Publication detail

Using Modified Q-learning With LWR for Inverted Pendulum Control

VĚCHET, S., KREJSA, J., BŘEZINA, T.

Original Title

Using Modified Q-learning With LWR for Inverted Pendulum Control

Type

conference paper

Language

English

Original Abstract

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.

Keywords

Q-Learning, LWR, Continuous Space

Authors

VĚCHET, S., KREJSA, J., BŘEZINA, T.

RIV year

2003

Released

24. 3. 2003

Publisher

Institute of Mechanics of Solids, Brno University of Technology

Location

Brno

ISBN

80-214-2312-9

Book

Mechatronics, Robotics and Biomachanics 2003

Pages from

91

Pages to

92

Pages count

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"
}