klíčová slova

Q-Learning, LWR, Continuous Space

Autoři

VĚCHET, S., KREJSA, J., BŘEZINA, T.

Rok RIV

2003

Vydáno

24. 3. 2003

Nakladatel

Institute of Mechanics of Solids, Brno University of Technology

Místo

Brno

ISBN

80-214-2312-9

Kniha

Mechatronics, Robotics and Biomachanics 2003

Strany od

91

Strany do

92

Strany počet

2

BibTex

@inproceedings{BUT9715,
  author="Stanislav {Věchet} and Jiří {Krejsa} and Tomáš {Březina}",
  title="Using Modified Q-learning With LWR for Inverted Pendulum Control",
  booktitle="Mechatronics, Robotics and Biomachanics 2003",
  year="2003",
  pages="2",
  publisher="Institute of Mechanics of Solids, Brno University of Technology",
  address="Brno",
  isbn="80-214-2312-9"
}