Publication detail

Using Q-Learning with LWR in continuous space

VĚCHET, S., MIČEK, P., KREJSA, J.

Original Title

Using Q-Learning with LWR in continuous space

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., MIČEK, P., KREJSA, J.

RIV year

2003

Released

18. 6. 2003

Publisher

Alexander Dubček University of Trenčí, Faculty of Mechatronics

Location

Trenčín

ISBN

80-88914-92-2

Book

Proceedings of 6th international symposium on Mechatronics

Pages from

58

Pages to

61

Pages count

4

BibTex

@inproceedings{BUT8367,
  author="Stanislav {Věchet} and Pavel {Miček} and Jiří {Krejsa}",
  title="Using Q-Learning with LWR in continuous space",
  booktitle="Proceedings of 6th international symposium on Mechatronics",
  year="2003",
  pages="4",
  publisher="Alexander Dubček University of Trenčí, Faculty of Mechatronics",
  address="Trenčín",
  isbn="80-88914-92-2"
}